File Exchange

image thumbnail

Character recognition using HAM (Neural Network)

version (17.9 KB) by Bhartendu
Neural Network using Auto Associative memory method to store 5 characters


Updated 01 Jun 2017

View License

A Hopfield Network has the following architecture:
◮ Recurrent network, weights Wij
◮ Symmetric weights, i.e. Wij= Wji
◮ All neurons can act as input units and all units are output units
◮ It’s a dynamical system (more precisely “attractor network”):
◮ It’s possible to store memory items in the weights W of the network and use it as associative memory
◮ Very simple model
◮ Nice mathematical analysis possible (also for capacity)
◮ Dynamics of the system are constrained to fixed points
◮ No storage of time series
◮ Low capacity
Related Examples:
1. Car detection from images

2. Perceptron Learning (Neural Networks)

3. Hebbian Learning (Neural Networks)

4. Delta Learning rule, Widrow-Hoff Learning rule (Artificial Neural Networks)

Cite As

Bhartendu (2020). Character recognition using HAM (Neural Network) (, MATLAB Central File Exchange. Retrieved .

Comments and Ratings (2)


Related Examples

>> character recognition

MATLAB Release Compatibility
Created with R2015a
Compatible with any release
Platform Compatibility
Windows macOS Linux