Salience-Affected Neural Networks

TL;DR

This paper introduces a salience-affected neural network (SANN) model that incorporates diffuse limbic projections to simulate global salience effects, enhancing one-time learning and mimicking brain-like interactions.

Contribution

The paper presents a novel neural network architecture combining local and diffuse connections to model salience effects, enabling one-trial learning and brain-like interactions.

Findings

Model responds to input salience signals during training and testing.

Uncovered a new method for training ANNs with a single iteration.

Demonstrated enhanced learning effects similar to biological systems.

Abstract

We present a simple neural network model which combines a locally-connected feedforward structure, as is traditionally used to model inter-neuron connectivity, with a layer of undifferentiated connections which model the diffuse projections from the human limbic system to the cortex. This new layer makes it possible to model global effects such as salience, at the same time as the local network processes task-specific or local information. This simple combination network displays interactions between salience and regular processing which correspond to known effects in the developing brain, such as enhanced learning as a result of heightened affect. The cortex biases neuronal responses to affect both learning and memory, through the use of diffuse projections from the limbic system to the cortex. Standard ANNs do not model this non-local flow of information represented by the ascending systems, which are a significant feature of the structure of the brain, and although they do allow associational learning with multiple-trial, they simply don't provide the capacity for one-time learning. In this research we model this effect using an artificial neural network (ANN), creating a salience-affected neural network (SANN). We adapt an ANN to embody the capacity to respond to an input salience signal and to produce a reverse salience signal during testing. This research demonstrates that input combinations similar to the inputs in the training data sets will produce similar reverse salience signals during testing. Furthermore, this research has uncovered a novel method for training ANNs with a single training iteration.