Opinion TRENDS in Cognitive Sciences Vol.6 No.12 December 2002

Subfields: Cognitive Science & Psychology

Citations in the corpus

• Continual Lifelong Learning with Neural Networks: A Review (2018, background): “To address this issue, task-relevant modulatory signals were modelled by Parisi et al. (2018)which regulate the process of neurogenesis and neural update (see Section 3.”
• Continual Learning with Deep Generative Replay (2017, background): “While several biological mechanisms contribute to this at multiple levels, the most apparent distinction between primate brains and artificial neural networks is the existence of separate, interacting memory systems [26].”
• Lifelong Learning of Spatiotemporal Representations With Dual-Memory Recurrent Self-Organization (2018, background): “However, there is no empirical evidence showing that this or similar contemporaneous approaches (see O’Reilly and Norman, 2002 for a review) scale up to large-scale image and video benchmark datasets.”
• Continual Learning by Modeling Intra-Class Variation (2022, methodology): “Interestingly, memory-based methods also serve as an effective model of complementary learning systems (McClelland et al., 1995; O’Reilly et al., 2014; O’Reilly & Norman, 2002) where episodic memories are retained by regular experience replay. ar X iv :2 21 0.”
• Sleep-Associated Changes in the Mental Representation of Spoken Words (2007, background): “Given that improvement in recall tasks is linked to specific configurations of non-REM/ REM sleep cycles (Gais, Mölle, Helms, & Born, 2002; Plihal & Born, 1997), the correlation between the postsleep competition effect and the overnight improvement in recall strongly supports this possibility.”
• Impaired spatial and non-spatial configural learning in patients with hippocampal pathology (2007, unknown): “Our results, therefore, would appear to run counter to recent formulations of the conjunctive theory (Moses & Ryan, 2006; O'Reilly & Norman, 2002; O'Reilly & Rudy, 2001), which regards the neocortex as a slower, but nevertheless powerful, learner of configural associations mediated by neocortical…”
• On the biological plausibility of grandmother cells: implications for neural network theories in psychology and neuroscience. (2009, background): “The significance of this distinction was recognized by Perrett et al. (1985). They recorded from cells in the temporal lobe of macaque monkey (superior temporal sulcus) and identified some cells that responded to one person more than others.”
• Self-Supervised Learning Aided Class-Incremental Lifelong Learning (2020, background): “[41] proposed a model of deep generative replay (DGR) in the generative adversarial networks (GANs) framework[10] and the complementary learning systems (CLS) theory [20, 34] can also be modelled [18].”
• Banishing the homunculus: making working memory work. (2006, unknown): “…over numerous publications (O'Reilly & McClelland, 1994; McClelland, McNaughton, & O'Reilly, 1995; O'Reilly & Rudy, 2001; Norman & O'Reilly, 2003; O'Reilly & Norman, 2002), and also includes many themes going back to earlier work (e.g., Marr, 1971; McNaughton & Morris, 1987; Rolls, 1989) that…”
• Learning and Consolidation of Novel Spoken Words (2009, background): “…of new words: (1) initial learning is supported by medial-temporal systems that rapidly adapt as novel words become familiar; and (2) long-term cortical representations of new words are altered by slow, off-line consolidation (cf. O’Reilly & Norman, 2002; McClelland, McNaughton, & O’Reilly, 1995).”