scholarly journals An Autoencoder-Based Deep Learning Classifier for Efficient Diagnosis of Autism

Children ◽  
2020 ◽  
Vol 7 (10) ◽  
pp. 182
Author(s):  
Harshini Sewani ◽  
Rasha Kashef
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Learning ◽  
Data Exchange ◽  
Neurodevelopmental Disorder ◽  
Autism Spectrum ◽  
Imaging Data ◽  
Neural Network Learning ◽  
Network Learning ◽  
Unsupervised Neural Network

Autism spectrum disorder (ASD) is a neurodevelopmental disorder characterized by a lack of social communication and social interaction. Autism is a mental disorder investigated by social and computational intelligence scientists utilizing advanced technologies such as machine learning models to enhance clinicians’ ability to provide robust diagnosis and prognosis of autism. However, with dynamic changes in autism behaviour patterns, these models’ quality and accuracy have become a great challenge for clinical practitioners. We applied a deep neural network learning on a large brain image dataset obtained from ABIDE (autism brain imaging data exchange) to provide an efficient diagnosis of ASD, especially for children. Our deep learning model combines unsupervised neural network learning, an autoencoder, and supervised deep learning using convolutional neural networks. Our proposed algorithm outperforms individual-based classifiers measured by various validations and assessment measures. Experimental results indicate that the autoencoder combined with the convolution neural networks provides the best performance by achieving 84.05% accuracy and Area under the Curve (AUC) value of 0.78.

Local Learning Algorithms for Sequential Tasks in Neural Networks

1998 ◽  
Vol 2 (6) ◽  
pp. 221-227 ◽  
Author(s):  
Anthony Robins ◽  
◽  
Marcus Frean ◽  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Learning Algorithms ◽  
Learning Task ◽  
Sequential Learning ◽  
Local Learning ◽  
Neural Network Learning ◽  
Network Learning ◽  
Sequential Task ◽  
Global And Local

In this paper, we explore the concept of sequential learning and the efficacy of global and local neural network learning algorithms on a sequential learning task. Pseudorehearsal, a method developed by Robins19) to solve the catastrophic forgetting problem which arises from the excessive plasticity of neural networks, is significantly more effective than other local learning algorithms for the sequential task. We further consider the concept of local learning and suggest that pseudorehearsal is so effective because it works directly at the level of the learned function, and not indirectly on the representation of the function within the network. We also briefly explore the effect of local learning on generalization within the task.

Adaptive Control Based on Neural Network for Ship Sterring Autopilot

2012 ◽  
Vol 503-504 ◽  
pp. 1239-1242
Author(s):  
Guan Shan Hu
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Reference Model ◽  
Learning Algorithm ◽  
Adaptive Controller ◽  
Membership Functions ◽  
Neural Network Learning ◽  
Network Learning ◽  
Ship Steering ◽  
Course Control

The Autopilot is importance for a ship to navigate safely and economically, so we proposes an intelligent reference modeling adaptive controller for ship steering based on neural networks. In order to satisfy the requirements of ship’s course control under various sea status, we used fuzzy logic and neural networks to design the feedback controller, used multilayer perceptron neural network to design the reference model and the identification network. In order to enhance adaptive characteristics of the controller，the parameters of membership functions and connection weights etc were revised online with neural network learning algorithm. The results of simulation shown that the performance of the ship controller is valuable and effective.

scholarly journals Mimicry Embedding Facilitates Advanced Neural Network Training for Image-Based Pathogen Detection

mSphere ◽  
2020 ◽  
Vol 5 (5) ◽  
Author(s):  
Artur Yakimovich ◽  
Moona Huttunen ◽  
Jerzy Samolej ◽  
Barbara Clough ◽  
Nagisa Yoshida ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Learning ◽  
Deep Neural Networks ◽  
Network Evolution ◽  
Great Promise ◽  
Data Sets ◽  
Imaging Data ◽  
Data Set ◽  
Novel Strategy

ABSTRACT The use of deep neural networks (DNNs) for analysis of complex biomedical images shows great promise but is hampered by a lack of large verified data sets for rapid network evolution. Here, we present a novel strategy, termed “mimicry embedding,” for rapid application of neural network architecture-based analysis of pathogen imaging data sets. Embedding of a novel host-pathogen data set, such that it mimics a verified data set, enables efficient deep learning using high expressive capacity architectures and seamless architecture switching. We applied this strategy across various microbiological phenotypes, from superresolved viruses to in vitro and in vivo parasitic infections. We demonstrate that mimicry embedding enables efficient and accurate analysis of two- and three-dimensional microscopy data sets. The results suggest that transfer learning from pretrained network data may be a powerful general strategy for analysis of heterogeneous pathogen fluorescence imaging data sets. IMPORTANCE In biology, the use of deep neural networks (DNNs) for analysis of pathogen infection is hampered by a lack of large verified data sets needed for rapid network evolution. Artificial neural networks detect handwritten digits with high precision thanks to large data sets, such as MNIST, that allow nearly unlimited training. Here, we developed a novel strategy we call mimicry embedding, which allows artificial intelligence (AI)-based analysis of variable pathogen-host data sets. We show that deep learning can be used to detect and classify single pathogens based on small differences.

scholarly journals Robot Manipulators Control with Guaranteed Stability Using Feedback Error Learning Neural Networks

1996 ◽  
Vol 8 (4) ◽  
pp. 383-391
Author(s):  
Ju-Jang Lee ◽  
◽  
Sung-Woo Kim ◽  
Kang-Bark Park
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Learning Rule ◽  
Neural Network Learning ◽  
Network Learning ◽  
The Neural Network ◽  
Control Schemes ◽  
Feedback Error Learning ◽  
Feedback Error ◽  
Error Learning

Among various neural network learning control schemes, feedback error learning(FEL)8),9) has been known that it has advantages over other schemes. However, such advantages are founded on the assumption that the systems is linearly parameterized and stable. Thus, FEL has difficulties in coping with uncertain and unstable systems. Furthermore, it is not clear how the learning rule of FEL is obtained in the minimization sense. Therefore, to overcome such problems, we propose neural network control schemes using FEL with guaranteed performance. The proposed strategy is to use multi-layer neural networks, to design a stabilityguaranteeing controller(SGC), and to derive a learning rule to obtain the tracking performance. Using multilayer neural networks we can fully utilize the learning capability no matter how the system is linearly parameterized or not. The SGC makes it possible for the neural network to learn without fear of instability. As a result, the more the neural network learning proceeds, the better the tracking performance becomes.

scholarly journals SYSTEM OF AUTOMATIC MICROSCOPIC ANALYSIS OF BIOMATERIALS FOR DIAGNOSTICS OF ONCOLOGICAL PATHOLOGIES USING TRAINED NEURAL NETWORKS AND TELEMEDICAL CONSULTATIONS

2019 ◽  
pp. 76-81
Author(s):  
Yu. S. Kucherov ◽  
V. N. Lobanov ◽  
V. S. Medovy ◽  
M. I. Cheldiev ◽  
P. B. Chuchkalov
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Microscopic Analysis ◽  
Labor Intensity ◽  
Expert Evaluation ◽  
Population Surveys ◽  
Scanning Microscope ◽  
Neural Network Learning ◽  
Network Learning ◽  
Diagnostic Potential

Labor  intensity,  complexity  of  morphology,  the  shortage  of  qualified  specialists  do  not  allow  full  use  of  the  diagnostic  potential  of   microscopic  analysis  of  biomaterials  in  mass  population  surveys.  The  article  discusses  the  technology  of  creating  an  Automatic   Scan  Microscope  Analyzer  of  Oncological  Pathologies  (ASMAOP)  that  uses  neural  network  learning  during  regular  telemedicine   consultations  with  expert  evaluation  of  digital  copies  of  biomaterials  produced  by  a  scanning  microscope.  The  scheme  of  work  of   ASMAOP  in  the  composition  of  a  telemedicine  network,  hardware  solutions  including  platform  for  deep  learning  are  considered.   The  purpose  of  creation  of  ASMAOP  is  to  perform  microscopic  analyses  at  the  level  of  the  experienced  experts  with  a  significant   advantage  in  performance  and  availability.

scholarly journals FUNCTIONAL MAGNETIC RESONANCE IMAGING FOR AUTISM SPECTRUM DISORDER DETECTION USING DEEP LEARNING

2021 ◽  
Vol 83 (3) ◽  
pp. 45-52
Author(s):  
R. Nur Syahindah Husna ◽  
A. R. Syafeeza ◽  
Norihan Abdul Hamid ◽  
Y. C. Wong ◽  
R. Atikah Raihan
Keyword(s):  
Magnetic Resonance Imaging ◽  
Deep Learning ◽  
Magnetic Resonance ◽  
Functional Magnetic Resonance Imaging ◽  
Brain Imaging ◽  
Data Exchange ◽  
Autism Spectrum ◽  
Imaging Data ◽  
Functional Magnetic Resonance ◽  
Resonance Imaging

Autism Spectrum Disorders (ASDs) define as a scope of disability in the development of certain conditions such as social communication, imagination, and patients' capabilities to make some connection. In Malaysia, the number of ASD cases diagnosed is increasing each year. Typically, ASD patients are analyzed by doctors based on history and behavior observation without the ability to diagnose instantaneously. This research intends to study the ASD biomarker based on neuroimaging functional Magnetic Resonance Imaging (fMRI) images, which can aid doctors in diagnosing ASD. This study applies a deep learning method from Convolutional Neural Network (CNN) variants to detect either the patients are ASD or non-ASD and extract the robust characteristics from neuroimages in fMRI. Then, it interprets the performance of pre-processed images in the form of accuracy to classify the neural patterns. The Autism Brain Imaging Data Exchange (ABIDE) dataset was used to research the brain imaging of ASD patients. The results achieved using CNN models namely VGG-16 and ResNet-50 are 63.4% and 87.0% accuracy, respectively. This method also assists doctors in detecting Autism from a quantifiable method that is not dependent on the behavioral observations of suspected autistic children.

Sign in / Sign up

Export Citation Format

Share Document