Learning representations in Bayesian Confidence Propagation neural networks
This work addresses unsupervised representation learning for neural networks, but appears incremental as it builds on existing BCPNN architecture.
The authors tackled unsupervised learning of hierarchical representations by extending the Bayesian Confidence Propagating Neural Network (BCPNN) with new mechanisms based on local Hebbian learning, and demonstrated its capability on the MNIST dataset.
Unsupervised learning of hierarchical representations has been one of the most vibrant research directions in deep learning during recent years. In this work we study biologically inspired unsupervised strategies in neural networks based on local Hebbian learning. We propose new mechanisms to extend the Bayesian Confidence Propagating Neural Network (BCPNN) architecture, and demonstrate their capability for unsupervised learning of salient hidden representations when tested on the MNIST dataset.