Learning to acquire novel cognitive tasks with evolution, plasticity and meta-meta-learning

TL;DR

This paper demonstrates how evolved neural networks with plasticity and neuromodulation can autonomously learn new cognitive tasks by modifying their connectivity, highlighting the importance of multiple learning loops in intelligent behavior.

Contribution

It introduces a method of evolving neural networks with plasticity and neuromodulation to acquire novel cognitive tasks without prior training.

Findings

Evolved networks can learn new cognitive tasks from stimuli and rewards.

Plasticity and neuromodulation are crucial for autonomous task acquisition.

Multiple learning loops are essential for emergent intelligent behavior.

Abstract

A hallmark of intelligence is the ability to autonomously learn new flexible, cognitive behaviors - that is, behaviors where the appropriate action depends not just on immediate stimuli (as in simple reflexive stimulus-response associations), but on contextual information that must be adequately acquired, stored and processed. While many meta-learning algorithms can design agents that autonomously learn new tasks, cognitive tasks adds another level of learning and memory to typical ``learning-to-learn'' problems. Here we evolve neural networks, endowed with plastic connections and neuromodulation, over a sizable set of simple cognitive tasks adapted from a computational neuroscience framework. The resulting evolved networks can automatically modify their own connectivity to acquire a novel simple cognitive task, never seen during evolution, from stimuli and rewards alone, through the spontaneous operation of their evolved neural organization and plasticity system. Our results emphasize the importance of carefully considering the multiple learning loops involved in the emergence of intelligent behavior.