What learning systems do intelligent agents need? Complementary learning systems theory updated
D Kumaran, D Hassabis, JL McClelland�- Trends in cognitive sciences, 2016 - cell.com
We update complementary learning systems (CLS) theory, which holds that intelligent
agents must possess two learning systems, instantiated in mammalians in neocortex and�…
agents must possess two learning systems, instantiated in mammalians in neocortex and�…
[HTML][HTML] Organizing memories for generalization in complementary learning systems
Memorization and generalization are complementary cognitive processes that jointly
promote adaptive behavior. For example, animals should memorize safe routes to specific�…
promote adaptive behavior. For example, animals should memorize safe routes to specific�…
Integration of new information in memory: new insights from a complementary learning systems perspective
JL McClelland, BL McNaughton…�- …�Transactions of the�…, 2020 - royalsocietypublishing.org
According to complementary learning systems theory, integrating new memories into the
neocortex of the brain without interfering with what is already known depends on a gradual�…
neocortex of the brain without interfering with what is already known depends on a gradual�…
Complementary learning systems
This paper reviews the fate of the central ideas behind the complementary learning systems
(CLS) framework as originally articulated in McClelland, McNaughton, and O'Reilly (1995)�…
(CLS) framework as originally articulated in McClelland, McNaughton, and O'Reilly (1995)�…
Hippocampal and neocortical contributions to memory: Advances in the complementary learning systems framework
RC O'Reilly, KA Norman�- Trends in cognitive sciences, 2002 - cell.com
The complementary learning systems framework provides a simple set of principles, derived
from converging biological, psychological and computational constraints, for understanding�…
from converging biological, psychological and computational constraints, for understanding�…
Incorporating rapid neocortical learning of new schema-consistent information into complementary learning systems theory.
JL McClelland�- Journal of Experimental Psychology: General, 2013 - psycnet.apa.org
The complementary learning systems theory of the roles of hippocampus and neocortex
(McClelland, McNaughton, & O'Reilly, 1995) holds that the rapid integration of arbitrary new�…
(McClelland, McNaughton, & O'Reilly, 1995) holds that the rapid integration of arbitrary new�…
Methods for reducing interference in the complementary learning systems model: oscillating inhibition and autonomous memory rehearsal
The stability–plasticity problem (ie how the brain incorporates new information into its model
of the world, while at the same time preserving existing knowledge) has been at the forefront�…
of the world, while at the same time preserving existing knowledge) has been at the forefront�…
Complementary learning systems within the hippocampus: a neural network modelling approach to reconciling episodic memory with statistical learning
AC Schapiro, NB Turk-Browne…�- …�of the Royal�…, 2017 - royalsocietypublishing.org
A growing literature suggests that the hippocampus is critical for the rapid extraction of
regularities from the environment. Although this fits with the known role of the hippocampus�…
regularities from the environment. Although this fits with the known role of the hippocampus�…
The neuroscience of learning: beyond the Hebbian synapse
CR Gallistel, LD Matzel�- Annual review of psychology, 2013 - annualreviews.org
From the traditional perspective of associative learning theory, the hypothesis linking
modifications of synaptic transmission to learning and memory is plausible. It is less so from�…
modifications of synaptic transmission to learning and memory is plausible. It is less so from�…
[HTML][HTML] Biologically plausible learning in recurrent neural networks reproduces neural dynamics observed during cognitive tasks
T Miconi�- Elife, 2017 - elifesciences.org
Neural activity during cognitive tasks exhibits complex dynamics that flexibly encode task-
relevant variables. Chaotic recurrent networks, which spontaneously generate rich�…
relevant variables. Chaotic recurrent networks, which spontaneously generate rich�…