Factored four way conditional restricted Boltzmann machines for activity recognition

Mocanu, Decebal, Ammar, Haitham Bou, Lowet, Dietwig, Driessens, Kurt, Liotta, Antonio, Weiss, Gerhard and Tuyls, Karl (2015) Factored four way conditional restricted Boltzmann machines for activity recognition. Pattern Recognition Letters, 66. pp. 100-108.

Text ffwcrbm_preprint-2.pdf - Unspecified Download (1MB)

Abstract

This paper introduces a new learning algorithm for human activity recogni- tion capable of simultaneous regression and classification. Building upon Conditional Restricted Boltzmann Machines (CRBMs), Factored Four Way Conditional Restricted Boltzmann Machines (FFW-CRBMs) incorporate a new label layer and four-way interactions among the neurons from the different layers. The additional layer gives the classification nodes a similar strong multiplicative effect compared to the other layers, and avoids that the classification neurons are overwhelmed by the (much larger set of) other neurons. This makes FFW-CRBMs capable of performing activity recogni- tion, prediction and self auto evaluation of classification within one unified framework. As a second contribution, Sequential Markov chain Contrastive Divergence (SMcCD) is introduced. SMcCD modifies Contrastive Divergence to compensate for the extra complexity of FFW-CRBMs during training. Two sets of experiments one on benchmark datasets and one a robotic platform for smart companions show the effectiveness of FFW-CRBMs.

Item Type:	Article
Uncontrolled Keywords:	Activity recognition, Deep learning, Restricted Boltzmann machines
Depositing User:	Symplectic Admin
Date Deposited:	16 Apr 2015 15:36
Last Modified:	15 Dec 2022 15:09
DOI:	10.1016/j.patrec.2015.01.013
Related URLs:	Author Publisher
URI:	https://livrepository.liverpool.ac.uk/id/eprint/2010100