README.md

Deep Learning Area

Hello, if you are going to dive into deep learning, I would suggest that you first take a look at the Resources section that I have prepared for you. And always remember why you started learning machine learning.

Rustam_Z🚀, 18 October 2020

deeplearning.ai Deep Learning Specialization

Neural Networks and Deep Learning

• Architecture of Neural Network

• Logistic Regression

• Cost function, Forward propagation, Backpropagation, Gradient descent

• Artificial Neural Network

• Logistic Regression vs NN, Activation fanctions, L-layer NN

Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization

• Train/dev/test sets

• Regularization, dropout technique, normalizing inputs, gradient checking

• Optimization algos (mini-batch GD, GD with momentum, RMS, Adam optimization)

• Xavier/He initialization

• Hyperparameters tuning (logarithmic scale), batch normalization

• Multiclass classification, TensorFlow introduction

Structuring Machine Learning Projects

• How to build a successful machine learning projects

• How to prioritize the problem

• ML strategy (satisficing & optimizing metrics)

• Choose a correct train/dev/test split of your dataset

• Human-level performance (avoidable bias)

• Error Analysis

• Mismatched training and dev/test set

Convolutional Neural Networks

• Foundations of Convolutional Neural Networks

• Deep convolutional models: case studies

• Object detection

• Special applications: Face recognition & Neural style transfer

Natural Language Processing: Building sequence models

• Recurrent Neural Networks (RNNs), natural language processing (NLP)

Resources📄

The list of things you need for this particular specialization

• In-depth deeplearning.ai Specialization Review, Daniel describes all about this specialization, continuation is here

• GitHub Notes

• TA Deep Learning Notes, haven't read actually

• Drawn DL notes

• TensorFlow Turorial, what is the tensor?

General Resources🔗

• TensorFlow Resources for Learning ML

• Krish Naik's complete DL course, if you get stuck and don't understand the concepts

• Krish Naik's complete ML course

• Practical Machine Learning with Python

• Stanford Online, awesome lectures by Andrew Ng at Stanford

• MIT Deep Learning

• Google's ML Crash Course

• Google AI

• Amazon Machine Learning Guide

Research🔬

• https://openai.com/blog/tags/research/

• https://deepmind.com/research

• https://www.microsoft.com/en-us/research/research-area/artificial-intelligence

• https://www.research.ibm.com/artificial-intelligence/#publications

• https://ai.stanford.edu

• https://www.csail.mit.edu

• https://ai.google/research/

• https://ai.googleblog.com/

Books📚

• Daniel's recommendation - https://youtu.be/7R08MPXxiFQ

• Machine Learning for Humans

• Python for Data Analysis 2^nd edition

• Hands-on Machine Learning with Scikit-Learn, Keras, and TensorFlow 2^nd edition

• Grokking Deep Learning

• The Mechanics of Machine Learning

• The Hundred-Page Machine Learning Book Andriy Burkov

• Deep Learning, deeplearningbook.org, "Written by three experts in the field, Deep Learning is the only comprehensive book on the subject." —Elon Musk

• Machine Learning Engineering Andriy Burkov

Curiosity

• Podcast with Andrew Ng about getting started in Deep Learning: https://youtu.be/1k37OcjH7BM

• Andrew Ng Machine Learning Career Advice: https://youtu.be/hkagmGAu74Y

• Andrew Ng - Career Advice/Reading Research Papers: https://youtu.be/733m6qBH-jI