Why there are complementary learning systems in the hippocampus and neocortex: insights from the successes and failures of connectionist models of learning and memory.

By James L. McClelland, Bruce L. McNaughton, Randall C. O’Reilly. 1995

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Neuroscience

Citations in the corpus

Continual Lifelong Learning with Neural Networks: A Review (2018, background): “(b) The complementary learning systems (CLS) theory (McClelland et al., 1995) comprising the hippocampus for the fast learning of episodic information and the neocortex for the slow learning of structured knowledge.”
A Comprehensive Survey of Continual Learning: Theory, Method and Application (2023, background): “A major challenge is known as catastrophic forgetting [6], [7], where adaptation to a new distribution generally results in a largely reduced ability to capture the old ones.”
Lifelong Learning of Spatiotemporal Representations With Dual-Memory Recurrent Self-Organization (2018, background): “Hippocampal replay provides the means for the gradual integration of knowledge into neocortical structures through the reactivation of recently acquired knowledge interleaved with the exposure to ongoing episodic experience (McClelland et al., 1995).”
FearNet: Brain-Inspired Model for Incremental Learning (2017, background): “FearNet is heavily inspired by the dual-memory model of mammalian memory (McClelland et al., 1995), which has considerable experimental support from neuroscience (Frankland et al., 2004; Takashima et al., 2006; Kitamura et al., 2017; Bontempi et al., 1999; Taupin & Gage, 2002; Gais et al., 2007).”
Gradient Episodic Memory for Continual Learning (2017, background): “In contrast, we focus on the problem of catastrophic forgetting [McCloskey and Cohen, 1989, French, 1999, Ratcliff, 1990, McClelland et al., 1995, Goodfellow et al., 2013].”
Born to Learn: the Inspiration, Progress, and Future of Evolved Plastic Artificial Neural Networks (2017, background): “Inspiration for new approaches could come from complementary learning systems (McClelland et al., 1995; Kumaran et al., 2016) that humans seem to possess, which include fast and slow learning components.”
Structural Synaptic Plasticity Has High Memory Capacity and Can Explain Graded Amnesia, Catastrophic Forgetting, and the Spacing Effect (2014, neutral): “hippocampal memory replay and consolidation [34,35], prevent-”
Generalization Through the Recurrent Interaction of Episodic Memories (2012, methodology): “…to CLS theory, is that this apparently serious shortcoming of the scope of hippocampal processing may be relatively inconsequential, given a neocortical learning system capable of efficiently discovering the general properties, or structure, of our overall experience (McClelland et al., 1995).”
Online Contrastive Divergence with Generative Replay: Experience Replay without Storing Data (2016, methodology): “Experience replay was ﬁrst introduced for RL in Lin (1992) and for supervised learning in McClelland et al (1995).”
Synaptic weight decay with selective consolidation enables fast learning without catastrophic forgetting (2019, background): “In systems consolidation, memories are suggested to be transferred to other brain areas for long-term storage such as the hippocampus (Squire and Alvarez, 1995; McClelland et al., 1995; Roxin and Fusi, 2013).”
Memory Efficient Experience Replay for Streaming Learning (2018, methodology): “ catastrophic forgetting of previously learned information [58]. Rehearsal is one of the earliest methods for preventing this phenomenon [50]. Rehearsal, also known as replay and interleaved learning [57], limits catastrophic forgetting by mixing past experience with new data [50]. Originally, it wa”
Selective Experience Replay for Lifelong Learning (2018, background): “This separation relates to work on complementary learning systems (McClelland, McNaughton, and O’Reilly 1995).”
Incorporating neuro-inspired adaptability for continual learning in artificial intelligence (2023, background): “1, b), although current efforts mainly focus on the former to prevent catastrophic forgetting [4, 5].”
SLCA: Slow Learner with Classifier Alignment for Continual Learning on a Pre-trained Model (2023, background): “Current efforts are mainly based on the premise of learning from scratch, attempting to mitigate catastrophic forgetting [27] of previously-learned knowledge when adapting to each incremental task.”