Tiny Classifier Circuits: Evolving Accelerators for Tabular Data

Autor: Iordanou, Konstantinos, Atkinson, Timothy, Ozer, Emre, Kufel, Jedrzej, Biggs, John, Brown, Gavin, Lujan, Mikel

A typical machine learning (ML) development cycle for edge computing is to maximise the performance during model training and then minimise the memory/area footprint of the trained model for deployment on edge devices targeting CPUs, GPUs, microcontr

Externí odkaz: http://arxiv.org/abs/2303.00031

Exploring Sparse Visual Odometry Acceleration with High-Level Synthesis

Autor: Ye, Ruiqi, Iordanou, Konstantinos, Riley, Graham, Luján, Mikel

Publikováno v: Ye, R, Iordanou, K, Riley, G & Luján, M 2023, ' Exploring Sparse Visual Odometry Acceleration with High-Level Synthesis ', IEEE Access . https://doi.org/10.1109/ACCESS.2023.3268992

Visual Odometry (VO) systems are widely used to determine the position and orientation of a robot or camera in an unknown environment. They are deployed on resource-constrained platforms, such as drones and Virtual Reality, or Augmented Reality, head

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=od______3818::b8cba9b38815ecb3bcdf9359984780ec
https://doi.org/10.1109/ACCESS.2023.3268992

A performance evaluation of multi-FPGA architectures for computations of information transfer

Autor: Iordanou Konstantinos, Nikolakaki Sofia-Maria, Malakonakis Pavlos, Dollas Apostolos

Summarization: Mutual Information (MI) and Transfer Entropy (TE) algorithms compute statistical measurements on the information shared between two dependent random processes. These measurements have focused on pairwise computations of time series in

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=od______4037::e5d002711d5cdacbb4795429ce14f78f
http://purl.tuc.gr/dl/dias/40BA5708-F048-4D3F-9D4B-1E86417AAB1D