Cognitive Memory Network
This work addresses hardware scalability and complexity issues for analog neural network implementations, but it appears incremental as it builds on existing resistive memory concepts with a specific application to character recognition.
The authors tackled the hardware limitations of conventional analog neural networks by proposing a resistive memory network without crossover wiring, achieving complete recognition of characters deformed by noise, rotation, scaling, and shifting through evolutionary training.
A resistive memory network that has no crossover wiring is proposed to overcome the hardware limitations to size and functional complexity that is associated with conventional analogue neural networks. The proposed memory network is based on simple network cells that are arranged in a hierarchical modular architecture. Cognitive functionality of this network is demonstrated by an example of character recognition. The network is trained by an evolutionary process to completely recognise characters deformed by random noise, rotation, scaling and shifting