Â鶹ӰԺ

Detecting emotional situations using convolutional neural networks and distributed models of human brain activity Emotions are thought to be canonical responses to situations ancestrally linked to survival or the well-being of an organism.

Osman Malik - Fast Randomized Matrix and Tensor Interpolative Decomposition Using CountSketchIn this talk I will present our recently developed fast randomized algorithm for matrix interpolative decomposition. If time permits, I will also say a few

"Don't go with the flow -- â€“ A new tensor algebra for Neural Networks"Multi-dimensional information often involves multi-dimensional correlations that may remain latent by virtue of traditional matrix-based learning algorithms. In this study,

Induction of time inconsistency in optimal stopping problemTime inconsistency is a common phenomenon of optimal control and optimal stopping problems, especially in finance and economics. It says a player will change his optimal strategy over time.

Colton Grainger, Department of Mathematics, Â鶹ӰԺOn Characterizing the Capacity of Neural Networks using Algebraic TopologyThe learnability of different neural architectures can be characterized directly by computable

Music Data Mining: Finding structure in songAn introduction to basic music data mining techniques

Exploiting Low-Dimensional Structure in Optimization Under UncertaintyIn computational science, optimization under uncertainty (OUU) provides a new methodology for building designs reliable under a variety of conditions with improved efficiency over

Fast Rates for Unbounded Losses: from ERM to Generalized BayesI will present new excess risk bounds for randomized and deterministic estimators, discarding boundedness assumptions to handle general unbounded loss functions like log loss and squared

Fast Algorithms and Community Software for Physical Prediction, Inference, and DesignPhysically-based computational models are the foundation of modern science and engineering, providing the only path to reliable prediction and inference in the

Online Optimization with FeedbackThe talk focuses on the design and analysis of running (i.e., online) algorithmic solutions to control systems or networked systems based on performance objectives and engineering constraints that may evolve over