A single fast Hebbian-like process enabling one-shot class addition in deep neural networks without backbone modification.

ABSTRACT: One-shot learning, the ability to learn a new concept from a single instance, is a distinctive brain function that has garnered substantial interest in machine learning. While modeling physiological mechanisms poses challenges, advancements in artificial neural networks have led to performances in specific tasks that rival human capabilities. Proposing one-shot learning methods with these advancements, especially those involving simple mechanisms, not only enhance technological development but also contribute to neuroscience by proposing functionally valid hypotheses. Among the simplest methods for one-shot class addition with deep learning image classifiers is "weight imprinting," which uses neural activity from a new class image data as the corresponding new synaptic weights. Despite its

SUBMITTER: Hosoda K 

PROVIDER: S-EPMC11202076 | biostudies-literature | 2024

REPOSITORIES: biostudies-literature