Reinforcement Learning with Brain-Inspired Modulation can Improve Adaptation to Environmental Changes

1 code implementation • 19 May 2022 • Eric Chalmers, Artur Luczak

Developments in reinforcement learning (RL) have allowed algorithms to achieve impressive performance in highly complex, but largely static problems.

reinforcement-learning Reinforcement Learning (RL)

Hippocluster: an efficient, hippocampus-inspired algorithm for graph clustering

1 code implementation • 19 May 2022 • Eric Chalmers, Artur Luczak

Interestingly, information processing in the brain may suggest a simpler method of learning clusters directly from random walks.

Clustering Community Detection +2

Biologically-inspired neuronal adaptation improves learning in neural networks

1 code implementation • 8 Apr 2022 • Yoshimasa Kubo, Eric Chalmers, Artur Luczak

Since humans still outperform artificial neural networks on many tasks, drawing inspiration from the brain may help to improve current machine learning algorithms.

A Deep Convolutional Auto-Encoder with Pooling - Unpooling Layers in Caffe

no code implementations • 18 Jan 2017 • Volodymyr Turchenko, Eric Chalmers, Artur Luczak

This paper presents the development of several models of a deep convolutional auto-encoder in the Caffe deep learning framework and their experimental evaluation on the example of MNIST dataset.

Clustering Decoder +1