Factored four way conditional restricted Boltzmann machines for activity recognition

D.C. Mocanu, H. Bou Ammar, D.J.C. Lowet, K. Driessens, A. Liotta, G. Weiss, K.P. Tuyls

Research output: Contribution to journalArticleAcademicpeer-review

38 Citations (Scopus)
309 Downloads (Pure)


This paper introduces a new learning algorithm for human activity recognition 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 recognition, 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.
Original languageEnglish
Pages (from-to)100-108
JournalPattern Recognition Letters
Publication statusPublished - 2015


Dive into the research topics of 'Factored four way conditional restricted Boltzmann machines for activity recognition'. Together they form a unique fingerprint.

Cite this