Videos uploaded by user “CodeEmporium”
Mask Region based Convolution Neural Networks - EXPLAINED!
In this video, we will take a look at new type of neural network architecture called "Masked Region based Convolution Neural Networks", Masked R-CNN for short. And in the process, highlight some key sub problems in computer vision. Please SUBSCRIBE to the channel for more content on Machine Learning, Deep Learning, Data Science, and Artificial Intelligence. Hoping to build a community of AI geeks. You'll fit right in! REFERENCES Main paper: https://arxiv.org/pdf/1703.06870v3.pdf Code: https://github.com/facebookresearch/Detectron Convolution Neural networks: https://www.youtube.com/watch?v=m8pOnJxOcqY Semantic segmentation in deep learning: http://blog.qure.ai/notes/semantic-segmentation-deep-learning-review Top papers: http://www.arxiv-sanity.com/top?timefilter=alltime&vfilter=all Recurrent Instance Segmentation: http://www.robots.ox.ac.uk/~tvg/publications/2016/RIS7.pdf Mask R-CNN Presentation by the Author: https://www.youtube.com/watch?v=g7z4mkfRjI4 Mark Jay's Video: https://www.youtube.com/watch?v=2TikTv6PWDw COCO dataset: http://cocodataset.org/#home Fully Convolutional Networks: https://people.eecs.berkeley.edu/~jonlong/long_shelhamer_fcn.pdf Faster R-CNN explained: https://medium.com/@smallfishbigsea/faster-r-cnn-explained-864d4fb7e3f8 Notes/summary of Masked R-CNN: http://www.shortscience.org/paper?bibtexKey=journals/corr/HeGDG17#aleju Music at : https://www.bensound.com/royalty-free-music/track/tenderness
Views: 15085 CodeEmporium
Attention in Neural Networks
In this video, we discuss Attention in neural networks. We go through Soft and hard attention, discuss the architecture with examples. SUBSCRIBE to the channel for more awesome content! My video on Generative Adversarial Networks: https://www.youtube.com/watch?v=O8LAi6ksC80 My video on Convolution Neural Networks: https://www.youtube.com/watch?v=m8pOnJxOcqY REFERENCES Show attend and tell (Image Captioning): https://arxiv.org/pdf/1502.03044.pdf What is attention: https://blog.heuritech.com/2016/01/20/attention-mechanism/ Attention is all you need: https://arxiv.org/pdf/1706.03762v5.pdf Nice blog on Attention: http://www.wildml.com/2016/01/attention-and-memory-in-deep-learning-and-nlp/ Feed Forward + Attention can solve problems: https://arxiv.org/pdf/1512.08756.pdf Teaching Machines to Read and Comprehend: https://arxiv.org/pdf/1506.03340.pdf
Views: 12785 CodeEmporium
Depthwise Separable Convolution - A FASTER CONVOLUTION!
In this video, I talk about depthwise Separable Convolution - A faster method of convolution with less computation power & parameters. We mathematically prove how it is faster, and discuss applications where it is used in modern research. If you liked that video, hit that like button. If you wanna stick around, hit that subscribe button. If you really wanna stick around, hit that bell icon next to the subscribe button to be notified of my uploads immediately. Convolution Neural Networks: https://www.youtube.com/watch?v=m8pOnJxOcqY REFERENCES Xception (main paper): https://arxiv.org/pdf/1610.02357.pdf Mobile Nets (Efficient CNN for mobile vision applications) : https://arxiv.org/pdf/1704.04861.pdf One model Learns all: https://arxiv.org/pdf/1706.05137v1.pdf Music at : https://www.bensound.com/royalty-free-music/track/tenderness
Views: 9071 CodeEmporium
Precision, Recall & F-Measure
In this video, we discuss performance measures for Classification problems in Machine Learning: Simple Accuracy Measure, Precision, Recall, and the F (beta)-Measure. We explain the concepts in detail, highlighting differences between the terms, introducing Confusion Matrices, and analyzing real world examples. If you like the video, please SHARE. Don't forget to like, comment and SUBSCRIBE on your way out! If you have any questions, feel free to contact me. Email: [email protected]
Views: 7801 CodeEmporium
Deep Learning on the Cloud - GPU TO LEARN FASTER
We talk about how you can train your models on the cloud with a p2.xlarge instance, leveraging GPU computation power. If you like the video, like and SUBSCRIBE to the channel for more amazing content! LINKS Create an account: https://aws.amazon.com Instances & AMI: https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/ec2-instances-and-amis.html
Views: 3397 CodeEmporium
Logistic Regression - THE MATH YOU SHOULD KNOW!
In this video, we are going to take a look at a popular machine learning classification model -- logistic regression. We will also see the math you need to know. My linear regression video: https://www.youtube.com/watch?v=K_EH2abOp00 Music at: https://www.bensound.com/royalty-free-music/track/tenderness SUBSCRIBE to my channel for more amazing content!
Views: 6073 CodeEmporium
Generative Adversarial Networks - FUTURISTIC & FUN AI !
I talk about Generative Adversarial Networks, how it works, fun applications and it’s types. If you liked the video, click that like button and SUBSCIBE for more content on Data Sciences, Machine Learning & Deep Learning. Follow me on QUORA for my answers to interesting questions on Data Sciences, Machine Learning, Programming & AI: https://www.quora.com/profile/Ajay-Halthor Music at: https://www.bensound.com/royalty-free-music/track/tenderness LINKS TO INTERESTING APPLICATIONS Progressive Growing of GANs for Improved Quality, Stability, and Variation: https://www.youtube.com/watch?v=XOxxPcy5Gr4 Pix2Pix: https://affinelayer.com/pixsrv/ Face Synthesis from Visual Attributes via Sketch using Conditional VAEs and GANs: https://arxiv.org/pdf/1801.00077.pdf LINKS TO PAPERS & BLOG POSTS Good Introduction to GANs: https://robotronblog.com/2017/09/05/gans/ Detailed overview of GANs & Types: http://guimperarnau.com/blog/2017/03/Fantastic-GANs-and-where-to-find-them#wassGANs About the loss function: https://danieltakeshi.github.io/2017/03/05/understanding-generative-adversarial-networks/ Deep Convolutional GANs: https://arxiv.org/pdf/1511.06434.pdf Deconvolutional Networks: http://www.matthewzeiler.com/wp-content/uploads/2017/07/cvpr2010.pdf Conditional GANs: : https://arxiv.org/pdf/1411.1784.pdf InfoGAN: https://arxiv.org/abs/1606.03657 More Accessable blog: http://aiden.nibali.org/blog/2016-12-01-implementing-infogan/ Wasserstein GANs (original paper): https://arxiv.org/pdf/1701.07875.pdf Accessible blog : https://www.alexirpan.com/2017/02/22/wasserstein-gan.html Text to Image Synthesis with StackGAN: https://arxiv.org/pdf/1612.03242.pdf
Views: 3834 CodeEmporium
Sound play with Convolution Neural Networks
In this video, I talk about processing audio using a convolutional Neural Network and discriminate environmental sounds. Code: https://github.com/ajhalthor/audio-classifier-convNet Convolution Neural Networks: https://www.youtube.com/watch?v=m8pOnJxOcqY Generative Adversarial Networks: https://www.youtube.com/watch?v=O8LAi6ksC80 Audio dataset: https://serv.cusp.nyu.edu/projects/urbansounddataset/download-urbansound8k.html REFERENCES Reference Research Paper: https://arxiv.org/pdf/1608.04363.pdf Generate waveforms from WAV files: http://convert.ing-now.com/
Views: 4064 CodeEmporium
Linear Regression and Multiple Regression
In this video, I will be talking about a parametric regression method called “Linear Regression” and it's extension for multiple features/ covariates, "Multiple Regression". You will gain an understanding of how to estimate coefficients using the least squares approach (scalar and matrix form) - fundamental for many other statistical learning methods. If you thought this content was useful, SHARE it with your friend – you know, the one with the stats exam tomorrow and trying to binge watch YouTube tutorials. SUBSCRIBE to my channel for more amazing content! More on Matrix Calculus: https://atmos.washington.edu/~dennis/MatrixCalculus.pdf
Views: 33155 CodeEmporium
Convolution Neural Networks - EXPLAINED
In this video, we talk about Convolutional Neural Networks. Give the video a thumbs up and hit that SUBSCRIBE button for more awesome content. Code to demonstrate Equivariance wrt Translation: https://github.com/ajhalthor/cnn-notes/blob/master/trans_conv_combined.py My video on Generative Adversarial Networks: https://www.youtube.com/watch?v=O8LAi6ksC80 Questions? : [email protected] Music at: https://www.bensound.com/royalty-free-music/track/tenderness REFERENCES First CNN Paper: http://yann.lecun.com/exdb/publis/pdf/lecun-01a.pdf The Deep Learning Book for details: http://www.deeplearningbook.org/contents/convnets.html DCGAN Paper: https://arxiv.org/abs/1511.06434 About CNNs : https://cambridgespark.com/content/tutorials/convolutional-neural-networks-with-keras/index.html Flatten Vs. FC1: https://alexisbcook.github.io/2017/global-average-pooling-layers-for-object-localization/ Diffference between CNN & MLP: https://www.quora.com/What-is-the-difference-between-a-convolutional-neural-network-and-a-multilayer-perceptron Nine Deep learning papers you should know about: https://adeshpande3.github.io/adeshpande3.github.io/The-9-Deep-Learning-Papers-You-Need-To-Know-About.html Global Average Pooling (GAP) Layers: https://alexisbcook.github.io/2017/global-average-pooling-layers-for-object-localization/ Equivariance: https://arxiv.org/pdf/1411.5908.pdf CNN slides based on the deep learning book (birds eye read): http://www.cedar.buffalo.edu/~srihari/CSE676/9.2%20CNN-Motivation.pdf Google's Deep Mind Learns how to walk: https://www.youtube.com/watch?v=gn4nRCC9TwQ Generate CNNs visually : https://github.com/yu4u/convnet-drawer Playing Atari with Deep Reinforecemnt Learning: https://arxiv.org/pdf/1312.5602v1.pdf Deep Mind's Q-Learning playing Atari games: https://www.youtube.com/watch?v=V1eYniJ0Rnk
Views: 10102 CodeEmporium
Random Forest Classification
Understand how the machine learning classifier "Random Forests" work the way they do. We also talk about concepts like: - Decision Trees - Bootstrapping - Bagging - Bagged Decision Trees
Views: 553 CodeEmporium
How do I create a Programming Language?  #1
Follow me on Twitter: Ajay Halthor - https://twitter.com/ajhalthor (@ajhalthor) TRANSCRIPT Why Lex & Yacc? or Why Flex & Bison? If you are watching this video, you must be some type of programmer or you may be interested in programming. You may see languages like C, Java, Python, and hundreds of others and wondered at some point of time: How do you create a programming language? We are going to answer that question here and also build our own system that analysis's the declaration section of a C program. A computer language is like any other spoken language. It has it’s own: - tokens - and Grammar Tokens are a set of symbols with their own meaning and are the building blocks for a “language”. Tokens can be lowercase alphabets, uppercase alphabets, punctuation or even special symbols. Every language has it’s own “grammar” as well. This involves the arrangement of the tokens to form something of meaning. So, if tokens can be described as a set of symbols, then it is the grammar that generates phrases and sentences. We can define a phrase as a sequence of 1 or more “word tokens” with the correct part of speech. So, a phrase could be defined as a “adverb with one or more adjectives followed by a noun”. These phrases in turn can be combined to form sentences. By defining various tokens (both single character and multi character) and defining how these tokens should appear, we have have effectively defined the structure of English Language! You can create A-N-Y language you want just by knowing the tokens and the grammar. For programming, instead of word tokens, we would have Keywords, Identifiers, Numbers, and Special symbols as tokens. Now the big question thats on everyone’s mind : How do you implement this? You can generate tokens in a language tool called LEX which is short for “lexical analyser”. In this .l file (or fl file for flex), you generate your own tokens. LEX files are actually converted into C behind the scenes. Once the tokens are defined, how do we define the grammar of our new language? This is done using Yacc or Bison. YACC stands for “Yet another Compiler Compiler”. You take the tokens generated by Lex and pass it to a parser. This parser is written in YACC .Yacc takes a concise description of a grammar and produces a C routine that can parse that grammar. This Yacc parser automatically detects whenever a sequence of input tokens matches one of the rules in the grammar and takes some action as defined. It also detects a syntax error whenever its input does not match any of the rules. I’ve said through this video “We are gonna create a language”. What I actually mean is, we are going to create some “program” that understands a custom set of tokens and grammar or syntax rules. Those familiar with programming will know that this is one task of a “compiler”. Of these 7 phases of compiler design, we are only concerned with the first 3: performing Lexical analysis, syntax analysis and semantic analysis. The lex file will take care of the “lexical analysis” while the yacc file will take care of both syntax and semantic analysis. How exactly does this happen? I’ll explain these 3 phases. SCANNER The source file, which is the C code in this case, is passed to our “Scanner” or “Lexical Analyser” or “Lexer”. This lexer will tokenize this input to generate a stream of tokens. These tokens represent the “alphabets” of our language that are to be recognized and processed. We define these tokens in our Lex file. Note that the lex file is the Scanner Generator. It will create a C program called lex.yy.c and this file is the scanner. PARSER The stream of tokens produced is now fed into a Yacc Parser. The grammar for the sequence of tokens is specified by the parser. A “parse tree” is generated and the program is checked to see if it follows this Context Free Grammar. YACC will generate a C file called y.tab.c which will act as the parser. SEMANTIC ANALYSIS Semantic analysis involves checking if the parse tree constructed follows the rules of language. Lex.yy.c is created from the lex file using LEX, the language tool. While y.tab.c is created from the yacc file using the YACC tool. The YACC tool also generates a harder file y.tab.h which is used by LEX to generate lex.yy.c. The two C files work together to form a Language Processor, which converts the given source code to Compiled or Interpreted Code. Now that you know how lex & yacc work, we are going to install and work with them in the next video.
Views: 28033 CodeEmporium
Some parametric methods, like polynomial regression and Support Vector Machines stand out as being very versatile. This is due to a concept called "Kernelization". In this video, we are going to kernelize linear regression. And show how they can be incorporated in other Algorithms to solve complex problems. If you like this video, hit that like button. If you’re new here, hit that SUBSCRIBE button and ring that bell for notifications! FOLLOW ME Quora: https://www.quora.com/profile/Ajay-Halthor REFERENCES [1] The Kernel Trick: https://people.eecs.berkeley.edu/~jordan/courses/281B-spring04/lectures/lec3.pdf [2] Positive Definite Kernels: https://en.wikipedia.org/wiki/Positive-definite_kernel
Views: 766 CodeEmporium
How I published my 1st Conference Paper!!
In this video, I'll explain how my process of publishing this conference paper in less than 4 minutes! Hope this helps some guys trying to publish their first conference papers. SUBSCRIBE on your way out for more amazing videos. Email: [email protected]
Views: 6100 CodeEmporium
A Cool PubSub Implementation | PubSub Pattern #1
If you are interested in a detailed explanation on every component and how it works, I’m making a MINI SERIES on that! Get the entire code at : https://github.com/ajhalthor/pubsub-application. In a PubSub implementation, we have 3 main elements: - Subscribers: who subscribe to multiple topics of interest - Publishers: who publish or post content on various topics. - PubSub module: which acts as a mediator between publishers and subscribers In the code files: - index.html: has the markup for the publisher and subscriber modules. - styles.css: for the basic styling - scripts.js: has the code for the subscriber and publisher modules . - pubsub.js: has the code for the pubsub module. - package.json: has the list of dependencies to get your code up and running with a simple npm install. For now, we just use: 1. Bootstrap: a CSS framework 2. jQuery: a JavaScript framework 3. and Mustache: Mustache is a Template engine to render HTML.
Views: 2434 CodeEmporium
Deep Mind's AlphaGo Zero - EXPLAINED
We take a look at the best Go player of all time AlphaGo Zero. How does it work? What kind of Neural Network does it use? How does Monte Carlo Tree Search help in Learning? We'll answer these questions in this video. SUBSCRIBE on your way out for more awesome content! REFERENCES Deep mind blog on Alpha Zero: https://deepmind.com/blog/alphago-zero-learning-scratch/ Video on Alhpa Go Zero: https://www.youtube.com/watch?v=tXlM99xPQC8 Alhpa Go: https://deepmind.com/research/alphago/ Top list in forbes: https://www.forbes.com/sites/mariyayao/2018/02/05/12-amazing-deep-learning-breakthroughs-of-2017/#1a81502665db Blog post: https://web.stanford.edu/~surag/posts/alphazero.html Monte Carlo Tree Search: https://en.wikipedia.org/wiki/Monte_Carlo_tree_search MCTS in Go: https://storage.googleapis.com/deepmind-media/alphago/AlphaGoNaturePaper.pdf Alphago Zero Vs Alpha Go: https://www.youtube.com/watch?v=jeVihsgCeeE Tricks that AlphaGo zero used: https://hackernoon.com/the-3-tricks-that-made-alphago-zero-work-f3d47b6686ef MIC REFENCES GAN Image from: https://medium.com/@awjuliani/generative-adversarial-networks-explained-with-a-classic-spongebob-squarepants-episode-54deab2fce39 Thumbnail Background: https://www.upi.com/Odd_News/2016/03/12/Googles-AlphaGo-computer-outplays-board-game-champion/7721457815287/ AlphaGo symbol image in thumbnail: https://www.theinquirer.net/inquirer/news/3019507/googles-deepmind-learns-by-itself-as-alphago-zero-beats-its-predecessor Mario Kart Image: http://mariokart.wikia.com/wiki/Ghosts
Views: 1183 CodeEmporium
Callbacks in Keras
Get the code: https://github.com/ajhalthor/Callbacks-in-Keras Web Scraping with Beautiful Soup and Python: https://www.youtube.com/watch?v=R3XJZAldhYQ Tensorflow version: https://www.youtube.com/watch?v=JqnSoUwahJk Music at: https://www.bensound.com/royalty-free-music/track/tenderness
Views: 1614 CodeEmporium
One Neural network learns EVERYTHING ?!
We explore a neural network architecture that can solve multiple tasks: multimodal Neural Network. We discuss important components and concepts along the way. If you like this video, hit that like button. If you really like this video, hit that SUBSCRIBE button. And if you just love me hit that BELL next to the subscribe button. RELATED VIDEOS [1] Convolution Neural Networks: https://www.youtube.com/watch?v=m8pOnJxOcqY [2] Depthwise Separable Convolution (A Faster Convolution): https://www.youtube.com/watch?v=T7o3xvJLuHk&t=248s [3] Attention in Neural Networks: https://www.youtube.com/watch?v=W2rWgXJBZhU [4] Sound Play with Convolution Neural Networks: https://www.youtube.com/watch?v=GNza2ncnMfA REFERENCES [1]Main paper "One Model to Learn them all": https://arxiv.org/pdf/1706.05137v1.pdf [2] Separable Convolutions (and other types): https://towardsdatascience.com/types-of-convolutions-in-deep-learning-717013397f4d [3] Outrageously large neural networks: https://techburst.io/outrageously-large-neural-network-gated-mixture-of-experts-billions-of-parameter-same-d3e901f2fe05 [4] Mobile Nets, Depthwise Separable Convolution: https://arxiv.org/pdf/1704.04861.pdf [5] Blog post on Depthwise Separable Convolution: https://arxiv.org/pdf/1610.02357.pdf [6] Attention Gan (Microsoft's AttnGAN): https://arxiv.org/abs/1711.10485 [7] Show, attend and tell: https://arxiv.org/pdf/1502.03044.pdf Music at : https://www.bensound.com/royalty-free-music/track/tenderness
Views: 1511 CodeEmporium
Unpaired Image-Image Translation using CycleGANs
We talk about cycle consistent adversarial networks for unpaired image-image translation. Some image-image translation problems include: - Season Transfer - Object Transfiguration - Style transfer - Photo Enhancement If you like the video, hit that like button. Wanna see content like this AI, Machine learning, Deep Learning Data Sciences, hit that SUBSCRIBE button. For instant notifications when I upload, RING that BELL. OTHER COOL VIDEOS - Generative Adversarial Networks: https://www.youtube.com/watch?v=O8LAi6ksC80 - CNN Architectures: https://www.youtube.com/watch?v=m8pOnJxOcqY SOCIAL LINKS Follow me on Quora: https://www.quora.com/profile/Ajay-Halthor Email: [email protected] REFERENCES [1] Main Paper: https://arxiv.org/pdf/1703.10593.pdf [2] Blog for architecture (Code too): https://hardikbansal.github.io/CycleGANBlog/ [3] Architecture borrowed from here: https://cs.stanford.edu/people/jcjohns/papers/eccv16/JohnsonECCV16.pdf [5] ConvNets are PatchGANs: https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix/issues/39 [6] Network Architecture is heavily based on Conditional Adversarial Nets: https://arxiv.org/pdf/1611.07004.pdf [7] pytorch implementation of CycleGAN: https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix
Views: 1618 CodeEmporium
Lets make a Programming Language! | Create Programming Language #2
Follow me on twitter: Ajay Halthor (@ajhalthor) https://twitter.com/ajhalthor Get the code for the entire project : https://github.com/ajhalthor/interpreter INSTALL FLEX & BISON linux: http://ccm.net/faq/30635-how-to-install-flex-and-bison-under-ubuntu macOS: http://stackoverflow.com/questions/31805431/how-to-install-bison-on-mac-osx Windows: http://techapple.net/2014/07/flex-windows-lex-and-yacc-flex-and-bison-installer-for-windows-xp788-1/ SYNTAX HIGHLIGHT FOR SUBLIME TEXT Flex : https://github.com/textmate/lex-flex.tmbundle Bison : https://bitbucket.org/artyom_smirnov/sublime-text-bison-highlighter/src NOTES In this video, we are going to create our own little compiler to validate the declaration and initialization section of a C program. We’ll use 2 language tools: Lex and Yacc (or flex and bison) to accomplish this. In this video, we are going to 1. install flex and bison 2. install syntax highlighting for flex and bison in sublime 3. Explain the code files 4. and run this output on a sample file. The lex file has 3 main parts, separated by “double percentage signs”: The first part is a list of harder files and function definitions encapsulated in “percentage-curly braces”. The second part has the list of acceptable tokens and the final is for some C user defined functions. Like the lex file, yacc file also consists of 3 sections. The first part is a list of harder files and function definitions encapsulated in “percentage-curly braces”. In between the first and second sections, we define the nature of the error message generated by YACC. The second section has the Context free Grammar and the 3rd has User defined functions. Langfunctions.h : Data_Type : character array that holds the data_type for the current declaration statement. noOfIdentifiers : number of identifiers in the input file. clearBuffers() : to clear the value of the datatype stored. storeDataType() : to store the datatype of the current declaration statement. retrieveDataType(): Created to make things look uniform. isDuplicate() : checks if the newly encountered identifier has already been declared before. extractIdentifier() : extracts the name of the array. storeIdentifier() : add the encountered identifier to the list of identifiers. AssignmentError() is called in case an invalid assignment is made DuplicateIdentifierError() is called if the isDuplicate() function returns True in the yacc file. validators.h : isValidAssignment() : checks if the datatype which we pass in from the later part of the yacc file is the same as the current datatype of the identifier. itoa, ftoa and ctoa are used to convert integers, floating point numbers and characters into ascii type. Run the Program: To execute this code, Go to your terminal, enter your working directory and type 4 commands. $ yacc -d syntax2.y $ lex semantics.l $ cc lex.yy.c y.tab.c -o output $ ./output [angle bracket] sample Now that we have the brains of the program setup, I’m gonna try to create a cool GUI in the next video so that it'll actually look like an application. Keep an eye out for that video. If you are new to the channel hit that subscribe button on your way out. Lets see if we can get 10 likes on this video (cmon!!!). PLEEEESSSSEEE. I’ll be a happy dude. :)
Views: 9411 CodeEmporium
Create a Signup Login Page with bootstrap and jQuery
Follow me on Twitter: @ajhalthor This signup-login page was designed keeping 4 user classes in mind: - Student - Teacher - HOD (that is 'Head of Department') - Administration Of course, they can be changed to your liking. FEATURES **Intelligent.** The Fields change depending on the user **Validation.** Provides appropriate validation for various fields. **Database.** Also coupled with the backend database, in case you are working on a similar application **Email.** Comes with the markup for a Welcome Mail! (which i will show later) **Its responsive!** So, it looks good on all mobiles, tablets, laptops and desktops with any orientation. USAGE - The user first signs up. If the password is adequate and the email entered is registered in the database, then a confirmation link is sent. - From this welcome mail, the user activates his account by clicking on the activation link. - They are redirected to the home page - Now the user logs in with their new username and password. FILES check_login.php : It just checks if the user has already logged in. It will go directly to thier page if so. connect.inc.php : Used to connect to the database session.inc.php : starts a session. index.php : contains the markup for the signup-login page login.js : Consists of the validation code for all fields login.php : consists of the backend code for the login form. signup.php : has the backend code for the signup form AND the markup for the welcome email confirm.php : activates the user account and is triggered from the welcome mail You can get this in my GitHub repo : https://github.com/ajhalthor/signup-login-form If you like what you saw, dont for get to SUBSCRIBE. Leave a like here, and on Github. And throw in a comment while you are at it ;)
Views: 102622 CodeEmporium
Everything you need to know about Machine Learning!
Here is an introduction to Machine Learning. Instead of developing algorithms for every task and subtask to solve a problem, Machine Learning involves teaching a computer to teach itself. There are different types of machine learning problems we may come across. TYPES OF MACHINE LEARNING PROBLEMS • Classification : This is the problem of categorizing samples or objects into a fixed number of predefined groups. • Regression : This involves predicting a value for the sample. • Clustering : Categorization with predefined labels TYPES OF MACHINE LEARNING ALGORITHMS • Supervised Learning : involves training your machine by supplying features of numerous samples and the corresponding labels. This is used to build statistical models that can determine the label of any new input sample. All Classification and regression problems are solved with supervised learning algorithms. Examples : Logistic Regression, Support Vector Machines, Decision Trees, Random Forests, Neural Networks • Unsupervised Learning : The goal is to have the computer learn how to do something that we don't tell it how to do! Unlike the supervised learning approach, Unsupervised learning has no labeled training data. There are no predefined groups in which objects are classified in a classification problem. Clustering problems are solved with Unsupervised learning. Examples : Hierarchical clustering, k-Means clustering, Gaussian mixture models, Self-organizing maps, Hidden Markov models. • Semi-Supervised Learning : This is the combination of Supervised and Unsupervised learning approaches. Examples : Self Training, Generative Models, Semi Supervised Support Vector Classification, Graph Based Algorithms Email : [email protected]
Views: 687 CodeEmporium
Build a Text Summarizer in Java
Get the Code here : https://github.com/ajhalthor/text-summarizer Follow me on Twitter : https://twitter.com/ajhalthor Take a look at the original by Shlomi Babluki : http://thetokenizer.com/2013/04/28/build-your-own-summary-tool/ TRANSCRIPT OVERVIEW ALGORITHM 1. Take the full CONTENT and split it into PARAGRAPHS. 2. Split each PARAGRAPH into SENTENCES. 3. Compare every sentence with every other. This is done by Counting the number of common words and then Normalize this by dividing by average number of words per sentence. 4. These intermediate scores/values are stored in an INTERSECTION matrix 5. Create the key-value dictionary - Key : Sentence - Value : Sum of intersection values with this sentence 6. From every paragraph, extract the sentences with the highest score. 7. Sort the selected sentences in order of appearance in the original text to preserve content and meaning. And like that, you have generated a summary of the original text. CLASSES IN JAVA PROJECT 1. Sentence : The entire text is divided into a number of paragraphs and each paragraph is divided into a number of sentences. 2. Paragraph : Every paragraph has a number associated with it and an Array List of sentences. 3. Sentence Comparitor : Compare Sentence objects based on Score 4. SentenceComparatorForSummary : Compare Sentence objects based on position in text. 5. SummayTool : akes care of all the operations from extracting sentences to generating the summary. HOW IS MY SUMMARIZER BETTER THAN THE ORIGINAL ? My text summarizer selects number of sentences from a paragraph depending on the length. This is an improvement over the original text summarizer implementation that only selects 1 sentence per paragraph regardless of length. So, If the author decides to crunch everything into 1 paragraph, then only one sentence would be chosen. In the current implementation, we set it to accept several sentences for larger paragraphs. It delivers cogent summaries for general essays, reviews and publications. RUN THIS PROGRAM $ javac -d bin improved_summary.java $ java -classpath bin improved_summary
Views: 6099 CodeEmporium
Curiosity in AI
Reinforcement learning generally uses a carrot-and-stick approach. Good actions are rewarded and bad actions are punished. But what are the drawbacks of this simple approach? How can we use curiosity to overcome it? Let's find out in this video! REFERENCES [1] Main Paper (Episodic Curiosity through Reachability) : https://arxiv.org/pdf/1810.02274.pdf [2] Blog: https://ai.googleblog.com/2018/10/curiosity-and-procrastination-in.html [3] AI learns to walk: https://deepmind.com/blog/producing-flexible-behaviours-simulated-environments/
Views: 304 CodeEmporium
Build a Web Scraper with Python and Beautiful Soup
Get the Code : https://github.com/ajhalthor/web-scraper We are going to scrape this webpage : http://www.dictionary.com/slideshows/food-idioms?prev=umwords.obviously#nutshell For every slide, we are going to extract: - the word - the pronunciation - and download audio data of the corresponding pronunciation Beautiful Soups is used the scrape the required data for your projects. Hope you guys like this little video. Check out some other videos for come cool stuff. Don’t forget to leave a comment on your way out and subscribe for more amazing videos.
Views: 4063 CodeEmporium
The Evolution of Convolution Neural Networks
From the one that started it all "LeNet" (1998) to the deeper networks we see today like Xception (2017), here are some important CNN architectures you should know. If you like the video, show your support with a like, and SUBSCRIBE for more awesome content on Machine Learning, deep Learning, Data Science and AI MY EQUIPMENT (on a $350 budget) Camera (GoPro Hero 5 Black + 32 GB Memory + Kit): https://goo.gl/V4542j Microphone: https://goo.gl/BxBRcW Pop filter: https://goo.gl/oQTQ8W FOLLOW ME https://www.quora.com/profile/Ajay-Halthor REFERENCES [1] LeNet-5 (the start of it all): http://yann.lecun.com/exdb/publis/pdf/lecun-01a.pdf [2] Nice Blog post: https://towardsdatascience.com/neural-network-architectures-156e5bad51ba [3] CNN Architectures: http://slazebni.cs.illinois.edu/spring17/lec01_cnn_architectures.pdf [4] ImageNet - The data that transformed AI research: https://qz.com/1034972/the-data-that-changed-the-direction-of-ai-research-and-possibly-the-world/ [5]Imagenet (main paper): https://www.researchgate.net/publication/221361415_ImageNet_a_Large-Scale_Hierarchical_Image_Database [6] AlexNet: https://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks.pdf [7] Difference between saturating & non-saturating nonlinearities: https://stats.stackexchange.com/questions/174295/what-does-the-term-saturating-nonlinearities-mean [8] Top-1 accuracy Vs Top-5 Accuracy. What do they mean? https://stats.stackexchange.com/questions/156471/imagenet-what-is-top-1-and-top-5-error-rate [9] OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks: https://arxiv.org/abs/1312.6229 [10] Network in Network (NiN) Architecture: https://arxiv.org/abs/1312.4400 [11] GoogleNet: https://arxiv.org/pdf/1409.4842.pdf [12] R-CNN: https://arxiv.org/abs/1311.2524 [13] ResNet: https://arxiv.org/abs/1512.03385 [14] An Overview of ResNet and its Variants: https://towardsdatascience.com/an-overview-of-resnet-and-its-variants-5281e2f56035 [15] Xception: Deep Learning with Depthwise Separable Convolutions: https://arxiv.org/abs/1610.02357
Views: 2096 CodeEmporium
Neural Voice Cloning
In this video, we take a look at a paper released by Baidu on Neural Voice Cloning with a few samples. The idea is to “clone” an unseen speaker’s voice with only a few sound clips. If you like the video, hit that like button. Ring the bell to stay notified of my videos on Machine Learning, Deep Learning, Data Sciences and AI. main paper: https://arxiv.org/abs/1802.06006 Check out the audio demos: https://audiodemos.github.io/ MY EQUIPMENT (on a $350 budget) Camera (GoPro Hero 5 Black + 32 GB Memory + Kit): https://goo.gl/V4542j Microphone: https://goo.gl/BxBRcW Pop filter: https://goo.gl/oQTQ8W FOLLOW ME https://www.quora.com/profile/Ajay-Halthor
Views: 5457 CodeEmporium
How to structure a Tensorflow Neural Network in 7 minutes
In this video, We are going to take a look at the basic structure of a tensorflow program for constructing a deep neural network. We'll also take a look at the tensorboard for scalars and computation graph. If you liked the video, please SUBSCRIBE for more amazing content. Get the code on Github: https://github.com/ajhalthor/Structure-Tensorflow-Neural-Network Email : [email protected] Amazing heavy metal intermission: https://www.youtube.com/watch?v=k6Ex2aJirzw More Resources: Dropout : https://www.cs.toronto.edu/~hinton/absps/JMLRdropout.pdf Adam Optimizer: https://arxiv.org/pdf/1412.6980v8.pdf
Views: 514 CodeEmporium
Bootstrapping, Bagging and Random Forests
Determine if a person is “Male” or “Female” by just looking their name using python 3.6. A Random Forest Classifier is trained to generate a gender classification model. Some of the initial Characteristics of a name considered : • First letter of the name • Second Letter • Last Letter of the name • Second from last Letter • Frequency of each alphabet in the name : that is the number of times each alphabet occurs in the name. • Frequency of alphabet pairs : which is the number of times alphabet pairs ‘AA’ or ‘BA’ occur. and the From this list, 806 features are generated and a performance of 82% is obtained with NLTK's name corpus. NLTK is the Natural Language Processing Toolkit. We perform "Feature Engineering" to determine an optimal subset of these features. The top features considered are : • Check if Name ends with A • Frequency of A • Check if Name ends with E • Check if Second character from Last is N Using these 4 features alone, we get an accuracy of up to 75% for this name corpus of 10,000 names (5000 male and female names). Performance can be increased further by : • Additional feature engineering • Parameter tuning for your Random Forest Model • Appropriate characteristic selection for names Remember that the type of names choosen for training and testing also determine performance. Names of a specific region are similar, so training against such names should yield a higher classification accuracy. Get the Code : https://github.com/ajhalthor/gender-classification-random-forest Get the Notebook : https://nbviewer.jupyter.org/github/ajhalthor/gender-classification-random-forest/blob/master/notebooks/main.ipynb Email: [email protected] SOME GOOD READS: - Bootstrapping example : https://www.thoughtco.com/example-of-bootstrapping-3126155 - Bootstrapping, Bagging : https://nititek.wordpress.com/2013/12/10/bootstrapping/ - Advantages of Random Forests : https://medium.com/rants-on-machine-learning/the-unreasonable-effectiveness-of-random-forests-f33c3ce28883 - Tuning Random Forest : https://www.analyticsvidhya.com/blog/2015/06/tuning-random-forest-model/ - What is One Hot Encoding : https://www.quora.com/What-is-one-hot-encoding-and-when-is-it-used-in-data-science - This guy got 80% with 3 features, worth checking out : http://blog.ayoungprogrammer.com/2016/04/determining-gender-of-name-with-80.html/ And thats it! Hit that like button on your way out and SUBSCRIBE for more videos!
Views: 1626 CodeEmporium
K-Means Clustering - EXPLAINED!
This video is going to be divided into 3 parts: • High level intuition of what K-Means is, what it does and the algorithm. • K-means in math notation • Code an image compressor. Code for image compression: https://github.com/ajhalthor/kmeans-image-compression FOLLOW ME : https://www.quora.com/profile/Ajay-Halthor If you like the video, hit that like button. For more content on AI, Machine Learning, Deep Learning and Data Sciences, SUBSCRIBE to my channel!
Views: 537 CodeEmporium
In this video, I am going to talk about the new Tacotron 2- google's the text to speech system that is as close to human speech till date. If you like the video, SUBSCRIBE for more awesome content. Research paper: https://arxiv.org/pdf/1712.05884.pdf Read some of my AI answers on Quora: https://www.quora.com/profile/Ajay-Halthor Music at : https://www.bensound.com/royalty-free-music/track/tenderness
Views: 11150 CodeEmporium
Principal Component Analysis (PCA) - THE MATH YOU SHOULD KNOW!
In this video, we are going to see exactly how we can perform dimensionality reduction with a famous Feature Extraction technique - Principal Component Analysis PCA. We’ll get into the math that powers it REFERENCES [1] Computing Eigen vectors and Eigen values: https://www.scss.tcd.ie/~dahyotr/CS1BA1/SolutionEigen.pdf [2] Diagonalizing a Matrix: http://mathworld.wolfram.com/MatrixDiagonalization.html [3] Step by step diagonalization: https://yutsumura.com/how-to-diagonalize-a-matrix-step-by-step-explanation/#Step_2_Find_the_eigenvalues IMAGE REFERENCES [1] Gene Expression: https://geneed.nlm.nih.gov/topic_subtopic.php?tid=15&sid=22 [2] Graph_plot: https://stats.stackexchange.com/questions/2691/making-sense-of-principal-component-analysis-eigenvectors-eigenvalues/140579#140579 [3] Eigenvecotrs: https://commons.wikimedia.org/wiki/File:Eigenvectors.gif
Views: 568 CodeEmporium
AI creates Image Classifiers…by DRAWING?
In this video, we talk about "Sketch-a-Classifier" released by researchers at the university of London. KEYWORDS 1. Zero Shot Learning 2. Model Regression Networks (MRN) 3. Parametric Model 4. Multilayer Perceptron (MLP) 5. Fully Convolutional Network (FCN) 6. Regression Loss 7. Performance Loss REFERENCES 1. Sketch-a-Classifier (main paper): https://arxiv.org/abs/1804.11182 2. Sketchy: https://www.cc.gatech.edu/~hays/tmp/sketchy-database.pdf 3. Imagenet: https://www-cs.stanford.edu/groups/vision/pdf/ImageNet_CVPR2009.pdf Follow me: https://www.quora.com/profile/Ajay-Halthor Hit that SUBSCRIBE button and ring the bell for instant access to my videos on Machine Learning, Deep Learning, Data Sciences and Artificial Intelligence!
Views: 544 CodeEmporium
But what *is* a Neural Network? - THE MATH YOU SHOULD KNOW!
We'll take a look at how exactly neural networks learn by starting with modeling an objective function through Maximum Likelihood Estimation. We then take a look at neural network training using back propagation and Stochastic gradient descent. FOLLOW ME https://www.quora.com/profile/Ajay-Halthor REFERENCES [1] Neural Netorks and deep learning: http://neuralnetworksanddeeplearning.com/chap2.html [2] Christopher Bishop [3] Machine Learning Basics from the deep Learning book: http://www.deeplearningbook.org/contents/ml.html [4] The principal of Maximum Likelihood: http://suriyadeepan.github.io/2017-01-22-mle-linear-regression/ [5] Stanford Deep Learning Handout: https://web.stanford.edu/class/archive/cs/cs109/cs109.1166/pdfs/41%20DeepLearning.pdf
Views: 848 CodeEmporium
Let's Analyze data with Pandas and Seaborn!
Show some love with a like and SUBSCRIBE to my channel for more awesome content on Machine Learning, Data Sciences, Artificial Intelligence. Get the code & Dataset: https://github.com/ajhalthor/ISIL-Iraq-Terror-Analysis part of speech tag list: https://pythonprogramming.net/natural-language-toolkit-nltk-part-speech-tagging/ Music at: https://www.bensound.com/royalty-free-music/track/tenderness
Views: 737 CodeEmporium
History of Calculus
Everything you need to know about calculus... in 7 minutes. Remember to subscribe and hit that bell. Follow me on Quora: https://www.quora.com/profile/Ajay-Halthor REFERENCES [1] The birth of Calculus (1986): https://www.youtube.com/watch?v=ObPg3ki9GOI [2] Brief History of Calculus: https://www.wyzant.com/resources/lessons/math/calculus/introduction/history_of_calculus [3] Calculus History: https://www.math.uh.edu/~tomforde/calchistory.html [4] Timeline: https://www.math.uh.edu/~tomforde/timeline.html [5] What is Calculus? Definition and History: https://study.com/academy/lesson/what-is-calculus-definition-history.html [6] Controversy: https://www.fitchburgstate.edu/uploads/files/Undergraduate_Research_Conference/Sample-Math-Poster.pdf [7] Babylonian Calculus: https://www.youtube.com/watch?v=Rx-5dCXx1SI&ab_channel=ScienceMagazine [8] Sexagesimal: https://en.wikipedia.org/wiki/Sexagesimal [9] Nice video: https://www.youtube.com/watch?v=rBVi_9qAKTU&ab_channel=ProfessorDaveExplains [10] Timeline of Calculus: https://prezi.com/zp6jszu6xne8/timeline-of-calculus-innovation/ [11] India Vs Newton: https://www.manchester.ac.uk/discover/news/indians-predated-newton-discovery-by-250-years/ [12] Madhava: https://www.storyofmathematics.com/indian_madhava.html [13] Babylonia: https://www.ancient.eu/babylon/ [14] Science and Tech in India: https://web.archive.org/web/20060821195309/http://www.kerala.gov.in/keralcallsep04/p22-24.pdf [15] Article in language you don’t care about: https://web.archive.org/web/20140714203538/http://epapervijayavani.in/Details.aspx?id=14794&boxid=142922796
Views: 180 CodeEmporium
Photo Cropper & Resizer
In this video, we are gonna take a look at a photo cropper & resizer We are going to save and crop a profile photo. Imagine you are logged in. *Click on the image *Add Profile photo *Select an image from your computer and select a cropping region * And presto! Its done !! Lets take a look at the project directory-- index.php : Markup for this cropper images folder : to hold the uploaded image AND the default image when no profile photo is selected photo_crop.html : markup for the modal upload.php : backend that performs the cropping AND resizing script.js : edit image upload parameters, like maximum image file size that you can upload In case you dont know where to start, i've left a number of comments in the code to help you out. The Source code is on gitHub. Do whatever you want with it. https://github.com/ajhalthor/photo-cropper Well, thats it! If you like what you saw, dont forget to like, rate , comment and SUBSCRIBE right here and on GitHub !!
Views: 1112 CodeEmporium
Hypothesis testing with Applications in Data Science
In this video, We talk about a quintessential statistics topic you need to know to know as a data scientist: hypothesis testing. We’ll take a look a description of a hypothesis test and see how we can use this in real applications. If you like the video hit that like button. If you’re new here, welcome. And hit that SUBSCRIBE button. FUN LINKS Concepts on Hypothesis Testing: https://onlinecourses.science.psu.edu/statprogram/reviews/statistical-concepts/hypothesis-testing Non-equidistant data ANOVA: file:///Users/Ajay/Downloads/ejbrm-volume12-issue1-article336.pdf ANOVA on non-normal data: http://www.psicothema.com/pdf/4434.pdf FOLLOW ME Quora : https://www.quora.com/profile/Ajay-Halthor
Views: 219 CodeEmporium
Support Vector Machines - THE MATH YOU  SHOULD KNOW
In this video, we are going to see exactly why SVMs are so versatile by getting into the math that powers it. If you like this video and want to see more content on data Science, Machine learning, Deep Learning and AI, hit that SUBSCRIBE button. And ring that damn bell for notifications when I upload. REFERENCES [1] What is “Primal Form”: https://jeremykun.com/tag/primal/ [2] Duality in Linear Programming: http://web.mit.edu/15.053/www/AMP-Chapter-04.pdf [3] Relationship between primal and dual: https://www3.nd.edu/~dgalvin1/30210/30210_F07/presentations/dual_opt.pdf FOLLOW ME Quora: https://www.quora.com/profile/Ajay-Halthor
Views: 541 CodeEmporium
NPM, Mustache & index.html | PubSub Pattern #2
Get the code for the entire series from my GitHub page: https://github.com/ajhalthor/pubsub-application Get node and npm installed : https://docs.npmjs.com/getting-started/installing-node jQuery is a javaScript library. Proof: http://jquery.com/
Views: 419 CodeEmporium
A/B Testing - Simply Explained
I'm going to walk you through A/B testing. A topic very crucial if you’re working in the data science space. We’re going to walk through the steps to conduct such a test ourselves. A/B test duration Calculator: https://vwo.com/ab-split-test-duration/ If like content like this, hit that like button and SUBSCRIBE for more videos! FOLLOW ME Quora: https://www.quora.com/profile/Ajay-Halthor
Views: 211 CodeEmporium
5 Tips For Getting A Data Science Job
I'm going to go through my 5 tips for data science noobs to get you up and running in the field FOLLOW ME : https://www.quora.com/profile/Ajay-Halthor
Views: 281 CodeEmporium
Data Science in Finance
In this video, we are going to conduct a thorough analysis on data related to customer churn. Hoping this will help you analyze data in Finance in general. Get the code used in video: https://github.com/ajhalthor/customer-churn-analysis Dataset link: https://www.kaggle.com/blastchar/telco-customer-churn FOLLOW ME Quora: https://www.quora.com/profile/Ajay-Halthor Comment on your thoughts below. If you like AI, Data Science, Machine Learning or Deep Learning SUBSCRIBE for more awesome content!
Views: 480 CodeEmporium
Cool jQuery Bootstrap Table
This is a cool jQuery Bootstrap table , particularly for rating and assessment. - Attractive - has a Colored design that makes the table more interactive for users. - Fully Equipped as Comes with a basic page layout with a fixed sidebar and navigation bar . -Uses jQuery for validation and supplies clean transitions. - Completely responsive. So, it looks good on all mobiles, tablets, laptops and desktops with any orientation. Also, it supports Automatic Naming. Each field is given a name depending on what you want displayed. This name is formed by converting the field entry to lowercase and replacing spaces ' ' with hyphens '-'. Eg. A field "Command over Subject" will be automatically named as "command-over-subject". This can be used for further frontend or backend processing. As far as the code is concerned, you only need to modify this part of the index file. You dont really need to touch the rest. You can get this in my GitHub repo : https://github.com/ajhalthor/responsive-jquery-bootstrap-table If you like what you saw, dont for get to SUBSCRIBE. Leave a like here, and on Github. And throw in a comment while you are at it ;)
Views: 791 CodeEmporium
IIFE, Subscriber Module | PubSub Pattern #3
Get the code for the entire project and follow along from my GitHub page: https://github.com/ajhalthor/pubsub-application IIFE - Immediately invoked Function Expression The code executed when a jQuery selector is used : https://j11y.io/jquery/#v=1.10.2&fn=init
Views: 249 CodeEmporium
When will AI take your job?
Ever wondered how fast AI is evolving? When do you think your job will be taken? Let me know your thoughts in the comments below. Source (When will AI exceed Human Performance): https://arxiv.org/pdf/1705.08807.pdf SOCIAL LINKS Follow me on Quora: https://www.quora.com/profile/Ajay-Ha... Email: [email protected]
Views: 273 CodeEmporium
Getting Started with Code Emporium
Hey Guys! I'm Ajay Halthor . And Welcome to Code Emporium. Here, We'll be looking at a number of plugins, addons and applications which you can use. I'll explain the basic features of every project with a demo. And for more information, i'll give you a link to the code and its documentation in the description below each video. Most of them will be on gitHub. GitHub : https://github.com/ajhalthor So, if you want to save time on your projects, Just click the SUBSCRIBE button. You Wont regret it!
Views: 784 CodeEmporium
The GUI for our Interpreter | Create Programming Language #3
Follow on twitter : Ajay Halthor https://twitter.com/ajhalthor (@ajhalthor) Code on Github : https://github.com/ajhalthor/interpreter/tree/master/GUI_Program TRANSCRIPT In the last video, we 1. installed flex and bison 2. installed syntax highlighting for flex and bison in sublime 3. Understood the code the code files 4. and got it running on a sample file. That was the brains of the application. Now, we are going to create an interface where users can choose their sample file. This is gonna be using Java Swings. Some may think its a good choice. Others may disagree. I’ll be using other languages (like python) for future videos. But lets stick to java for now. I’ll first show you how to run this in the eclipse IDE. and then we’ll see how to do the same on the command line. ECLIPSE This project will have 3 classes: SSMain — that contains the main function MyFrame — creates the window frame, the file chooser and the rest of the UI and Listener class— which listens to mouse events and perform the execution of the “output” file Take the output file generated from the compilation of lex.yy.c and y.tab.c and put it in our project directory, on the sample level as the source folder. Before I move any further, I’ll just gloss over the 2 main classes here : MyFrame and Listener. Myframe extends the JFrame class and inherits its properties and methods. - JPanel to give a nice background to the app. - JScrollPane will be used to display the error message. - JLabel is used to display text. We will use it to display the full path of the sample file chosen, on the botton and other places where text is required. - JButton is used to create the file chooser button. In our constructor, we set the initial size of the window to be 500 by 500 pixels. We then instantiate all the elements I just discussed. In the createGUI method , the components are added and positioned on the screen. At the end of the method, we add a mouse listener for the JButton we created. The “listener” is actually the Listener Class, which I’ll explain now. Listener handles 3 major mouse events. a Mouse Click event a Mouse Enter event a mouse exit event When the “Choose File” button is clicked, a file chooser opens up where the user selects their sample file. Once the file is chosen, we execute the typical output command that we use in the terminal in the last video . The response is stored in the message variable and displayed on the screen for the user. setBorderColor method creates a red border and text if an error is displayed. Otherwise, the text and border color are both green. The other 2 mouse events are just used to give a hover effect on the “choose” button for a nice UI. And that all code for the GUI. Now, lets run thing with 4 sample files. Sample_1 : ERROR on line 12: duplicate identifier ‘man’ found Sample_2 : ERROR ON LINE 7 : syntax error, unexpected SEMI_COLON, expecting IDENTIFIER or ARRAY_IDENTIFIER Sample_3 : ERROR ON LINE 1 : Invalid Token -. Sample_4 : No Errors And like that, we have a neat user interface to accompany our little interpreter. COMMAND LINE If you want to execute this program on command line, go to your terminal and enter your project directory. and enter the src folder. Since our main class SSMain is in the package p, we compile it with the command $ javac p/SSMain.java This will generate the corresponding class files. Now, execute it with the command $ java p.SSMain And clearly, everything works the same even without eclipse. So, this will certainly come in useful for people who think eclipse, netbeans or any other java specific IDE is too slow. Hope you guys liked this video and the others before this. If you jumped straight into this video without watching the others and ignored the link to the previous video at the beginning of this video….. then….. just go back and watch that last video. I’ve explained everything there. In any case, Hope you guys liked this video! Please subscribe to my channel. Please. Pretty please. In my last video, I asked for 10 likes. This time, I’m gonna be greedy and ask for 13 likes. 13 come on! Lets hit that unlucky number! If we hit this number, I will give my 13th liker a year supply of —.
Views: 2355 CodeEmporium
DropBlock - A BETTER DROPOUT for Neural Networks
Dropout is a common method of regularization in neural networks. However, it doesn’t work too well in Convolution Neural network Architectures. We are going to understand why this is this case, and offer an alternative approach to regularization: DropBlock. Hit that SUBSCRIBE, ring that BELL, share this content, like and comment down below your video suggestions. I don’t get many so I’ll read them all. FOLLOW ME Quora: https://www.quora.com/profile/Ajay-Halthor REFERENCES [1] DropBlock (Main Paper): https://arxiv.org/pdf/1810.12890v1.pdf [2] Neural Network Playground: https://playground.tensorflow.org [3] AlexNet: https://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks.pdf [4] Pytorch Code for DropBlock: https://github.com/miguelvr/dropblock/blob/master/dropblock/dropblock.py
Views: 268 CodeEmporium
Publisher, PubSub & Add/Remove Modules | PubSub Pattern #4
Get the code for the entire project on GitHub: https://github.com/ajhalthor/pubsub-application
Views: 131 CodeEmporium

Paralegal cover letter tips
Typo in college admissions essay question
Inter cover letter
Most effective cover letter template
Iphone 3gs ios 6.1.6 application letters