• Stars
    star
    1,046
  • Rank 44,062 (Top 0.9 %)
  • Language
    Jupyter Notebook
  • Created almost 8 years ago
  • Updated over 6 years ago

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

Implementations of CNNs, RNNs, GANs, etc

Tensorflow Programs and Tutorials

This repository will contain Tensorflow tutorials on a lot of the most popular deep learning concepts. It'll also contain some experiments on cool papers that I read. Hopefully, the notebooks will be helpful to anyone reading!

  • CNN's with Noisy Labels - This notebook looks at a recent paper that discusses how convolutional neural networks that are trained on random labels (with some probability) are still able to acheive good accuracy on MNIST. I thought that the paper showed some eye-brow raising results, so I went ahead and tried it out for myself. It was pretty amazing to see that even when training a CNN with random labels 50% of the time, and the correct labels the other 50% of the time, the network was still able to get a 90+% accuracy.

  • Character Level RNN (Work in Progress) - This notebook shows you how to train a character level RNN in Tensorflow. The idea was inspired by Andrej Karpathy's famous blog post and was based on this Keras implementation. In this notebook, you'll learn more about what the model is doing, and how you can input your own dataset, and train a model to generate similar looking text.

  • Convolutional Neural Networks - This notebook goes through a simple convolutional neural network implementation in Tensorflow. The model is very similar to the own described in the Tensorflow docs. Hopefully this notebook can give you a better understanding of what is necessary to create and train your own CNNs. For a more conceptual view of CNNs, check out my introductory blog post on them.

  • Generative Adversarial Networks - This notebook goes through the creation of a generative adversarial network. GANs are one of the hottest topics in deep learning. From a high level, GANs are composed of two components, a generator and a discriminator. The discriminator has the task of determining whether a given image looks natural (ie, is an image from the dataset) or looks like it has been artificially created. The task of the generator is to create natural looking images that are similar to the original data distribution, images that look natural enough to fool the discriminator network.For more of a conceptual view of GANs, check out my blog post.

  • Linear and Logistic Regression - This notebook shows you how Tensorflow is not just a deep learning library, but is a library centered on numerical computation, which allows you to create classic machine learning models relatively easily. Linear regression and logistic regression are two of the most simple, yet useful models in all of machine learning.

  • Simple Neural Networks - This notebook shows you how to create simple 1 and 2 layer neural networks. We'll then see how these networks perform on MNIST, and look at the type of hyperparamters that affect a model's accuracy (network architecture, weight initialization, learning rate, etc)

  • Math in Tensorflow - This notebook introduces you to variables, constants, and placeholders in Tensorflow. It'll go into describing sessions, and showinng you how to perform typical mathematical operations and deal with large matrices.

  • Question Pair Classification with RNNs (Work in Progress) - This notebook looks at the newly released question pair dataset released by Quora a little earlier this year. It looks at the ways in which you can build a machine learning model to predict whether two sentences are duplicates of one another. Before running this notebook, it's very important to extract all the data. We'll run the following command to get our word vectors and training/testing matrices.

    tar -xvzf Data/Quora/QuoraData.tar.gz
  • SELU Nonlinearity - A recent paper titled "Self Normalizing Neural Networks" started getting a lot of buzz starting in June 2017. The main contribution of the paper was this new nonlinear activation function called a SELU (scaled exponential linear unit). We'll be looking at how this function performs in practice with simple neural nets and CNNs.

  • Sentiment Analysis with LSTMs - In this notebook, we'll be looking at how to apply deep learning techniques to the task of sentiment analysis. Sentiment analysis can be thought of as the exercise of taking a sentence, paragraph, document, or any piece of natural language, and determining whether that text's emotional tone is positive, negative or neutral. We'll look at why RNNs and LSTMs are the most popular choices for handling natural language processing tasks. Be sure to run the following commands to get our word vectors and training data.

    tar -xvzf Data/Sentiment/models.tar.gz
    tar -xvzf Data/Sentiment/training_data.tar.gz
  • Universal Approximation Theorem (Work in Progress) - The Universal Approximation Theorem states that any feed forward neural network with a single hidden layer can model any function. In this notebook, I'll go through a practical example of illustrating why this theorem works, and talk about what the implications are for when you're training your own neural networks. cough Overfitting cough

  • Learning to Model the XOR Function (Work in Progress) - XOR is one of the classic functions we see in machine learning theory textbooks. The significance is that we cannot fit a linear model to this function no matter how hard we try. In this notebook, you'll see proof of that, and you'll see how adding a simple hidden layer to the neural net can solve the problem.

More Repositories

1

Machine-Learning-Links-And-Lessons-Learned

List of all the lessons learned, best practices, and links from my time studying machine learning
986
star
2

LSTM-Sentiment-Analysis

Sentiment Analysis with LSTMs in Tensorflow
Jupyter Notebook
959
star
3

Facebook-Messenger-Bot

Facebook chatbot that I trained to talk like me using Seq2Seq
Python
705
star
4

Generative-Adversarial-Networks

Tutorial on GANs
Jupyter Notebook
285
star
5

March-Madness-ML

Machine learned bracketology
Python
191
star
6

UCLA-Course-Notes

My notes from the classes I've taken at UCLA
101
star
7

Pandas-Tutorial

Tutorial on Using Pandas
Jupyter Notebook
79
star
8

March-Madness-2017

Kaggle Competition for Predicting NCAA Basketball Tourney Games
Jupyter Notebook
70
star
9

Chatbot-Flask-Server

The Flask server that communicates with my FB Messenger chatbot
Python
58
star
10

Machine-Learning-Notes

Notes for several Machine Learning and Deep Learning courses, textbooks, and talks
56
star
11

MachineLearningReimplementations

Just trying to reimplement machine learning techniques like linear regression, neural nets, logistic regression, etc in Python
Python
32
star
12

NLP-Stuff

Programs with word vectors, RNN, NLP stuff, etc
Jupyter Notebook
18
star
13

Quandl-Machine-Learning

Using the Quandl API to (try) to apply ML to the stock market
Jupyter Notebook
13
star
14

NBA-Data-Visualization

Visualizations of statistics for NBA players
Jupyter Notebook
12
star
15

MLB_Win_Predictor

Neural network that predicts the number of wins for a baseball team based on the importance of different statistical categories and their influence on a team's success.
Lua
11
star
16

Music-Analysis

Trying to apply deep learning to music analysis
Jupyter Notebook
11
star
17

Kaggle-Zillow

Repo for the $1.2 million Kaggle competition
Jupyter Notebook
11
star
18

PyTorch-Programs

Trying out PyTorch because the hype is real
Jupyter Notebook
10
star
19

ReinforcementLearning

A collection of simple RL agents in different environments
Python
10
star
20

Job-Descriptions-Hacker-Rank-Comp

Hackerrank ML Competition
Jupyter Notebook
9
star
21

Kaggle-MNIST

Simple ConvNet to classify digits from the famous MNIST dataset
Python
9
star
22

KaggleTitanic

Kaggle Titanic Survival ML Competition
Python
6
star
23

WalmartLabs-ML-CodeSprint

Hackerrank ML Contest
Python
6
star
24

Two-Sigma-Renting-Listing-Competition

Kaggle Competition for Predicting Interest of New Rental Listings
Jupyter Notebook
6
star
25

OpenAI_Gym_Universe

Playing around with Open AI's reinforcement learning frameworks
Python
6
star
26

MLB

MLB Web App using React
JavaScript
6
star
27

CS-145-Project

CS 145 Yelp Project
Python
4
star
28

Tech-Plus-You-March-Madness

My Machine Learning + March Madness demo for UCLA's Tech+You event
Python
3
star
29

KaggleGhosts

Kaggle Ghosts ML Competition
Jupyter Notebook
2
star
30

Accelerometer-Pogram

Program that reads in accelerometer data (x, y, z direction values), trains a neural network program for classification, and then outputs predictions for a set of test data
Lua
2
star