Detecting Information Relays in Deep Neural Networks

01/03/2023
by   Arend Hintze, et al.
0

Deep learning of artificial neural networks (ANNs) is creating highly functional processes that are, unfortunately, nearly as hard to interpret as their biological counterparts. Identification of functional modules in natural brains plays an important role in cognitive and neuroscience alike, and can be carried out using a wide range of technologies such as fMRI, EEG/ERP, MEG, or calcium imaging. However, we do not have such robust methods at our disposal when it comes to understanding functional modules in artificial neural networks. Ideally, understanding which parts of an artificial neural network perform what function might help us to address a number of vexing problems in ANN research, such as catastrophic forgetting and overfitting. Furthermore, revealing a network's modularity could improve our trust in them by making these black boxes more transparent. Here, we introduce a new information-theoretic concept that proves useful in understanding and analyzing a network's functional modularity: the relay information I_R. The relay information measures how much information groups of neurons that participate in a particular function (modules) relay from inputs to outputs. Combined with a greedy search algorithm, relay information can be used to identify computational modules in neural networks. We also show that the functionality of modules correlates with the amount of relay information they carry.

READ FULL TEXT

page 5

page 13

page 14

research
05/20/2017

Diffusion-based neuromodulation can eliminate catastrophic forgetting in simple neural networks

A long-term goal of AI is to produce agents that can learn a diversity o...
research
06/04/2021

Extreme sparsity gives rise to functional specialization

Modularity of neural networks – both biological and artificial – can be ...
research
06/25/2023

Network Optimization – Using Relays as Neurons

We consider the optimization of a network with amplify-and-forward relay...
research
03/02/2018

A computational perspective of the role of Thalamus in cognition

Thalamus has traditionally been considered as only a relay source of cor...
research
11/12/2020

Artificial Neural Variability for Deep Learning: On Overfitting, Noise Memorization, and Catastrophic Forgetting

Deep learning is often criticized by two serious issues which rarely exi...
research
07/30/2023

Pupil Learning Mechanism

Studies on artificial neural networks rarely address both vanishing grad...
research
11/23/2022

Functional Connectome: Approximating Brain Networks with Artificial Neural Networks

We aimed to explore the capability of deep learning to approximate the f...

Please sign up or login with your details

Forgot password? Click here to reset