We live in a world where, for better and for worse, we are surrounded by deep learning algorithms. From social network filtering to driverless cars to movie recommendations, and from financial fraud detection to drug discovery to medical image processing, deep learning algorithms influence our lives and our decisions every single day.
At a fundamental level, deep learning is a part of the machine learning family based on learning data representations rather than task-specific algorithms. The inspiration for deep learning is the way that the human brain filters information. It teaches a computer to filter inputs like images, text, or sound through layers to learn how to predict and classify data. Its purpose is to mimic how the human brain works to create some real magic.
What does it take to get started in deep learning? What does it take to do it well? Which libraries and frameworks are best for deep learning problems, and what’s the best way to use them? Are we already seeing the limitations of deep learning? In order to examine these questions, we’ve pulled together some of our best articles, and we’re excited to share them with you.
— Anne Bonner, TDS Editor
Deep Dive into Math Behind Deep Networks
By Piotr Skalski – 9 min read
Mysteries of Neural Networks
Detecting Malaria with Deep Learning
By Dipanjan (DJ) Sarkar – 16 min read
AI for Social Good – A Healthcare Case Study
How to do Deep Learning on Graphs with Graph Convolutional Networks
By Tobias Skovgaard Jepsen – 9 min read
A High-Level Introduction to Graph Convolutional Networks
One neural network, many uses
By Paras Chopra – 15 min read
Build image search, image captioning, similar words and similar images using a single model
Which Deep Learning Framework is Growing Fastest?
By Jeff Hale – 8 min read
TensorFlow vs. PyTorch
Neural ODEs: breakdown of another deep learning breakthrough
By Alexandr Honchar – 11 min read
If you’re reading this article, most probably you’re catching up with the recent advances that happen in the AI world.
Is Deep Learning Already Hitting its Limitations?
By Thomas Nield – 11 min read
And Is Another AI Winter Coming?
An Easy Guide to Gauge Equivariant Convolutional Networks
By Michael Kissner – 12 min read
Geometric deep learning is a very exciting new field, but its mathematics is slowly drifting into the territory of algebraic topology and theoretical physics.
We also thank all the great new writers who joined us recently, Gary Koplik, Sarah Eade, Timothy Tan, Dave Lorenz, Paulynn Yu, Khanh Nguyen, Jordan Ryda, Kayo Yin, shravan kuchkula, Pranav Prathvikumar, Oscar Kwok, Martin Dittgen, Marco Santos, Steven Eulig, and many others. We invite you to take a look at their profiles and check out their work.