Papers on Instantaneously Trained and Related Neural Networks

The concept of radius of generalization was introduced in CC3 and thus this neural network overcame the generalization problem that plagued the earlier CC2 network. The Hamming distance was used for classification between binary vectors, i.e. any test vector whose Hamming distance from a training vector is smaller than the radius of generalization of the network is classified in the same output class as that training vector. A unique neuron is associated with each training sample and each node in the network acts as a filter for the training sample. The filter is realized by making it act as a hyper plane to separate the corner of the n-dimensional cube represented by the training vector and hence the name corner-classification (CC) technique.