PSA Gradient Estimators for Stochastic Binary Networks (2020)
In neural networks with binary activations and or binary weights the training by gradient descent is complicated as the model has piecewise constant response. We consider stochastic binary networks, obtained by adding noises in front of activations. The expected model response becomes a smooth function of parameters, its gradient is well defined but it is challenging to estimate it accurately. We propose a new method for this estimation problem combining sampling and analytic approximation steps.
Joint segmentation detection and tracking (2017-2020)
We have developed a novel method for joint segmentation, detection and tracking of multiple objects. The method is based on a probabilistic model that is defined implicitly in terms of a Markov chain Monte Carlo algorithm. The parameters of the model are learned using an objective based on empirical risk minimization.