We consider the problem of learning a target function corresponding to a deep, extensive-width, non-linear neural network with random Gaussian weights. We consider the asymptotic limit where the number of samples, the input dimension and the network width ...
Using robotics to automate complex manipulation tasks such as cooking could offer significant advantages. Robotics could offer improved throughput, provide assistance for those that lack the required mobility or allow for creative robotic chefs. Generating ...
This thesis consists of three applications of machine learning techniques to risk management. The first chapter proposes a deep learning approach to estimate physical forward default intensities of companies. Default probabilities are computed using artifi ...
Deep learning algorithms are responsible for a technological revolution in a variety oftasks including image recognition or Go playing. Yet, why they work is not understood.Ultimately, they manage to classify data lying in high dimension – a feat generical ...
We introduce a variational framework to learn the activation functions of deep neural networks. Our aim is to increase the capacity of the network while controlling an upper-bound of the actual Lipschitz constant of the input-output relation. To that end, ...
