Weightless neural networks (WNNs) are a type of neural model which use random access memory (RAM) to determine neuron activation, as opposed to weights and dot products commonly used in modern deep learning approaches. This makes WNN attractive for a class of applications wherein the computational load (and energy requirements) is limited due to device size, cost or battery lifetimes. Furthermore, WNN have a large VC dimension, indicating that the lowered costs do not imply in a reduction of classification ability. The Vapnik–Chervonenkis (VC) dimension measures the complexity of the knowledge represented by a set of functions that can be encoded by a binary classification algorithm. Previous work demonstrates that the VC dimension of WiSARD is very large indicating a large capacity for discrimination at reduced resource costs.

--

neural networks,random access memory

• Computer and Information Sciences - Natural Sciences