Digests » 137

this week's favorite

RoboLeague: A clone of Rocket League for AI experiments

A car soccer environment inspired by Rocket League for deep reinforcement learning experiments in an adversarial self-play setting.

Visual Guide to K-Nearest Neighbors

K-Nearest Neighbors or KNN is one of the most fundamental tools that a machine learning scientist uses. In this video, we'll see how we can use it to determine the MPAA rating of the 2019 hit Bombshell!

How Transformers work in deep learning and NLP: an intuitive introduction

The famous paper “Attention is all you need” in 2017 changed the way we were thinking about attention. With enough data, matrix multiplications, linear layers, and layer normalization we can perform state-of-the-art-machine-translation.

What are Decision Trees?

Decision trees are one of the more commonly used algorithms, they are extremely powerful and easy to learn making it one of the better algorithms to learn in-depth first. They can be used for both classification and regression problems, even ensemble methods which we will look at another time.

Recognize sounds from audio

In this tutorial, you'll use machine learning to build a system that can recognize when a particular sound is happening—a task known as audio classification. The system you create will be able to recognize the sound of water running from a faucet, even in the presence of other background noise.