Biologically-Inspired Spatial Neural Networks

10/07/2019
by   Maciej Wołczyk, et al.
0

We introduce bio-inspired artificial neural networks consisting of neurons that are additionally characterized by spatial positions. To simulate properties of biological systems we add the costs penalizing long connections and the proximity of neurons in a two-dimensional space. Our experiments show that in the case where the network performs two different tasks, the neurons naturally split into clusters, where each cluster is responsible for processing a different task. This behavior not only corresponds to the biological systems, but also allows for further insight into interpretability or continual learning.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/13/2023

A Study of Biologically Plausible Neural Network: The Role and Interactions of Brain-Inspired Mechanisms in Continual Learning

Humans excel at continually acquiring, consolidating, and retaining info...
research
08/30/2017

Continual One-Shot Learning of Hidden Spike-Patterns with Neural Network Simulation Expansion and STDP Convergence Predictions

This paper presents a constructive algorithm that achieves successful on...
research
09/19/2022

Autonomous Visual Navigation A Biologically Inspired Approach

Inspired by the navigational behavior observed in the animal kingdom and...
research
11/13/2020

Continual Learning with Deep Artificial Neurons

Neurons in real brains are enormously complex computational units. Among...
research
12/12/2020

Low-Order Model of Biological Neural Networks

A biologically plausible low-order model (LOM) of biological neural netw...
research
05/10/2005

Characterizing Self-Developing Biological Neural Networks: A First Step Towards their Application To Computing Systems

Carbon nanotubes are often seen as the only alternative technology to si...
research
06/21/2023

Mitigating Communication Costs in Neural Networks: The Role of Dendritic Nonlinearity

Our comprehension of biological neuronal networks has profoundly influen...

Please sign up or login with your details

Forgot password? Click here to reset