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 ...
Having a single neural network to handle a wide and varied range of tasks and modalities has been a long-standing goal. Such a model brings notable advantages, such as test-time computational efficiency, modality fusion, and reduced model size. Our goal in ...
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 ...
This paper analyzes the implementation of least-mean-squares (LMS)-based, adaptive diffusion algorithms over networks in the frequency-domain (FD). We focus on a scenario of noisy links and include a moving-average step for denoising after self-learning to ...
Objective. Recent results have shown the potentials of neural interfaces to provide sensory feedback to subjects with limb amputation increasing prosthesis usability. However, their advantages for decoding motor control signals over current methods based o ...
The computational load associated with computer vision is often prohibitive, and limits the capacity for on-board image analysis in compact mobile robots. Replicating the kind of feature detection and neural processing that animals excel at remains a chall ...
In this work we present a residual based a posteriori error estimation for a heat equation with a random forcing term and a random diffusion coefficient which is assumed to depend affinely on a finite number of independent random variables. The problem is ...
