GPU-accelerated Neural Networks in JavaScript

GPU-accelerated Neural Networks in JavaScript

  • March 22, 2018
Table of Contents

GPU-accelerated Neural Networks in JavaScript

While its feature set is geared towards neural networks, deeplearn.js can be described as a general-purpose machine learning framework. Propel is a library for scientific computing that offers automatic differentiation. Gpu.js provides a convenient way to run JavaScript functions on the GPU.

Brain.js is a continuation of an older neural network library and uses gpu.js for hardware acceleration.

Source: towardsdatascience.com

Tags :
Share :
comments powered by Disqus

Related Posts

Soft robotic fish swims alongside real ones in coral reefs

Soft robotic fish swims alongside real ones in coral reefs

Read More
Robots Are Trying To Pick Strawberries. So Far, They’re Not Very Good At It

Robots Are Trying To Pick Strawberries. So Far, They’re Not Very Good At It

Read More
Understanding Deep Learning through Neuron Deletion

Understanding Deep Learning through Neuron Deletion

Deep neural networks are composed of many individual neurons, which combine in complex and counterintuitive ways to solve challenging tasks, ranging from machine translation to Go. This complexity grants neural networks their power but also earns them their reputation as confusing and opaque black boxes. Understanding how deep neural networks function is critical for explaining their decisions and enabling us to build more powerful systems.

Read More