The conditional RBM model

t-1        t

• Given the data and the previous hidden state, the hidden units at time t are conditionally independent. – So online inference is very easy if we do not need to propagate uncertainty about the hidden states. • Learning can be done by using contrastive divergence. – Reconstruct the data at time t from the inferred states of the hidden units. – The temporal connections between hiddens can be learned as if they were additional biases

t-2       t-1        t