An overview of machine learning within embedded and mobile devices–optimizations and applications

TS Ajani, AL Imoize, AA Atayero - Sensors, 2021 - mdpi.com
Embedded systems technology is undergoing a phase of transformation owing to the novel
advancements in computer architecture and the breakthroughs in machine learning …

Resource-efficient deep neural networks for automotive radar interference mitigation

J Rock, W Roth, M Toth, P Meissner… - IEEE Journal of …, 2021 - ieeexplore.ieee.org
Radar sensors are crucial for environment perception of driver assistance systems as well
as autonomous vehicles. With a rising number of radar sensors and the so far unregulated …

[HTML][HTML] Measuring creativity: an account of natural and artificial creativity

C Moruzzi - European Journal for Philosophy of Science, 2021 - Springer
Despite the recent upsurge of interest in the investigation of creativity, the question of how to
measure creativity is arguably underdiscussed. The aim of this paper is to address this gap …

[图书][B] Advanced Reduced Order Methods and Applications in Computational Fluid Dynamics

G Rozza, G Stabile, F Ballarin - 2022 - SIAM
Reduced order modeling is an important and fast-growing research field in computational
science and engineering, motivated by several reasons, of which we mention just a few …

S-rocket: Selective random convolution kernels for time series classification

H Salehinejad, Y Wang, Y Yu, T Jin… - arXiv preprint arXiv …, 2022 - arxiv.org
Random convolution kernel transform (Rocket) is a fast, efficient, and novel approach for
time series feature extraction using a large number of independent randomly initialized 1-D …

[HTML][HTML] A dimensionality reduction approach for convolutional neural networks

L Meneghetti, N Demo, G Rozza - Applied Intelligence, 2023 - Springer
The focus of this work is on the application of classical Model Order Reduction techniques,
such as Active Subspaces and Proper Orthogonal Decomposition, to Deep Neural …

[HTML][HTML] Load classification: A case study for applying neural networks in hyper-constrained embedded devices

A Agiollo, A Omicini - Applied Sciences, 2021 - mdpi.com
The application of Artificial Intelligence to the industrial world and its appliances has recently
grown in popularity. Indeed, AI techniques are now becoming the de-facto technology for the …

A tiny CNN architecture for identifying bat species from echolocation calls

I Zualkernan, J Judas, T Mahbub… - 2020 IEEE/ITU …, 2020 - ieeexplore.ieee.org
Effective monitoring of bat populations will contribute towards the United Nations' SGD 15
which is tied to maintaining biodiversity and SGD 3 which is about maintaining good health …

Detecting soccer balls with reduced neural networks: a comparison of multiple architectures under constrained hardware scenarios

DDR Meneghetti, TPD Homem, JHR de Oliveira… - Journal of Intelligent & …, 2021 - Springer
Object detection techniques that achieve state-of-the-art detection accuracy employ
convolutional neural networks, implemented to have lower latency in graphics processing …

Efficient Similarity-Based Passive Filter Pruning for Compressing CNNS

A Singh, MD Plumbley - ICASSP 2023-2023 IEEE International …, 2023 - ieeexplore.ieee.org
Convolution neural networks (CNNs) have shown great success in various applications.
However, the computational complexity and memory storage of CNNs is a bottleneck for …