Brain inspired neuronal silencing mechanism to enable reliable sequence identification

Shiri Hodassman, Yuval Meir, Karin Kisos, Itamar Ben-Noam, Yael Tugendhaft, Amir Goldental, Roni Vardi, Ido Kanter

Research output: Contribution to journalArticlepeer-review

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.

Original languageEnglish
Article number16003
Number of pages14
JournalScientific Reports
Volume12
Issue number1
DOIs
StatePublished - 29 Sep 2022

All Science Journal Classification (ASJC) codes

  • General

Fingerprint

Dive into the research topics of 'Brain inspired neuronal silencing mechanism to enable reliable sequence identification'. Together they form a unique fingerprint.

Cite this