Cargando…

Schizophrenia-Mimicking Layers Outperform Conventional Neural Network Layers

We have reported nanometer-scale three-dimensional studies of brain networks of schizophrenia cases and found that their neurites are thin and tortuous when compared to healthy controls. This suggests that connections between distal neurons are suppressed in microcircuits of schizophrenia cases. In...

Descripción completa

Detalles Bibliográficos
Autores principales: Mizutani, Ryuta, Noguchi, Senta, Saiga, Rino, Yamashita, Yuichi, Miyashita, Mitsuhiro, Arai, Makoto, Itokawa, Masanari
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8995800/
https://www.ncbi.nlm.nih.gov/pubmed/35418846
http://dx.doi.org/10.3389/fnbot.2022.851471
_version_ 1784684360368128000
author Mizutani, Ryuta
Noguchi, Senta
Saiga, Rino
Yamashita, Yuichi
Miyashita, Mitsuhiro
Arai, Makoto
Itokawa, Masanari
author_facet Mizutani, Ryuta
Noguchi, Senta
Saiga, Rino
Yamashita, Yuichi
Miyashita, Mitsuhiro
Arai, Makoto
Itokawa, Masanari
author_sort Mizutani, Ryuta
collection PubMed
description We have reported nanometer-scale three-dimensional studies of brain networks of schizophrenia cases and found that their neurites are thin and tortuous when compared to healthy controls. This suggests that connections between distal neurons are suppressed in microcircuits of schizophrenia cases. In this study, we applied these biological findings to the design of a schizophrenia-mimicking artificial neural network to simulate the observed connection alteration in the disorder. Neural networks that have a “schizophrenia connection layer” in place of a fully connected layer were subjected to image classification tasks using the MNIST and CIFAR-10 datasets. The results revealed that the schizophrenia connection layer is tolerant to overfitting and outperforms a fully connected layer. The outperformance was observed only for networks using band matrices as weight windows, indicating that the shape of the weight matrix is relevant to the network performance. A schizophrenia convolution layer was also tested using the VGG configuration, showing that 60% of the kernel weights of the last three convolution layers can be eliminated without loss of accuracy. The schizophrenia layers can be used instead of conventional layers without any change in the network configuration and training procedures; hence, neural networks can easily take advantage of these layers. The results of this study suggest that the connection alteration found in schizophrenia is not a burden to the brain, but has functional roles in brain performance.
format Online
Article
Text
id pubmed-8995800
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-89958002022-04-12 Schizophrenia-Mimicking Layers Outperform Conventional Neural Network Layers Mizutani, Ryuta Noguchi, Senta Saiga, Rino Yamashita, Yuichi Miyashita, Mitsuhiro Arai, Makoto Itokawa, Masanari Front Neurorobot Neuroscience We have reported nanometer-scale three-dimensional studies of brain networks of schizophrenia cases and found that their neurites are thin and tortuous when compared to healthy controls. This suggests that connections between distal neurons are suppressed in microcircuits of schizophrenia cases. In this study, we applied these biological findings to the design of a schizophrenia-mimicking artificial neural network to simulate the observed connection alteration in the disorder. Neural networks that have a “schizophrenia connection layer” in place of a fully connected layer were subjected to image classification tasks using the MNIST and CIFAR-10 datasets. The results revealed that the schizophrenia connection layer is tolerant to overfitting and outperforms a fully connected layer. The outperformance was observed only for networks using band matrices as weight windows, indicating that the shape of the weight matrix is relevant to the network performance. A schizophrenia convolution layer was also tested using the VGG configuration, showing that 60% of the kernel weights of the last three convolution layers can be eliminated without loss of accuracy. The schizophrenia layers can be used instead of conventional layers without any change in the network configuration and training procedures; hence, neural networks can easily take advantage of these layers. The results of this study suggest that the connection alteration found in schizophrenia is not a burden to the brain, but has functional roles in brain performance. Frontiers Media S.A. 2022-03-28 /pmc/articles/PMC8995800/ /pubmed/35418846 http://dx.doi.org/10.3389/fnbot.2022.851471 Text en Copyright © 2022 Mizutani, Noguchi, Saiga, Yamashita, Miyashita, Arai and Itokawa. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Neuroscience
Mizutani, Ryuta
Noguchi, Senta
Saiga, Rino
Yamashita, Yuichi
Miyashita, Mitsuhiro
Arai, Makoto
Itokawa, Masanari
Schizophrenia-Mimicking Layers Outperform Conventional Neural Network Layers
title Schizophrenia-Mimicking Layers Outperform Conventional Neural Network Layers
title_full Schizophrenia-Mimicking Layers Outperform Conventional Neural Network Layers
title_fullStr Schizophrenia-Mimicking Layers Outperform Conventional Neural Network Layers
title_full_unstemmed Schizophrenia-Mimicking Layers Outperform Conventional Neural Network Layers
title_short Schizophrenia-Mimicking Layers Outperform Conventional Neural Network Layers
title_sort schizophrenia-mimicking layers outperform conventional neural network layers
topic Neuroscience
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8995800/
https://www.ncbi.nlm.nih.gov/pubmed/35418846
http://dx.doi.org/10.3389/fnbot.2022.851471
work_keys_str_mv AT mizutaniryuta schizophreniamimickinglayersoutperformconventionalneuralnetworklayers
AT noguchisenta schizophreniamimickinglayersoutperformconventionalneuralnetworklayers
AT saigarino schizophreniamimickinglayersoutperformconventionalneuralnetworklayers
AT yamashitayuichi schizophreniamimickinglayersoutperformconventionalneuralnetworklayers
AT miyashitamitsuhiro schizophreniamimickinglayersoutperformconventionalneuralnetworklayers
AT araimakoto schizophreniamimickinglayersoutperformconventionalneuralnetworklayers
AT itokawamasanari schizophreniamimickinglayersoutperformconventionalneuralnetworklayers