Training of CC4 Neural Network with Spread Unary Coding
This addresses a problem in computational neuroscience by exploring biological data representation, but it is incremental as it modifies an existing algorithm.
The paper adapted the corner classification algorithm (CC4) to train neural networks using spread unary inputs, showing that misclassification rates are not highly sensitive to the generalization radius in pattern classification experiments.
This paper adapts the corner classification algorithm (CC4) to train the neural networks using spread unary inputs. This is an important problem as spread unary appears to be at the basis of data representation in biological learning. The modified CC4 algorithm is tested using the pattern classification experiment and the results are found to be good. Specifically, we show that the number of misclassified points is not particularly sensitive to the chosen radius of generalization.