Zobrazeno 1 - 10
of 341
pro vyhledávání: '"O'Reilly Randall C"'
Publikováno v:
CogSci 2022, 44
Neural networks struggle in continual learning settings from catastrophic forgetting: when trials are blocked, new learning can overwrite the learning from previous blocks. Humans learn effectively in these settings, in some cases even showing an adv
Externí odkaz:
http://arxiv.org/abs/2202.04773
The Bayesian brain hypothesis postulates that the brain accurately operates on statistical distributions according to Bayes' theorem. The random failure of presynaptic vesicles to release neurotransmitters may allow the brain to sample from posterior
Externí odkaz:
http://arxiv.org/abs/2111.09780
Autor:
Rohrlich, John, O'Reilly, Randall C.
Infants, adults, non-human primates and non-primates all learn patterns implicitly, and they do so across modalities. The biological evidence supports the hypothesis that the mechanism for this learning is general but computationally local. We hypoth
Externí odkaz:
http://arxiv.org/abs/2108.06065
A hallmark of human intelligence is the ability to adapt to new situations, by applying learned rules to new content (systematicity) and thereby enabling an open-ended number of inferences and actions (generativity). Here, we propose that the human b
Externí odkaz:
http://arxiv.org/abs/2108.03387
The neural mechanisms supporting flexible relational inferences, especially in novel situations, are a major focus of current research. In the complementary learning systems framework, pattern separation in the hippocampus allows rapid learning in no
Externí odkaz:
http://arxiv.org/abs/2105.08944
Autor:
Webb, Taylor W., Dulberg, Zachary, Frankland, Steven M., Petrov, Alexander A., O'Reilly, Randall C., Cohen, Jonathan D.
Extrapolation -- the ability to make inferences that go beyond the scope of one's experiences -- is a hallmark of human intelligence. By contrast, the generalization exhibited by contemporary neural network algorithms is largely limited to interpolat
Externí odkaz:
http://arxiv.org/abs/2007.05059
How do humans learn from raw sensory experience? Throughout life, but most obviously in infancy, we learn without explicit instruction. We propose a detailed biological mechanism for the widely-embraced idea that learning is based on the differences
Externí odkaz:
http://arxiv.org/abs/2006.14800
Publikováno v:
Behavioral and Brain Functions, Vol 4, Iss 1, p 5 (2008)
Abstract The transitive inference (TI) task assesses the ability to generalize learned knowledge to new contexts, and is thought to depend on the hippocampus (Dusek & Eichenbaum, 1997). Animals or humans learn in separate trials to choose stimulus A
Externí odkaz:
https://doaj.org/article/decf66698dad4245874fd7c3deed319b
Standard methods in deep learning for natural language processing fail to capture the compositional structure of human language that allows for systematic generalization outside of the training distribution. However, human learners readily generalize
Externí odkaz:
http://arxiv.org/abs/1904.09708
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.