Apoptotic self-organized electronic device using thin-film transistors for artificial neural networks with unsupervised learning functions

2015 ◽  
Vol 54 (3S) ◽  
pp. 03CB02 ◽  
Author(s):  
Mutsumi Kimura ◽  
Tomoaki Miyatani ◽  
Yusuke Fujita ◽  
Tomohiro Kasakawa
Keyword(s):  
Thin Film ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
Unsupervised Learning ◽  
Thin Film Transistors ◽  
Electronic Device ◽  
Self Organized ◽  
Learning Functions ◽  
Artificial Neural

Estimation of optical constants of thin film by the use of artificial neural networks

1996 ◽  
Vol 35 (25) ◽  
pp. 5035 ◽  
Author(s):  
Yuan-sheng Ma ◽  
Xu Liu ◽  
Pei-fu Gu ◽  
Jin-fa Tang
Keyword(s):  
Thin Film ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
Optical Constants ◽  
Artificial Neural

Automatic Detection of Arrhythmias Using Wavelets and Self-Organized Artificial Neural Networks

2009 ◽  
Author(s):  
Sérgio Renato Rogal Jr ◽  
Alfredo Beckert Neto ◽  
Marcus Vinícius ◽  
Mazega Figueredo ◽  
Emerson Cabrera Paraiso ◽  
...  
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Automatic Detection ◽  
Self Organized ◽  
Artificial Neural

Unsupervised Learning in Artificial Neural Networks

2008 ◽  
pp. 48-90
Author(s):  
Darryl Charles ◽  
Colin Fyfe ◽  
Daniel Livingstone ◽  
Stephen McGlinchey
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Unsupervised Learning ◽  
Input Data ◽  
Descent Methods ◽  
Training Set ◽  
Human Capabilities ◽  
Artificial Neural ◽  
Do So

With the artificial neural networks which we have met so far, we must have a training set on which we already have the answers to the questions which we are going to pose to the network. Yet humans appear to be able to learn (indeed some would say can only learn) without explicit supervision. The aim of unsupervised learning is to mimic this aspect of human capabilities and hence this type of learning tends to use more biologically plausible methods than those using the error descent methods of the last two chapters. The network must self-organise and to do so, it must react to some aspect of the input data - typically either redundancy in the input data or clusters in the data; i.e. there must be some structure in the data to which it can respond.

Synaptic plasticity, metaplasticity and memory effects in hybrid organic–inorganic bismuth-based materials

Nanoscale ◽  
2019 ◽  
Vol 11 (3) ◽  
pp. 1080-1090 ◽  
Author(s):  
Tomasz Mazur ◽  
Piotr Zawal ◽  
Konrad Szaciłowski
Keyword(s):  
Thin Film ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
Synaptic Plasticity ◽  
Memory Effects ◽  
Bismuth Iodide ◽  
Artificial Neural ◽  
Thin Film Devices

Herein, we present memristive, thin film devices made of methylammonium bismuth iodide that exhibit a wide variety of neuromorphic effects simultaneously. Described materials have the potential to become universal cells in artificial neural networks.

scholarly journals Acquisition and Analysis of EMG Signals to Recognize Multiple Hand Movements for Prosthetic Applications

2012 ◽  
Vol 9 (2) ◽  
pp. 145-155 ◽  
Author(s):  
Giuseppina Gini ◽  
Matteo Arvetti ◽  
Ian Somlai ◽  
Michele Folgheraiter
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Classification System ◽  
Electronic Device ◽  
Hand Movements ◽  
Hand Prosthesis ◽  
Wavelet Features ◽  
Artificial Neural ◽  
Natural Way

One of the main problems in developing active prosthesis is how to control them in a natural way. In order to increase the effectiveness of hand prostheses there is a need in better exploiting electromyography (EMG) signals. After an analysis of the movements necessary for grasping, we individuated five movements for the wrist-hand mobility. Then we designed the basic electronics and software for the acquisition and the analysis of the EMG signals. We built a small size electronic device capable of registering them that can be integrated into a hand prosthesis. Among all the numerous muscles that move the fingers, we have chosen the ones in the forearm and positioned only two electrodes. To recognize the operation, we developed a classification system, using a novel integration of Artificial Neural Networks (ANN) and wavelet features.

Sign in / Sign up

Export Citation Format

Share Document