Skip to content

Latest commit

 

History

History
706 lines (551 loc) · 50.6 KB

Deep-Learning-TensorFlow.md

File metadata and controls

706 lines (551 loc) · 50.6 KB
Raw

Deep Learning Using TensorFlow

Lecturer: Hossein Hajiabolhassan
Data Science Center, Shahid Beheshti University

Index:

Course Overview:

In this course, you will learn the foundations of Deep Learning, understand how to build 
neural networks, and learn how to lead successful machine learning projects. You will learn 
about Convolutional networks, RNNs, LSTM, Adam, Dropout, BatchNorm, and more.

Main TextBooks:

Book 1 Book 2 Book 3 Book 4 Book 5

Main TextBooks:

Additional TextBooks:

Slides and Papers:

Recommended Slides & Papers:

  1. Introduction

Required Reading:

Suggested Reading:

Additional Resources:
  • Video of lecture by Ian Goodfellow and discussion of Chapter 1 at a reading group in San Francisco organized by Alena Kruchkova
  • Paper: On the Origin of Deep Learning by Haohan Wang and Bhiksha Raj 
Applied Mathematics and Machine Learning Basics:

  1. Toolkit Lab 1: Google Colab and Anaconda

Required Reading:

Suggested Reading:

Additional Resources:

  1. Toolkit Lab 2: Image Preprocessing by Keras

Required Reading:

Suggested Reading:

Additional Resources:

  1. Deep Feedforward Networks

Required Reading:

Interesting Questions:

Suggested Reading:

Additional Resources:

  1. Toolkit Lab 3: Introduction to Artificial Neural Networks with Keras

Required Reading:

Suggested Reading:

Additional Resources:

Building Dynamic Models Using the Subclassing API:

  1. Regularization for Deep Learning

Required Reading:

Suggested Reading:

Additional Reading:

  1. Optimization for Training Deep Models

Required Reading:

Suggested Reading:

Additional Reading:

  1. Toolkit Lab 4: Training Deep Neural Networks

Required Reading:

Suggested Reading:

Additional Resources:

  1. Toolkit Lab 5: Custom Models and Training with TensorFlow 2.0

Required Reading:

Suggested Reading:

Additional Resources:

TensorFlow 1.0:
  • To Learn TensorFlow 1.0, Check the Section of TensorFlow-1.

  1. Convolutional Networks

Required Reading:

Suggested Reading:

Additional Reading:  

Fourier Transformation:

  1. Toolkit Lab 6: TensorBoard

TensorBoard:

Suggested Reading:

Additional Reading:

  1. Sequence Modeling: Recurrent and Recursive Networks

Required Reading:

Suggested Reading:

Additional Reading:

  1. Practical Methodology

Required Reading:

Suggested Reading:

Additional Reading:

  1. Applications

Required Reading:

Suggested Reading:

Additional Reading:

  1. Autoencoders

Required Reading:

Suggested Reading:

Additional Reading:

  1. Generative Adversarial Networks

Required Reading:

Slide: Generative Adversarial Networks (GANs) by Binglin, Shashank, and Bhargav
Paper: NIPS 2016 Tutorial: Generative Adversarial Networks by Ian Goodfellow

Suggested Reading:

Additional Reading:

  1. Graph Neural Networks:

Required Reading:

Suggested Reading:

Additional Reading:

Additional Resources:

Class Time and Location:

Sunday and Tuesday 13:00-14:30 AM (Fall 2019)

Projects:

Projects are programming assignments that cover the topic of this course. Any project is written by Jupyter Notebook. Projects will require the use of Python 3.7, as well as additional Python libraries.

Google Colab:

Google Colab is a free cloud service and it supports free GPU!

Fascinating Guides For Machine Learning:

Latex:

The students can include mathematical notation within markdown cells using LaTeX in their Jupyter Notebooks.

  • A Brief Introduction to LaTeX PDF
  • Math in LaTeX PDF
  • Sample Document PDF
  • TikZ: A collection Latex files of PGF/TikZ figures (including various neural networks) by Petar Veličković.

Grading:

  • Projects and Midterm – 50%
  • Endterm – 50%

Prerequisites:

General mathematical sophistication; and a solid understanding of Algorithms, Linear Algebra, and Probability Theory, at the advanced undergraduate or beginning graduate level, or equivalent.

Linear Algebra:

Probability and Statistics:

Topics:

Have a look at some reports of Kaggle or Stanford students (CS224N, CS224D) to get some general inspiration.

Account:

It is necessary to have a GitHub account to share your projects. It offers plans for both private repositories and free accounts. Github is like the hammer in your toolbox, therefore, you need to have it!

Academic Honor Code:

Honesty and integrity are vital elements of the academic works. All your submitted assignments must be entirely your own (or your own group's).

We will follow the standard of Department of Mathematical Sciences approach:

  • You can get help, but you MUST acknowledge the help on the work you hand in
  • Failure to acknowledge your sources is a violation of the Honor Code
  • You can talk to others about the algorithm(s) to be used to solve a homework problem; as long as you then mention their name(s) on the work you submit
  • You should not use code of others or be looking at code of others when you write your own: You can talk to people but have to write your own solution/code

Questions?

I will be having office hours for this course on Sunday (09:00 AM--10:00 AM). If this is not convenient, email me at hhaji@sbu.ac.ir or talk to me after class.