Foundations of a Developmental Design Paradigm for Integrated Continual Learning, Deliberative Behavior, and Comprehensibility

TL;DR

This paper proposes a biologically inspired developmental design framework for continual learning, deliberative behavior, and comprehensibility, addressing key limitations of current machine learning systems through a modular, hierarchical approach.

Contribution

It introduces a novel developmental system design with a gradient-free learner, goal-directed planner, and hierarchical behavior model, grounded in evolutionary biology principles.

Findings

Proof-of-principle demonstrated in a simple environment

Extended framework successfully applied to MNIST shape detection

Shows potential to overcome multiple ML limitations simultaneously

Abstract

Inherent limitations of contemporary machine learning systems in crucial areas -- importantly in continual learning, information reuse, comprehensibility, and integration with deliberate behavior -- are receiving increasing attention. To address these challenges, we introduce a system design, fueled by a novel learning approach conceptually grounded in principles of evolutionary developmental biology, that overcomes key limitations of current methods. Our design comprises three core components: The Modeller, a gradient-free learning mechanism inherently capable of continual learning and structural adaptation; a planner for goal-directed action over learned models; and a behavior encapsulation mechanism that can decompose complex behaviors into a hierarchical structure. We demonstrate proof-of-principle operation in a simple test environment. Additionally, we extend our modeling framework to higher-dimensional network-structured spaces, using MNIST for a shape detection task. Our framework shows promise in overcoming multiple major limitations of contemporary machine learning systems simultaneously and in an organic manner.