deep-learning-resources

A Collection of resources I have found useful on my journey, finding my way through the world of Deep Learning.

Courses

Stanford CS231n Convolutional Neural Networks for Visual Recognition

Learn about artificial neural networks and how they're being used for machine learning, as applied to speech and object recognition, image segmentation, modeling language and human motion, etc. by Geoffrey Hinton

Coursera: Neural Networks for Machine Learning

Deep Learning is an important subset of Machine Learning and it is therefor important to get a wider knowledge and understanding of Machine Learning. The Coursera Machine Learning course by Andrew Ng is highly recommended.

Coursera: Machine Learning

The fast.ai team (Jeremy Howard & Rachel Thomas) promises to take you to the cool stuff asap.

fast.ai course

Tutorials & Articles

You know when Chris Olah is involved it will be brilliant - one of the best posts on visualising how Neural Networks learn to see around.

Feature Visualization - How neural networks build up their understanding of images

Image Kernels - Explained visually

Preprocessing data

How to setup your Windows 10 machine for Machine Learning using Ubuntu Bash shell

Deep Learning - a gentle dive

A 'Brief' History of Neural Nets and Deep Learning (4 parts)

YouTube: Excellent visualization of How Neural Networks Work

Tinker with a Neural Network Right Here in Your Browser - Tensorflow Playground

A Beginner's Guide To Understanding Convolutional Neural Networks

An Intuitive Explanation of Convolutional Neural Networks

Hacker's guide to Neural Networks ~Andrej Karpathy

Gradient Descent Optimisation Algorithms

Recurrent Neural Networks

A Few Useful Things to Know about Machine Learning ~Pedro Domingos

YouTube: Introduction to Deep Learning with Python

YouTube: Machine Learning with Python

YouTube: Deep Visualization Toolbox

Yes you should understand backprop ~Andrej Karpathy

PDF: Dropout: A Simple Way to Prevent Neural Networks from Overfitting

PDF: SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and 0.5MB model size

Quora: How does a confusion matrix work

PDF: Understanding the difficulty of training deep feedforward neural networks

PDF: Lip reading using CNN and LSTM

Running Jupyter notebooks on GPU on AWS: a starter guide

Jupyter notebook - DeepDreaming with TensorFlow

The Black Magic of Deep Learning - Tips and Tricks for the practitioner

YouTube: Dimensionality Reduction: Principal Component Analysis, Part 1 | Part 2 | Part 3

Books & e-Books

Hands-On Machine Learning with Scikit-Learn and Tensorflow

Neural Networks and Deep Learning

Deep Learning Book - some call this book the Deep Learning bible

Machine Learning Yearning - Technical Strategy for AI Engineers, in the Era of Deep Learning ~Andrew Ng

Getting Philosophical

Diverse AI applications around the world

What is the next likely breakthrough in Deep Learning

Looking at The major advancements in Deep Learning in 2016 gives us a peek into the future of deep learing. A big portion of the effort went into Generative Models, let us see if that is the case in 2017.

Do machines actually beat doctors?

Visualising a Neural Network as a tree with branches and using smart pruning techniques might be the answer to getting a peek view of what is going on inside the 'black box' of a Neural Network

A One-Step Program for Becoming a Data Scientist**

** Is interchangeable with Deep Learning Expert

Cardiologist-Level Arrhythmia Detection With Convolutional Neural Networks

When not to use Deep Learning

Competitions

Kaggle is the place to be for Data Scientists and Deep Learning experts at the moment - but you don't have to be an expert to feel the adrenalin of a $150000 competition

Kaggle competitions perfect for deep learning:

iNaturalist competition 2017

** The training and validation images weighs in at a hefty 186GB - only for the brave with a monster deep learning machine

Tools of the Trade

Python

Python Official

Python Programming Tutorials

YouTube: How did Python become a data science powerhouse?

MatplotLib

Deep Learning is far from being an exact science and a lot of what you do is based on getting a feel for the underlying mechanics, visualising the moving parts makes it easier to understand and Matplotlib is the go-to library for visualisation

Matplotlib official

Matplotlib tutorial

YouTube: Bare Minimum: Matplotlib for data visualization

NumPy

NumPy is a fast optimized package for scientific computing, and is also the underlying library a lot of Machine Learning frameworks are build on top of. Becoming a NumPy ninja is an important step to mastery.

NumPy official

CS231n Python Numpy Tutorial

100 NumPy exercises

Intro to Numpy PDF | Jupyter Notebook

Pandas

Pandas is a high level data manipulation tool based on the Numpy package. At it's core Pandas uses a DataFrame which allows you to store and manipulate tabular data.

Pandas Cheat Sheet

TensorFlow

TensorFlow is an open source software library for numerical computation using data flow graphs. TensorFlow is designed and highly optimised to take advantage of GPU technology in a distributed manner not only on a single instance with many GPU's, but also across many devices and networks, making it an ideal framework for learning and production.

TensorFlow official documentation

Getting Started With TensorFlow

Learn TensorFlow and deep learning, without a Ph.D.

Installing TensorFlow on a Raspberry Pi 3