Architecture for large microelectronic supervised learning artificial neural networks using a hybrid digital-analog approach

1988 ◽  
Vol 1 ◽  
pp. 389 ◽  
Author(s):  
F.J. Kub ◽  
M.G. Ancona ◽  
I.A. Mack ◽  
K. Moon ◽  
C.T. Yao
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Supervised Learning ◽  
Analog Approach ◽  
Artificial Neural

scholarly journals Computational Principles of Supervised Learning in the Cerebellum

2018 ◽  
Vol 41 (1) ◽  
pp. 233-253 ◽  
Author(s):  
Jennifer L. Raymond ◽  
Javier F. Medina
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Supervised Learning ◽  
Brain Area ◽  
Future Research ◽  
Brain Areas ◽  
Adaptive Mechanisms ◽  
Networks Analysis ◽  
Artificial Neural ◽  
Organizational Principles

Supervised learning plays a key role in the operation of many biological and artificial neural networks. Analysis of the computations underlying supervised learning is facilitated by the relatively simple and uniform architecture of the cerebellum, a brain area that supports numerous motor, sensory, and cognitive functions. We highlight recent discoveries indicating that the cerebellum implements supervised learning using the following organizational principles: ( a) extensive preprocessing of input representations (i.e., feature engineering), ( b) massively recurrent circuit architecture, ( c) linear input–output computations, ( d) sophisticated instructive signals that can be regulated and are predictive, ( e) adaptive mechanisms of plasticity with multiple timescales, and ( f) task-specific hardware specializations. The principles emerging from studies of the cerebellum have striking parallels with those in other brain areas and in artificial neural networks, as well as some notable differences, which can inform future research on supervised learning and inspire next-generation machine-based algorithms.

Supervised Learning with Artificial Neural Networks

2008 ◽  
pp. 24-40
Author(s):  
Darryl Charles ◽  
Colin Fyfe ◽  
Daniel Livingstone ◽  
Stephen McGlinchey
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Problem Solving ◽  
Supervised Learning ◽  
Learning Algorithms ◽  
Theory And Practice ◽  
Delta Rule ◽  
Neural Learning ◽  
Artificial Neural

In this chapter we will look at supervised learning in more detail, beginning with one of the simplest (and earliest) supervised neural learning algorithms – the Delta Rule. The objectives of this chapter are to provide a solid grounding in the theory and practice of problem solving with artificial neural networks – and an appreciation of some of the challenges and practicalities involved in their use.

scholarly journals A Semi-supervised Learning-Based Diagnostic Classification Method Using Artificial Neural Networks

2021 ◽  
Vol 11 ◽  
Author(s):  
Kang Xue ◽  
Laine P. Bradshaw
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Supervised Learning ◽  
Real Data ◽  
Classification Model ◽  
Diagnostic Classification ◽  
Diagnostic Quality ◽  
Q Matrix ◽  
Artificial Neural ◽  
Research Studies

The purpose of cognitive diagnostic modeling (CDM) is to classify students' latent attribute profiles using their responses to the diagnostic assessment. In recent years, each diagnostic classification model (DCM) makes different assumptions about the relationship between a student's response pattern and attribute profile. The previous research studies showed that the inappropriate DCMs and inaccurate Q-matrix impact diagnostic classification accuracy. Artificial Neural Networks (ANNs) have been proposed as a promising approach to convert a pattern of item responses into a diagnostic classification in some research studies. However, the ANNs methods produced very unstable and unappreciated estimation unless a great deal of care was taken. In this research, we combined ANNs with two typical DCMs, the deterministic-input, noisy, “and” gate (DINA) model and the deterministic-inputs, noisy, “or” gate (DINO) model, within a semi-supervised learning framework to achieve a robust and accurate classification. In both simulated study and real data study, the experimental results showed that the proposed method could achieve appreciated performance across different test conditions, especially when the diagnostic quality of assessment was not high and the Q-matrix contained misspecified elements. This research study is the first time of applying the thinking of semi-supervised learning into CDM. Also, we used the validating test to choose the appropriate parameters for the ANNs instead of using typical statistical criteria.

Sign in / Sign up

Export Citation Format

Share Document