A gradient descent algorithm for SNN with time-varying weights for reliable multiclass interpretation

Jeyasothy, A and Ramasamy, S and Sundaram, S (2024) A gradient descent algorithm for SNN with time-varying weights for reliable multiclass interpretation. In: Applied Soft Computing, 161 .

PDF App_ Sof_Com_161_2024_111747.pdf - Published Version Restricted to Registered users only Download (2MB) | Request a copy

Abstract

Interpretation of the prediction is vital for mission critical tasks. Accurate interpretation relies upon the generalization accuracy of the model. In this paper, we propose a modified gradient descent learning algorithm to improve the generalization ability of a Spiking Neural Network with time-varying weights (SNN-t). This algorithm is referred to as GradST, can help towards improving the interpretation of multiclass classification problems. We have transformed the SNN-t to a Generalized Additive Model (GAM) to provide interpretation. The resultant Spiking Additive Model (SAM) has the generalization ability of SNN-t and the interpretable characteristics of GAM for multiclass problems. We also propose a post-processing method to enable better visualization of multiple shape functions of GAMs, towards better relative interpretation for multiclass classification problems. The post-processing method utilizes the properties of multiclass GAMs to visually modify the shape functions to establish the importance of the feature in multiclass setting. We first evaluate the performance of SNN-t, trained with GradST and the SAM generated from it, on large public datasets. The SNN-t trained with GradST has better generalization accuracy than other SNN-t classifier and consequently, the SAM generated from it has better generalization accuracy than other state-of-the-art multiclass GAMs. Improved accuracy in SAM implies more reliable interpretation. Then, we evaluate the proposed post-processing method for multiclass GAMs to provide relative interpretation. It is observed that relative interpretation of multiclass GAM is more meaningful and reliable. © 2024 Elsevier B.V.

Item Type:	Journal Article
Publication:	Applied Soft Computing
Publisher:	Elsevier Ltd
Additional Information:	The copyright for this article belongs to Elsevier Ltd
Keywords:	Classification (of information); Complex networks; Function evaluation; Gradient methods; Large datasets; Network coding; Neural networks, Additive models; Encodings; Generalized additive model; Model interpretations; Multi-class classification; Neural-networks; Spiking neural network; Temporal encoding; Time-varying weight model; Time-varying weights, Time varying networks
Department/Centre:	Division of Mechanical Sciences > Aerospace Engineering(Formerly Aeronautical Engineering)
Date Deposited:	28 Jul 2024 16:49
Last Modified:	28 Jul 2024 16:49
URI:	http://eprints.iisc.ac.in/id/eprint/85168

Actions (login required)

View Item