Despite the widespread empirical success of ResNet, the generalization properties of deep ResNet are rarely explored beyond the lazy training regime. In this work, we investigate scaled ResNet in the limit of infinitely deep and wide neural networks, of wh ...
The present work proposes a framework for nonlinear model order reduction based on a Graph Convolutional Autoencoder (GCA-ROM). In the reduced order modeling (ROM) context, one is interested in obtaining real -time and many-query evaluations of parametric ...
To obtain a more complete understanding of material microstructure at the nanoscale and to gain profound insights into their properties, there is a growing need for more efficient and precise methods that can streamline the process of 3D imaging using a tr ...
In recent years, there has been a significant revolution in the field of deep learning, which has demonstrated its effectiveness in automatically capturing intricate patterns from large datasets. However, the majority of these successes in Computer Vision ...
We present a statistical framework to benchmark the performance of reconstruction algorithms for linear inverse problems, in particular, neural-network-based methods that require large quantities of training data. We generate synthetic signals as realizati ...
Within the context of contemporary machine learning problems, efficiency of optimization process depends on the properties of the model and the nature of the data available, which poses a significant problem as the complexity of either increases ad infinit ...
Natural language processing and other artificial intelligence fields have witnessed impressive progress over the past decade. Although some of this progress is due to algorithmic advances in deep learning, the majority has arguably been enabled by scaling ...
The thesis at hand is concerned with robots' navigation in human crowds. Specifically, methods are developed for planning a mobile robot's local motion between pedestrians, and they are evaluated in experiments where a robot interacts with real pedestrians ...
ML-based edge devices may face memory and computational errors that affect applications' reliability and performance. These errors can be the result of particular working conditions (e.g., radiation areas in physical experiments or avionics) or could be th ...
Bolometry is an essential diagnostic for calculating the power balances and for the understanding of different physical aspects of tokamak experiments. The reconstruction method based on the Maximum Likelihood (ML) principle, developed initially for JET, h ...
