STAM-SNN: Spatio-Temporal Associative Memory in Brain-Inspired Spiking Neural Networks: Concepts and Perspectives

The paper introduces the main principles of spatio-temporal associative memory (STAM) inspired by learning principles in the human brain and implemented on a brain -inspired spiking neural network (SNN) architecture. A STAM-SNN is a machine learning model that is trained on a full set of spatio-temporal variables, but can be successfully recalled on only a subset of the variables measured in different time intervals. In addition, a STAM-SNN model can be further incrementally trained on a new subset of variables measured at varying times. STAM-SNN is based on spatio-temporal learning (STL), where existing spatial or other relevant information from the data is used to structure a SNN model and then temporal information is used to train the model. The model captures evolvable and explainable spatio/specro temporal patterns. A STAM-SNN model is validated through the introduced association- and generalization accuracy. Departing from traditional deep neural networks and machine learning methods, where trained models can only be recalled or incrementally trained on the same set of variables using vector-based representation, STAM-SNN opens the field of machine intelligence for the development of large-scale global spatio-temporal models that can be recalled and used locally, within the available local spatio-temporal data. Possible applications for STAM-SNN include: biological and brain signals; audio-visual data; seismic sensory data; financial and economic data; and other.