/explore

Click through on any links that interest you or select the planets on the right to continue exploring the Outer Web.
You are here

 adl1995.github.io
An overview of activation functions used in neural networks
| | michael-lewis.com
A machine learning glossary for hackers ยท Michael I Lewis
0.7 parsecs away

Travel
| | This is a short summary of some of the terminology used in machine learning, with an emphasis on neural networks. I've put it together primarily to help my own understanding, phrasing it largely in non-mathematical terms. As such it may be of use to others who come from more of a programming than a mathematical background.
| | www.lesswrong.com
Nonlinear limitations of ReLUs - LessWrong
0.8 parsecs away

Travel
| | A neural net using rectified linear unit activation functions of any size is unable to approximate the function sin(x) outside a compact interval. ...
| | programmathically.com
Understanding The Exploding and Vanishing Gradients Problem - Programmathically
1.2 parsecs away

Travel
| | Sharing is caringTweetIn this post, we develop an understanding of why gradients can vanish or explode when training deep neural networks. Furthermore, we look at some strategies for avoiding exploding and vanishing gradients. The vanishing gradient problem describes a situation encountered in the training of neural networks where the gradients used to update the weights []
| | golb.hplar.ch
Building a simple neural network with Java and JavaScript
9.2 parsecs away

Travel
| [AI summary] The blog post details the author's experience implementing a feedforward neural network for digit recognition using Java and JavaScript, explaining the underlying algorithms, shared external libraries, and architectural decisions while reviewing an introductory book on the topic.