Handwritten digit recognition by bio-inspired hierarchical networks

TL;DR

This paper introduces a biologically plausible hierarchical network, ICN, inspired by neuronal mechanisms, capable of learning invariant patterns and classifying handwritten digits with competitive accuracy.

Contribution

The paper presents the Inductive Conceptual Network (ICN), a novel bio-inspired hierarchical model that learns invariant patterns and classifies images, mimicking cortical functions.

Findings

ICN achieved 5.73% error on MNIST dataset.

ICN achieved 12.56% error on USPS dataset.

The model demonstrates biological plausibility in pattern recognition.

Abstract

The human brain processes information showing learning and prediction abilities but the underlying neuronal mechanisms still remain unknown. Recently, many studies prove that neuronal networks are able of both generalizations and associations of sensory inputs. In this paper, following a set of neurophysiological evidences, we propose a learning framework with a strong biological plausibility that mimics prominent functions of cortical circuitries. We developed the Inductive Conceptual Network (ICN), that is a hierarchical bio-inspired network, able to learn invariant patterns by Variable-order Markov Models implemented in its nodes. The outputs of the top-most node of ICN hierarchy, representing the highest input generalization, allow for automatic classification of inputs. We found that the ICN clusterized MNIST images with an error of 5.73% and USPS images with an error of 12.56%.