Schizophrenia-mimicking layers outperform conventional neural network layers

09/23/2020
by   Ryuta Mizutani, et al.
0

We have reported nanometer-scale three-dimensional studies of brain networks of schizophrenia cases and found that their neurites are thin and tortuous compared to healthy controls. This suggests that connections between distal neurons are impaired in microcircuits of the schizophrenia cases. In this study, we applied this biological findings to designing schizophrenia-mimicking artificial neural network to simulate the connection impairment in the disorder. Neural networks having the schizophrenia connection layer in place of fully connected layer were subjected to image classification tasks using MNIST and CIFAR-10 datasets. The obtained results revealed that the schizophrenia connection layer is tolerant to overfitting and outperforms fully connected layer. Schizophrenia-mimicking convolution layer was also tested with the VGG configuration, showing that 60 can be eliminated while keeping competitive performance. Schizophrenia-mimicking layers can be used instead of fully-connected or convolution layers without any change in the network configuration and training procedures, hence the outperformance of the schizophrenia-mimicking layer is easily incorporated in neural networks. The results of this study indicate that the connection impairment in schizophrenia is not a burden to the brain, but has some functional roles to attain a better brain performance. We suggest that the seemingly neuropathological alterations observed in schizophrenia have been rationally implemented in our brain during the process of biological evolution.

READ FULL TEXT
research
05/17/2023

Connected Hidden Neurons (CHNNet): An Artificial Neural Network for Rapid Convergence

The core purpose of developing artificial neural networks was to mimic t...
research
11/06/2017

Characterizing Sparse Connectivity Patterns in Neural Networks

We propose a novel way of reducing the number of parameters in the stora...
research
06/05/2019

Visual Confusion Label Tree For Image Classification

Convolution neural network models are widely used in image classificatio...
research
06/27/2019

A shallow residual neural network to predict the visual cortex response

Understanding how the visual cortex of the human brain really works is s...
research
06/09/2023

Weight Freezing: A Regularization Approach for Fully Connected Layers with an Application in EEG Classification

In the realm of EEG decoding, enhancing the performance of artificial ne...
research
07/29/2021

Structure and Performance of Fully Connected Neural Networks: Emerging Complex Network Properties

Understanding the behavior of Artificial Neural Networks is one of the m...
research
08/31/2018

An Adaptive Locally Connected Neuron Model: Focusing Neuron

We present a new artificial neuron model capable of learning its recepti...

Please sign up or login with your details

Forgot password? Click here to reset