Normalization techniques are essential for accelerating the training and improving the
generalization of deep neural networks (DNNs), and have successfully been used in various …

As a powerful modelling method, piecewise linear neural networks (PWLNNs) have proven
successful in various fields, most recently in deep learning. To apply PWLNN methods, both …

The pairwise interaction paradigm of graph machine learning has predominantly governed
the modelling of relational systems. However, graphs alone cannot capture the multi-level …

Neural Architecture Search (NAS) has been explosively studied to automate the discovery of
top-performer neural networks. Current works require heavy training of supernet or intensive …

Abstract Spiking Neural Networks (SNNs) have gained huge attention as a potential energy-
efficient alternative to conventional Artificial Neural Networks (ANNs) due to their inherent …

Accuracy predictor is a key component in Neural Architecture Search (NAS) for ranking
architectures. Building a high-quality accuracy predictor usually costs enormous …

In the past decade, deep learning became the prevalent methodology for predictive
modeling thanks to the remarkable accuracy of deep neural networks in tasks such as …

Neural networks tend to achieve better accuracy with training if they are larger {—} even if
the resulting models are overparameterized. Nevertheless, carefully removing such excess …

Deep learning (DL) has proven to be a highly effective approach for developing models in
diverse contexts, including visual perception, speech recognition, and machine translation …

Training-free network architecture search (NAS) aims to discover high-performing networks
with zero-cost proxies capturing network characteristics related to the final performance …