Morphological Cognition: Classifying MNIST Digits Through Morphological Computation Alone

TL;DR

This paper demonstrates that simple, fixed morphological behaviors in a simulated robot can lead to emergent cognitive classification of MNIST digits without neural networks, highlighting embodiment's role in intelligence.

Contribution

It introduces the concept of morphological cognition, showing how fixed physical behaviors can produce high-level cognitive tasks like image classification without neural circuitry.

Findings

Robots with fixed voxel behaviors can classify MNIST digits by movement direction.

This is the first demonstration of high-level cognition without neural networks.

Embodiment alone can produce emergent intelligent behaviors.

Abstract

With the rise of modern deep learning, neural networks have become an essential part of virtually every artificial intelligence system, making it difficult even to imagine different models for intelligent behavior. In contrast, nature provides us with many different mechanisms for intelligent behavior, most of which we have yet to replicate. One of such underinvestigated aspects of intelligence is embodiment and the role it plays in intelligent behavior. In this work, we focus on how the simple and fixed behavior of constituent parts of a simulated physical body can result in an emergent behavior that can be classified as cognitive by an outside observer. Specifically, we show how simulated voxels with fixed behaviors can be combined to create a robot such that, when presented with an image of an MNIST digit zero, it moves towards the left; and when it is presented with an image of an MNIST digit one, it moves towards the right. Such robots possess what we refer to as ``morphological cognition'' -- the ability to perform cognitive behavior as a result of morphological processes. To the best of our knowledge, this is the first demonstration of a high-level mental faculty such as image classification performed by a robot without any neural circuitry. We hope that this work serves as a proof-of-concept and fosters further research into different models of intelligence.