The uncanny ability of over-parameterised neural networks to generalise well has been explained using various ‘simplicity biases’. These theories postulate that neural networks avoid overfitting by first fitting simple, linear classifiers before learning m ...
The design of wings is crucial for tailless Flapping-wing robots (FWRs), as these robots rely exclusively on their wings for lift generation and body control. However, the current methodology for wing design primarily depends on the experience and heuristi ...
While convolution and self-attention mechanisms have dominated architectural design in deep learning, this survey examines a fundamental yet understudied primitive: the Hadamard product. Despite its widespread implementation across various applications, th ...
The transfer of technology from research to structural engineering and construction practice is illustrated using two cases of the implementation of innovative engineering methods and technologies in the renewal and 'upcycling' of existing bridges, namely ...
While stability analysis is a mainstay for control science, especially computing regions of attraction of equilibrium points, until recently most stability analysis tools always required explicit knowledge of the model or a high-fidelity simulator represen ...
The rise of high-throughput first-principles calculations of materials since the turn of the millennium has gifted the fields of physics, quantum chemistry, and materials science with a mountainous and ever-growing pile of data ready to be mined for hidden ...
A potential framework to estimate the volume of water stored in a porous storage reservoir from seismic data is neural networks. In this study, the man-made groundwater reservoir is modeled as a coupled poroviscoelastic–viscoelastic medium, and the underly ...
Recent advancements in recommender systems have focused on integrating knowledge graphs (KGs) to leverage their auxiliary information. The core idea of KG-enhanced recommenders is to incorporate rich semantic information for more accurate recommendations. ...
We introduce a new task, novel view synthesis for LiDAR sensors. While traditional model-based LiDAR simulators with style-transfer neural networks can be applied to render novel views, they fall short of producing accurate and realistic LiDAR patterns bec ...
This thesis sets itself the goal of investigating function learning approaches. The topic is extremely relevant today, since the abundance of data, jointly with the technological progress which has enhanced computing power, now allow to represent functions ...
We prove closed-form equations for the exact high-dimensional asymptotics of a family of first-order gradient-based methods, learning an estimator (e.g., M-estimator, shallow neural network) from observations on Gaussian data with empirical risk minimizati ...
Society for Industrial & Applied Mathematics (SIAM)2024
Planning for diverse real-world robotic tasks necessitates to know and write all constraints. However, instances exist where these constraints are either unknown or challenging to specify accurately. A possible solution is to infer the unknown constraints ...
Datacenter networks are becoming increasingly flexible with the incorporation of new optical communication technologies, such as optical circuit switches, enabling self-adjusting topologies that can adapt to the traffic pattern in a demand-aware manner. In ...
Institute of Electrical and Electronics Engineers Inc.2024
Metal additive manufacturing is a recent breakthrough technology that promises automated production of complex geometric shapes at low operating costs. However, its potential is not yet fully exploited due to the low reproducibility of quality in mass prod ...
The current generation of large language models (LLMs) has limited chemical knowledge. Recently, it has been shown that these LLMs can learn and predict chemical properties through fine-tuning. Using natural language to train machine learning models opens ...
Constrained Markov decision processes (CMDPs) are a common way to model safety constraints in reinforcement learning. State-of-the-art methods for efficiently solving CMDPs are based on primal-dual algorithms. For these algorithms, all currently known regr ...
