04 Convegni (Proceedings)

04 Convegni (Proceedings): [22026] Home page macrotipologia

Sfoglia

Pubblicazioni recenti

NEvoFed: A Decentralized Approach to Federated NeuroEvolution of Heterogeneous Neural Networks

In the past few years, Federated Learning (FL) has emerged as an effective approach for training neural networks (NNs) over a computing network while preserving data privacy. Most of the existing FL approaches require the user to define a priori the same structure for all the NNs running on the clients, along with an explicit aggregation procedure. This can be a limiting factor in cases where pre-defining such algorithmic details is difficult. To overcome these issues, we propose a novel appr...

Hyperparameter selection for reliable EEG denoising using ASR: A benchmarking study

Artifacts preprocessing in EEG is remarkably significant to extract reliable neural responses in the downstream analysis. A recently emerging powerful preprocessing tool among the EEG community is Artifacts Subspace Reconstruction (ASR). ASR is an unsupervised machine learning algorithm to identify and correct the transient-like non-stationary noisy samples. ASR is fully automatic, therefore, suitable for online applications. However, the performance of ASR is strongly dependent on the user-d...

Autonomous Shape Memory Hinge for Space Applications Powered via Solar Energy

This work demonstrates a proof-of-concept autonomous hinge for the deployment of satellite radiators. The hinge utilizes the shape memory effect (SME), thanks to the use of a shape memory alloy (SMA). First SMA wires based on Nickel-Titanium are embedded into an Ecoflex polymeric material and subsequently solidified. The bending of the hinge is induced by a thermal stimulus provided by a silver-based heater printed on a 10 µm thick Polyether ether ketone (PEEK) substrate and embedded on top o...

Algorithmic Diversity and Tiny Models: Comparing Binary Networks and the Fruit Fly Algorithm on Document Representation Tasks

Neural language models have seen a dramatic increase in size in the last years. While many still advocate that ‘bigger is better’, work in model distillation has shown that the number of parameters used by very large networks is actually more than what is required for state-of-the-art performance. This prompts an obvious question: can we build smaller models from scratch, rather than going through the inefficient process of training at scale and subsequently reducing model size. In this paper...

Explaining Human Comparisons using Alignment-Importance Heatmaps

We present a computational explainability approach for human comparison tasks, using Alignment Importance Score (AIS) heatmaps derived from deep-vision models. The AIS reflects a feature-map's unique contribution to the alignment between Deep Neural Network's (DNN) representational geometry and that of humans. We first validate the AIS by showing that prediction of out-of-sample human similarity judgments is improved when constructing representations using only higher-AIS feature maps identif...

Scopri

Accesso al fulltext

no fulltext17412
reserved2830
open1440
partially open313
mixed27
embargoed4