Need is All You Need: Homeostatic Neural Networks Adapt to Concept Shift

TL;DR

This paper introduces a homeostatic neural network that self-regulates its internal states, enhancing adaptability to concept shifts and improving learning in dynamic environments by mimicking biological regulation.

Contribution

It presents a novel neural network design incorporating homeostatic features that improve adaptability to concept shift, a significant advancement over traditional static models.

Findings

Homeostatic networks adapt better to concept shifts.

Self-regulation enhances learning speed during data distribution changes.

Vulnerability in the model can improve overall performance.

Abstract

In living organisms, homeostasis is the natural regulation of internal states aimed at maintaining conditions compatible with life. Typical artificial systems are not equipped with comparable regulatory features. Here, we introduce an artificial neural network that incorporates homeostatic features. Its own computing substrate is placed in a needful and vulnerable relation to the very objects over which it computes. For example, artificial neurons performing classification of MNIST digits or Fashion-MNIST articles of clothing may receive excitatory or inhibitory effects, which alter their own learning rate as a direct result of perceiving and classifying the digits. In this scenario, accurate recognition is desirable to the agent itself because it guides decisions to regulate its vulnerable internal states and functionality. Counterintuitively, the addition of vulnerability to a learner does not necessarily impair its performance. On the contrary, self-regulation in response to vulnerability confers benefits under certain conditions. We show that homeostatic design confers increased adaptability under concept shift, in which the relationships between labels and data change over time, and that the greatest advantages are obtained under the highest rates of shift. This necessitates the rapid un-learning of past associations and the re-learning of new ones. We also demonstrate the superior abilities of homeostatic learners in environments with dynamically changing rates of concept shift. Our homeostatic design exposes the artificial neural network's thinking machinery to the consequences of its own "thoughts", illustrating the advantage of putting one's own "skin in the game" to improve fluid intelligence.