ABSTRACT
The chapter presents Multi-layer Auto Resonance Networks (ARNs), a new neural model, for image recognition. Neurons in ARN, called Nodes, latch on to an incoming pattern and resonate when the input is within its ‘coverage’. Resonance allows the neuron to be noise tolerant and tunable. Coverage of nodes gives them an ability to approximate the incoming pattern. Its latching characteristics allow it to respond to episodic events without disturbing the existing trained network. These networks are capable of addressing problems in varied fields but have not been sufficiently explored. Implementation of an image classification and identification system using two-layer ARN is discussed in this chapter. Recognition accuracy of 94% has been achieved for MNIST dataset with only two layers of neurons and just 50 samples per numeral, making it useful in computing at the edge of cloud infrastructure.
