NeRFs have revolutionized the world of per-scene radiance field reconstruction because of
their intrinsic compactness. One of the main limitations of NeRFs is their slow rendering …

Abstract LOBSTER (LOss-Based SensiTivity rEgulaRization) is a method for training neural
networks having a sparse topology. Let the sensitivity of a network parameter be the …

While deep neural networks are highly effective at solving complex tasks, large pre-trained
models are commonly employed even to solve consistently simpler downstream tasks …

Neural network pruning allows for impressive theoretical reduction of models sizes and
complexity. However it usually offers little practical benefits as it is most often limited to just …

Deploying AI models on edge computing platforms enhances real-time performance,
reduces network dependency, and ensures data privacy on terminal devices. However …

Recent advances in deep learning optimization showed that, with some a-posteriori
information on fully-trained models, it is possible to match the same performance by simply …

The design of sparse neural networks, ie, of networks with a reduced number of parameters,
has been attracting increasing research attention in the last few years. The use of sparse …

This works explores the benefits of structured parameter pruning in the framework of the
MPEG standardization efforts for neural network compression. First less relevant parameters …

ABSTRACT Network Intrusion Detection Systems (NIDS) play a crucial role in ensuring
cybersecurity across various digital infrastructures. However, traditional NIDS face …

The likelihood of encountering in-training failures rises substantially with larger Deep
Learning (DL) training workloads, leading to lost work and resource wastage. Such failures …