Brain inspired neuronal silencing mechanism to enable reliable sequence identification
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...
Main Authors: | , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Portfolio
2022-09-01
|
Series: | Scientific Reports |
Online Access: | https://doi.org/10.1038/s41598-022-20337-x |
_version_ | 1797998304177422336 |
---|---|
author | Shiri Hodassman Yuval Meir Karin Kisos Itamar Ben-Noam Yael Tugendhaft Amir Goldental Roni Vardi Ido Kanter |
author_facet | Shiri Hodassman Yuval Meir Karin Kisos Itamar Ben-Noam Yael Tugendhaft Amir Goldental Roni Vardi Ido Kanter |
author_sort | Shiri Hodassman |
collection | DOAJ |
description | 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. |
first_indexed | 2024-04-11T10:46:34Z |
format | Article |
id | doaj.art-4266cd1315b9494db5cfa0b387bde045 |
institution | Directory Open Access Journal |
issn | 2045-2322 |
language | English |
last_indexed | 2024-04-11T10:46:34Z |
publishDate | 2022-09-01 |
publisher | Nature Portfolio |
record_format | Article |
series | Scientific Reports |
spelling | doaj.art-4266cd1315b9494db5cfa0b387bde0452022-12-22T04:29:01ZengNature PortfolioScientific Reports2045-23222022-09-0112111410.1038/s41598-022-20337-xBrain inspired neuronal silencing mechanism to enable reliable sequence identificationShiri Hodassman0Yuval Meir1Karin Kisos2Itamar Ben-Noam3Yael Tugendhaft4Amir Goldental5Roni Vardi6Ido Kanter7Department of Physics, Bar-Ilan UniversityDepartment of Physics, Bar-Ilan UniversityDepartment of Physics, Bar-Ilan UniversityDepartment of Physics, Bar-Ilan UniversityDepartment of Physics, Bar-Ilan UniversityDepartment of Physics, Bar-Ilan UniversityGonda Interdisciplinary Brain Research Center, Bar-Ilan UniversityDepartment of Physics, Bar-Ilan UniversityAbstract 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.https://doi.org/10.1038/s41598-022-20337-x |
spellingShingle | Shiri Hodassman Yuval Meir Karin Kisos Itamar Ben-Noam Yael Tugendhaft Amir Goldental Roni Vardi Ido Kanter Brain inspired neuronal silencing mechanism to enable reliable sequence identification Scientific Reports |
title | Brain inspired neuronal silencing mechanism to enable reliable sequence identification |
title_full | Brain inspired neuronal silencing mechanism to enable reliable sequence identification |
title_fullStr | Brain inspired neuronal silencing mechanism to enable reliable sequence identification |
title_full_unstemmed | Brain inspired neuronal silencing mechanism to enable reliable sequence identification |
title_short | Brain inspired neuronal silencing mechanism to enable reliable sequence identification |
title_sort | brain inspired neuronal silencing mechanism to enable reliable sequence identification |
url | https://doi.org/10.1038/s41598-022-20337-x |
work_keys_str_mv | AT shirihodassman braininspiredneuronalsilencingmechanismtoenablereliablesequenceidentification AT yuvalmeir braininspiredneuronalsilencingmechanismtoenablereliablesequenceidentification AT karinkisos braininspiredneuronalsilencingmechanismtoenablereliablesequenceidentification AT itamarbennoam braininspiredneuronalsilencingmechanismtoenablereliablesequenceidentification AT yaeltugendhaft braininspiredneuronalsilencingmechanismtoenablereliablesequenceidentification AT amirgoldental braininspiredneuronalsilencingmechanismtoenablereliablesequenceidentification AT ronivardi braininspiredneuronalsilencingmechanismtoenablereliablesequenceidentification AT idokanter braininspiredneuronalsilencingmechanismtoenablereliablesequenceidentification |