Brain inspired neuronal silencing mechanism to enable reliable sequence identification

TL;DR

This paper introduces a biologically inspired neuronal silencing mechanism that enables reliable, high-precision sequence identification in neural networks without feedback loops, demonstrating effectiveness in digit sequence recognition and potential cryptographic applications.

Contribution

The paper presents a novel neuronal plasticity mechanism for feedforward neural networks that improves sequence recognition without feedback, inspired by brain processes.

Findings

Successfully identified 10 handwritten digit sequences

Generalized to deep convolutional ANNs for image sequences

High classification accuracy with limited training data

Abstract

Real-time sequence identification is a core use-case of artificial neural networks (ANNs), ranging from recognizing temporal events to identifying verification codes. Existing methods apply recurrent neural networks, which suffer from training difficulties; however, performing this function without feedback loops remains a challenge. Here, we present an experimental neuronal long-term plasticity mechanism for high-precision feedforward sequence identification networks (ID-nets) without feedback loops, wherein input objects have a given order and timing. This mechanism temporarily silences neurons following their recent spiking activity. Therefore, transitory objects act on different dynamically created feedforward sub-networks. ID-nets are demonstrated to reliably identify 10 handwritten digit sequences, and are generalized to deep convolutional ANNs with continuous activation nodes trained on image sequences. Counterintuitively, their classification performance, even with a limited number of training examples, is high for sequences but low for individual objects. ID-nets are also implemented for writer-dependent recognition, and suggested as a cryptographic tool for encrypted authentication. The presented mechanism opens new horizons for advanced ANN algorithms.