Related Experiment Videos

Analog design of a new neural network for optical character recognition

I P Morns, S S Dlay

IEEE Transactions on Neural Networks

|February 7, 2008

Abstract:

An electronic circuit is presented for a new type of neural network, which gives a recognition rate of over 100 kHz. The network is used to classify handwritten numerals, presented as Fourier and wavelet descriptors, and has been shown to train far quicker than the popular backpropagation network while maintaining classification accuracy.

Related Concept Videos

Neural Circuits

Neural Circuits

Neural circuits and neuronal pools are two of the main structures found in the nervous system. Neural circuits are networks of neurons that work together to carry out a specific task or process. They consist of interconnected neurons and glial cells, which provide structural and metabolic support.
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...

Articles linked to this work by shared authors, journal, and citation graph.

Underdetermined reverberant acoustic source separation using weighted full-rank nonnegative tensor models.

The Journal of the Acoustical Society of America·2016

Single-channel blind separation using L₁-sparse complex non-negative matrix factorization for acoustic signals.

The Journal of the Acoustical Society of America·2015

Variational regularized 2-D nonnegative matrix factorization.

IEEE transactions on neural networks and learning systems·2014

Single-channel blind separation using pseudo-stereo mixture and complex 2-D histogram.

IEEE transactions on neural networks and learning systems·2014

The DSFPN, a new neural network for optical character recognition.

IEEE transactions on neural networks·2008

Nonlinear signal separation for multinonlinearity constrained mixing model.

IEEE transactions on neural networks·2006

See all related articles