The capabilities of deep learning systems have advanced much faster than our ability to understand them. Whilst the gains from deep neural networks (DNNs) are significant, they are accompanied by a growing risk and gravity of a bad outcome. This is troubli ...
The field of biometrics, and especially face recognition, has seen a wide-spread adoption the last few years, from access control on personal devices such as phones and laptops, to automated border controls such as in airports. The stakes are increasingly ...
Driven by the need for more efficient and seamless integration of physical models and data, physics -informed neural networks (PINNs) have seen a surge of interest in recent years. However, ensuring the reliability of their convergence and accuracy remains ...
Modern computing has enhanced our understanding of how social interactions shape collective behaviour in animal societies. Although analytical models dominate in studying collective behaviour, this study introduces a deep learning model to assess social in ...
Perovskite solar cells (PSCs) have garnered significant attention within the photovoltaic research community due to their remarkable progress in just one decade. Among the device configurations, the p-i-n structured PSC offers several advantages, including ...
Buildings play a pivotal role in the ongoing worldwide energy transition, accounting for 30% of the global energy consumption. With traditional engineering solutions reaching their limits to tackle such large-scale problems, data-driven methods and Machine ...
In this PhD manuscript, we explore optimisation phenomena which occur in complex neural networks through the lens of 2-layer diagonal linear networks. This rudimentary architecture, which consists of a two layer feedforward linear network with a diagonal ...
Photovoltaic (PV) technology is necessary for global decarbonization. However, one of the challenges of the technology is that its land use may conflict with other space demands. Building-integrated photovoltaic (BIPV) is a solution to efficiently use the ...
The performance of machine learning algorithms is conditioned by the availability of training datasets, which is especially true for the field of nondestructive evaluation. Here we propose one reconfigurable specimen instead of numerous reference specimens ...
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 ...
