no code implementations • 1 Dec 2023 • Laura Smets, Werner van Leekwijck, Ing Jyh Tsang, Steven Latré
A key aspect that determines the performance of HDC is the encoding of the input data to the hyperdimensional (HD) space.
1 code implementation • 29 Nov 2023 • Thomas Dooms, Ing Jyh Tsang, Jose Oramas
Local learning, which focuses on updating subsets of a model's parameters at a time, has emerged as a promising technique to address these issues.
no code implementations • 12 Sep 2023 • Lucas Deckers, Laurens Van Damme, Ing Jyh Tsang, Werner van Leekwijck, Steven Latré
Spiking neural networks (SNN) distinguish themselves from artificial neural networks (ANN) because of their inherent temporal processing and spike-based computations, enabling a power-efficient implementation in neuromorphic hardware.
no code implementations • 30 May 2023 • Laura Smets, Werner van Leekwijck, Ing Jyh Tsang, Steven Latre
Hyperdimensional computing (HDC) has become popular for light-weight and energy-efficient machine learning, suitable for wearable Internet-of-Things (IoT) devices and near-sensor or on-device processing.