Header Ads

Free E-book read Online : Deep Learning - The Straight Dope

Free E-book read Online : Deep Learning - The Straight Dope

Deep Learning - The Straight Dope

This repo contains an incremental sequence of notebooks designed to teach deep learning, Apache MXNet (incubating), and the gluon interface. Our goal is to leverage the strengths of Jupyter notebooks to present prose, graphics, equations, and code together in one place. If we’re successful, the result will be a resource that could be simultaneously a book, course material, a prop for live tutorials, and a resource for plagiarising (with our blessing) useful code. To our knowledge there’s no source out there that teaches either (1) the full breadth of concepts in modern deep learning or (2) interleaves an engaging textbook with runnable code. We’ll find out by the end of this venture whether or not that void exists for a good reason.

Another unique aspect of this book is its authorship process. We are developing this resource fully in the public view and are making it available for free in its entirety. While the book has a few primary authors to set the tone and shape the content, we welcome contributions from the community and hope to coauthor chapters and entire sections with experts and community members. Already we’ve received contributions spanning typo corrections through full working examples.

Part 1: Deep Learning Fundamentals

Crash course

  • Preface
  • Introduction
  • Manipulate data the MXNet way with ndarray
  • Linear algebra
  • Intermediate linear algebra
  • Probability and statistics
  • Automatic differentiation with autograd

Introduction to supervised learning

  • Linear regression from scratch
  • Linear regression with gluon
  • Binary classification with logistic regression
  • Multiclass logistic regression from scratch
  • Multiclass logistic regression with gluon
  • Overfitting and regularization
  • Overfitting and regularization (with gluon)
  • The Perceptron
  • Environment

Deep neural networks

  • Multilayer perceptrons from scratch
  • Multilayer perceptrons in gluon
  • Faster modeling with gluon.nn.Sequential
  • Dropout regularization from scratch
  • Dropout regularization with gluon
  • Plumbing: A look under the hood of gluon
  • Designing a custom layer with gluon
  • Serialization - saving, loading and checkpointing

Convolutional neural networks

  • Convolutional neural networks from scratch
  • Convolutional Neural Networks in gluon
  • Deep convolutional neural networks
  • Very deep networks with repeating elements
  • Batch Normalization from scratch
  • Batch Normalization in gluon

Recurrent neural networks

  • Recurrent Neural Networks (RNNs) for Language Modeling
  • Long short-term memory (LSTM) RNNs
  • Gated recurrent unit (GRU) RNNs
  • Recurrent Neural Networks with gluon


  • Introduction
  • Gradient descent and stochastic gradient descent from scratch
  • Gradient descent and stochastic gradient descent with Gluon
  • Momentum from scratch
  • Momentum with Gluon
  • Adagrad from scratch
  • Adagrad with Gluon
  • RMSprop from scratch
  • RMSprop with Gluon
  • Adadelta from scratch
  • Adadelta with Gluon
  • Adam from scratch
  • Adam with Gluon

High-performance and distributed training

  • Fast, portable neural networks with Gluon HybridBlocks
  • Training with multiple GPUs from scratch
  • Training on multiple GPUs with gluon
  • Distributed training with multiple machines

Part 2: Applications

Computer vision

  • Object Detection Using Convolutional Neural Networks
  • Transfering knowledge through finetuning
  • Visual Question Answering in gluon

Natural language processing

  • Tree LSTM modeling for semantic relatedness
  • Recommender systems
  • Introduction to recommender systems

Time series

  • Linear Dynamical Systems with MXNet
  • Filtering
  • Generating Synthetic Dataset
  • Exponential Smoothing and Innovation State Space Model (ISSM)
  • Filtering

Part 3: Advanced Topics

Generative adversarial networks

  • Generative Adversarial Networks
  • Deep Convolutional Generative Adversarial Networks
  • Pixel to Pixel Generative Adversarial Networks

Variational methods

  • Bayes by Backprop from scratch (NN, classification)
  • Bayes by Backprop with gluon (NN, classification)

Click on this link to view the e-Book  : Free E-book read Online : Deep Learning - The Straight Dope

No comments

Powered by Blogger.