This repository contains -
✔️ Chapter-wise summarized notes.
✔️ Chapter-wise PDF.
✔️ Chapter-wise codes. (.ipynb files)
✔️ Summarized notes on Udacity's Nanodegree in AI (Bertelsmann Scholarship)

The images in this repository are taken from Udacity's Deep Learning Nanodegree program.

Over the course of time, I have enrolled in multiple MOOCs and read multiple books related to Deep Learning. I try to document all the important notes in one place so that it is easy for me to revise 😊.

Below are the list of projects/theorey that I have worked on/documented. Please see the Project List for the code and refer the Theorey List for the detailed explaination of various concepts.:

1. Recap of Numpy and Matrices

   • Quiz on Numpy
   • Scalars, Vectors, Matrices, Tensors

2. Introduction to PyTorch

   • Deep Learning with PyTorch - 60 minute blitz
   • Verify PyTorch Installation
   • Autograd Automatic Differentiation
   • Single Layer Neural Network
   • Neural Networks
   • Multi-layer Neural Networks
   • Implementing Softmax Function
   • Training an Image Classifier
   • Implementing ReLU Activation Function via PyTorch
   • Playing with TensorBoard
   • Training Neural Network via PyTorch
   • Validation via PyTorch
   • Regularization via PyTorch
   • Loading Image Data via PyTorch
   • Transfer Learning via PyTorch

3. Convolutional Neural Networks

   • Basics: Load, Train, Test and Validate your Model
   • CIFAR Image Classification
   • Object Detection
     • Frontal Face Recognition
     • Object Detection
   • Transfer Learning
     • Bees Prediction via Transfer Learning
     • Flower Prediction via Transfer Learning
   • Style Transfer
     • Style Transfer on an Octopus
     • Style Transfer on Purva
   • Data Augmentation
   • Weight Initialization Strategies
   • Autoencoders
     • Linear Autoencoder
     • Convolutional Autoencoder
   • Dog Breed Classifier

4. Recurrent Neural Networks

   • Text Generation using RNNs
     • Future Anna Karenina Series
     • Future Harry Potter Series
   • Sentiment Analysis
   • Time Series Prediction
   • Word2Vec
   • Generation of T.V. Scripts via NLG
   • Attention

5. Generative Adversarial Networks (GANs)

   • Overview: Theorey
   • Generate Hand Written Digits using GANs
   • Deep Convolutional GANs
   • Cyclic GANs
     • Image-to-Image Translation via Cyclic GANs
   • Generating Faces via DCGAN

6. Deploying Sentiment Analysis Model using Amazon Sagemaker

   • Deploy IMDB Sentiment Analysis Model
   • Deploy Your Own Sentiment Analysis Model

7. Natural Language Processing

   • Naive Bayes Classifier
     • Spam Classifier
     • Sentiment Analysis
   • POS Tagging
     • POS Tagging via HMM and Viterbi Algorithm
     • HMMs for POS Tagging
   • Feature Extraction and Embeddings
     • Word Embeddings
   • Topic Modelling
   • Latent Dirichlet Allocation
   • Sentiment Analysis
     • BERT for sentiment analysis of Twits (StockTwits)
     • EDA and sentiment analysis of COVID-19 tweets
     • EDA and sentiment analysis of Joe Biden's tweets
   • Machine Translation
     • NMT via Basic Linear Algebra
     • NMT via Encoder-Decoder Architecture)
   • Speech Recognition
   • Autocorrect Tool via Minimum Edit Distance
   • Autocomplete tool using n-gram language model
   • Natural Language Generation
     • Text generation via RNNs and (Bi)LSTMs
   • Question Answering Models
     • BERT for answering queries related to stocks
   • Text Classification
     • Github bug prediction using BERT
     • Predicting DJIA movement using BERT
     • SMS spam classifier
   • Siamese Networks
     • Question Duplication

8. Attention Models

   • Neural Machine Translation

This list basically contains summarized notes for each chapter from the book, 'Deep Learning' by 'Goodfellow, Benigo and Courville':

1. Chapter 1: Linear Algebra
2. Chapter 2: Probability and Information Theorey
3. Chapter 3: Numerical Computation
4. Chapter 4: Machine Learning Basics
5. Chapter 5: Deep Forward Networks
   5.1.Chapter 5.1: Back Propogation
6. Chapter 6: Regularization for Deep Learning
7. Chapter 7: Optimization for Training Deep Models
8. Chapter 8: Convolutional Neural Networks
9. Chapter 9: Reccurent Neural Networks
   9.1 Chapter 9.1: LSTMs

• Purva Singh

Please feel free to open a Pull Request to contribute towards this repository. Also, if you think there's any section that requires more/better explanation, please use the issue tracker to let me know about the same.

If you like this repo and find it useful, please consider (★) starring it (on top right of the page) so that it can reach a broader audience.