TY - JOUR
T1 - Factored four way conditional restricted Boltzmann machines for activity recognition
AU - Mocanu, D.C.
AU - Bou Ammar, H.
AU - Lowet, D.J.C.
AU - Driessens, K.
AU - Liotta, A.
AU - Weiss, G.
AU - Tuyls, K.P.
PY - 2015
Y1 - 2015
N2 - 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.
AB - 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.
U2 - 10.1016/j.patrec.2015.01.013
DO - 10.1016/j.patrec.2015.01.013
M3 - Article
SN - 0167-8655
VL - 66
SP - 100
EP - 108
JO - Pattern Recognition Letters
JF - Pattern Recognition Letters
ER -