Multi-Level Error-Resilient Neural Networks with Learning
This work addresses a gap in neural network design for pattern retrieval, offering a more balanced solution, though it appears incremental in nature.
The paper tackles the problem of neural network association by proposing a method that simultaneously improves learning, pattern retrieval capacity, and noise resilience, showing drastic improvements in retrieval capacity and fair noise tolerance.
The problem of neural network association is to retrieve a previously memorized pattern from its noisy version using a network of neurons. An ideal neural network should include three components simultaneously: a learning algorithm, a large pattern retrieval capacity and resilience against noise. Prior works in this area usually improve one or two aspects at the cost of the third. Our work takes a step forward in closing this gap. More specifically, we show that by forcing natural constraints on the set of learning patterns, we can drastically improve the retrieval capacity of our neural network. Moreover, we devise a learning algorithm whose role is to learn those patterns satisfying the above mentioned constraints. Finally we show that our neural network can cope with a fair amount of noise.