The Need for Scalable Digital Spiking Neurons.

Spiking neural networks (SNNs) are emerging as energy efficient computational frameworks for learning to solve complex problems in data science. However, many designs for digital spiking neurons run into scalability issues due to large amounts of multiplication and complex time modeling. This work compares the strengths and the weaknesses in terms of scalability of currently implemented digital spiking neurons. Then, this work proposes a new digital spiking neuron design using spike latency encoding to overcome scalability problems. The neuron's operation and place within a SNN is discussed along with an example demonstration of its functionality.