Extracting Temporal Correlations Using Hierarchical Spatio-Temporal Feature Maps

MacHireddy, A and Gowgi, P and Garani, SS (2021) Extracting Temporal Correlations Using Hierarchical Spatio-Temporal Feature Maps. In: 2021 International Joint Conference on Neural Networks, IJCNN 2021, 18- 22 July 2021, Virtual, Shenzhen.

PDF IJCNN_2021.pdf - Published Version Restricted to Registered users only Download (2MB) | Request a copy

Abstract

Self-organizing maps (SOM) are popularly used for applications in learning features, vector quantization and recalling spatial input patterns. The adaptation rule in SOM is based on the Euclidean distance between the input vector and the neuronal weight vector along with a neighborhood function that brings in topological arrangement of the neurons. It is capable of learning the spatial correlations among the data but fails to capture temporal correlations present in a sequence of inputs. We formulate a potential function based on a spatio-temporal metric and create hierarchical vector quantization feature maps by embedding memory structures similar to long short-term memories (LSTM) across the feature maps to learn the spatiotemporal correlations in the data across clusters. We derive the learning rule from first principles and estimate the computational complexity. Simulation results over a synthetic data set and a real world climate data set show that our algorithm is capable of learning the spatio-temporal mappings.

Item Type:	Conference Paper
Publication:	Proceedings of the International Joint Conference on Neural Networks
Publisher:	Institute of Electrical and Electronics Engineers Inc.
Additional Information:	The copyright for this article belongs to the Institute of Electrical and Electronics Engineers Inc.
Keywords:	Conformal mapping; Long short-term memory; Neurons; Self organizing maps; Vectors, Adaptation rules; Euclidean distance; Feature map; Features vector; Input patterns; Spatial inputs; Spatio-temporal; Spatiotemporal feature; Temporal correlations; Vector quantisation, Vector quantization
Department/Centre:	Division of Electrical Sciences > Electronic Systems Engineering (Formerly Centre for Electronic Design & Technology)
Date Deposited:	26 Nov 2023 09:37
Last Modified:	26 Nov 2023 09:37
URI:	https://eprints.iisc.ac.in/id/eprint/82952

Actions (login required)

View Item