The Yin-Yang dataset

02/16/2021
by   Laura Kriener, et al.
0

The Yin-Yang dataset was developed for research on biologically plausible error backpropagation and deep learning in spiking neural networks. It serves as an alternative to classic deep learning datasets, especially in algorithm- and model-prototyping scenarios, by providing several advantages. First, it is smaller and therefore faster to learn, thereby being better suited for the deployment on neuromorphic chips with limited network sizes. Second, it exhibits a very clear gap between the accuracies achievable using shallow as compared to deep neural networks.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

09/27/2021

Training Spiking Neural Networks Using Lessons From Deep Learning

The brain is the perfect place to look for inspiration to develop more e...
10/17/2021

Backpropagation with Biologically Plausible Spatio-Temporal Adjustment For Training Deep Spiking Neural Networks

The spiking neural network (SNN) mimics the information processing opera...
02/27/2019

Biologically plausible deep learning -- but how far can we go with shallow networks?

Training deep neural networks with the error backpropagation algorithm i...
12/06/2019

A Neural Spiking Approach Compared to Deep Feedforward Networks on Stepwise Pixel Erasement

In real world scenarios, objects are often partially occluded. This requ...
02/04/2019

A Spiking Neural Network with Local Learning Rules Derived From Nonnegative Similarity Matching

The design and analysis of spiking neural network algorithms will be acc...
05/28/2018

NengoDL: Combining deep learning and neuromorphic modelling methods

NengoDL is a software framework designed to combine the strengths of neu...
07/24/2020

Online Spatio-Temporal Learning in Deep Neural Networks

Biological neural networks are equipped with an inherent capability to c...

Code Repositories

This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.