AI-Based High-Fidelity Image Synthesis

AI-Based High-Fidelity Image Synthesis

Two Minute Papers highlights some of the advances made in GANs over the last 18 months or so. The paper "Large Scale GAN Training for... Details
Can an AI Learn To Draw a Caricature?

Can an AI Learn To Draw a Caricature?

Two Minute Papers highlights an academic research paper that covers how to teach a computer to draw caricatures. Details
A Deeper Understanding of Deep Learning

A Deeper Understanding of Deep Learning

Kaggle has a series of videos on Deep Learning and this video does a great job of explaining gradient descent, loss functions, and other fundamentals of deep... Details
Introduction to Neural Networks

Introduction to Neural Networks

Here are parts 1 and 2 of a series by The Coding Train about the fundamentals of neural networks. Part 2: The Perceptron Details
How Does Transfer Learning Work?

How Does Transfer Learning Work?

This Kaggle explains the inner workings of transfer learning, a fascinating application of neural networks. Details
An AI That Learns Acrobatics by Watching YouTube

An AI That Learns Acrobatics by Watching YouTube

Two Minute Papers explores an interesting paper on how an AI can learn acrobatics from watching YouTube videos. Details
Can GANs Give AI an Imagination?

Can GANs Give AI an Imagination?

Imagination comes naturally to humans, but how can we create artificial intelligence that can imagine? It turns out that GANs are the key. Details
Neural Networks that Empower Digital Artists

Neural Networks that Empower Digital Artists

The YouTube channel "Two Minute Papers" explores how neural networks can help artists be more creative. Details
How Neural Networks Learn (Part 2)

How Neural Networks Learn (Part 2)

In this video, Arxiv continues his dive into the world of adversarial examples: images specifically engineered to fool neural networks into making completely wrong decisions! This... Details
How Neural Networks Learn (Part 1)

How Neural Networks Learn (Part 1)

Interpreting what neural networks are doing is a tricky problem. In fact, they are often referred to as a "black box." In this video Arxiv... Details