pith. sign in

arxiv: 1702.06456 · v3 · pith:YAC3TJZ5new · submitted 2017-02-21 · 💻 cs.NE · cs.CV

Online Representation Learning with Single and Multi-layer Hebbian Networks for Image Classification

classification 💻 cs.NE cs.CV
keywords learningnetworksfeaturesmulti-layerunsupervisedalgorithmalgorithmsbeen
0
0 comments X
read the original abstract

Unsupervised learning permits the development of algorithms that are able to adapt to a variety of different data sets using the same underlying rules thanks to the autonomous discovery of discriminating features during training. Recently, a new class of Hebbian-like and local unsupervised learning rules for neural networks have been developed that minimise a similarity matching cost-function. These have been shown to perform sparse representation learning. This study tests the effectiveness of one such learning rule for learning features from images. The rule implemented is derived from a nonnegative classical multidimensional scaling cost-function, and is applied to both single and multi-layer architectures. The features learned by the algorithm are then used as input to an SVM to test their effectiveness in classification on the established CIFAR-10 image dataset. The algorithm performs well in comparison to other unsupervised learning algorithms and multi-layer networks, thus suggesting its validity in the design of a new class of compact, online learning networks.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.