no code implementations • 25 Feb 2022 • L. Zancato, A. Achille, G. Paolini, A. Chiuso, S. Soatto
We present an end-to-end differentiable neural network architecture to perform anomaly detection in multivariate time series by incorporating a Sequential Probability Ratio Test on the prediction residual.
no code implementations • 27 Oct 2019 • R. Fioresi, P. Chaudhari, S. Soatto
Stochastic gradient descent (SGD) is a key ingredient in the training of deep neural networks and yet its geometrical significance appears elusive.
no code implementations • CVPR 2014 • J. Balzer, S. Soatto
We develop a method for optimization in shape spaces, i. e., sets of surfaces modulo re-parametrization.
1 code implementation • 11 Nov 2013 • J. Balzer, M. Peters, S. Soatto
We explore the application of volumetric reconstruction from structured-light sensors in cognitive neuroscience, specifically in the quantification of the size-weight illusion, whereby humans tend to systematically perceive smaller objects as heavier.