TopicNeuro

generalisation

3 ePosters1 Seminar

Latest

SeminarNeuroscienceRecording

Cross Domain Generalisation in Humans and Machines

Leonidas Alex Doumas
The University of Edinburgh
Feb 4, 2021

Recent advances in deep learning have produced models that far outstrip human performance in a number of domains. However, where machine learning approaches still fall far short of human-level performance is in the capacity to transfer knowledge across domains. While a human learner will happily apply knowledge acquired in one domain (e.g., mathematics) to a different domain (e.g., cooking; a vinaigrette is really just a ratio between edible fat and acid), machine learning models still struggle profoundly at such tasks. I will present a case that human intelligence might be (at least partially) usefully characterised by our ability to transfer knowledge widely, and a framework that we have developed for learning representations that support such transfer. The model is compared to current machine learning approaches.

ePosterNeuroscience

Hippocampal networks support continual learning and generalisation

Samia Mohinta,Dabal Pedamonti,Martin Dimitrov,Hugo Malagon-Vina,Stephane Ciocchi,Rui Ponte Costa

COSYNE 2022

ePosterNeuroscience

Hippocampal networks support continual learning and generalisation

Samia Mohinta,Dabal Pedamonti,Martin Dimitrov,Hugo Malagon-Vina,Stephane Ciocchi,Rui Ponte Costa

COSYNE 2022

ePosterNeuroscience

Computation with neuronal cultures: Effects of connectivity modularity on response separation and generalisation in simulations and experiments

Akke Mats Houben, Anna-Christina Haeb, Jordi Garcia-Ojalvo, Jordi Soriano

FENS Forum 2024

generalisation coverage

4 items

ePoster3
Seminar1
Domain spotlight

Explore how generalisation research is advancing inside Neuro.

Visit domain