Topic: online learning

With recent advances in learning algorithms, recurrent networks of spiking neurons are achieving performance competitive with standard recurrent neural networks. Still, these learning algorithms are limited to small networks of simple spiking neurons and modest-length temporal sequences, as they impose high memory requirements, have difficulty training complex neuron models, and are incompatible with online learning.Taking inspiration from the concept of Liquid Time-Constant (LTCs), we introduce a novel class of spiking neurons, the Liquid Time-Constant Spiking Neuron (LTC-SN), resulting in fu

The success of Artificial Neural Networks (ANNs) trained with error-backpropagation algorithms relies on the combination of offline training, vast amounts of data, and energy-intensive simulations on dedicated hardware accelerators. In contrast, biological neurons can learn quickly in a self-supervised manner by utilizing (a) recurrent connections within their local network and from other areas, (b) segregated dendrites receiving inputs from feedforward and feedback pathways, and (c) learning rules that combine locally available information from pre- and -post-synaptic sources. Inspired by loc

Working memory is inherently limited in capacity and duration, which may hamper learning, including in online learning environments. Because working memory capacity varies among individuals, cognitive load in online learning may not have the same impact for neurotypical and neurodivergent students. This study investigated the relationship between neurodivergent traits and cognitive load during online learning. Seventy participants, including 35 neurotypical students and 35 neurodivergent students with a diagnosis of attention deficit hyperactivity disorder (ADHD), autism spectrum disorder (ASD