Continual lifelong learning with neural networks: A review

Neural Networks, Journal Year: 2019, Volume and Issue: 113, P. 54 - 71

Published: Feb. 10, 2019

Humans and animals have the ability to continually acquire, fine-tune, transfer knowledge skills throughout their lifespan. This ability, referred as lifelong learning, is mediated by a rich set of neurocognitive mechanisms that together contribute development specialization our sensorimotor well long-term memory consolidation retrieval. Consequently, learning capabilities are crucial for computational systems autonomous agents interacting in real world processing continuous streams information. However, remains long-standing challenge machine neural network models since continual acquisition incrementally available information from non-stationary data distributions generally leads catastrophic forgetting or interference. limitation represents major drawback state-of-the-art deep typically learn representations stationary batches training data, thus without accounting situations which becomes over time. In this review, we critically summarize main challenges linked artificial compare existing approaches alleviate, different extents, forgetting. Although significant advances been made domain-specific with networks, extensive research efforts required robust on robots. We discuss well-established emerging motivated factors biological such structural plasticity, replay, curriculum intrinsic motivation, multisensory integration.

Language: Английский

---

Memory engrams: Recalling the past and imagining the future

Science, Journal Year: 2020, Volume and Issue: 367(6473)

Published: Jan. 3, 2020

In 1904, Richard Semon introduced the term "engram" to describe neural substrate for storing memories. An experience, proposed, activates a subset of cells that undergo off-line, persistent chemical and/or physical changes become an engram. Subsequent reactivation this engram induces memory retrieval. Although Semon's contributions were largely ignored in his lifetime, new technologies allow researchers image and manipulate brain at level individual neurons has reinvigorated research. We review recent progress studying engrams, including evaluation evidence existence importance intrinsic excitability synaptic plasticity lifetime Together, these findings are beginning define as basic unit memory.

Language: Английский

---

Prefrontal–hippocampal interactions in episodic memory

Nature reviews. Neuroscience, Journal Year: 2017, Volume and Issue: 18(9), P. 547 - 558

Published: June 28, 2017

Language: Английский

---

Neurobiology of Schemas and Schema-Mediated Memory

Trends in Cognitive Sciences, Journal Year: 2017, Volume and Issue: 21(8), P. 618 - 631

Published: May 24, 2017

Language: Английский

---

Activity-Regulated Transcription: Bridging the Gap between Neural Activity and Behavior

Neuron, Journal Year: 2018, Volume and Issue: 100(2), P. 330 - 348

Published: Oct. 1, 2018

Language: Английский

---

Microglial Remodeling of the Extracellular Matrix Promotes Synapse Plasticity

Cell, Journal Year: 2020, Volume and Issue: 182(2), P. 388 - 403.e15

Published: July 1, 2020

Language: Английский

---

Temporal evolution of cortical ensembles promoting remote memory retrieval

Nature Neuroscience, Journal Year: 2019, Volume and Issue: 22(3), P. 460 - 469

Published: Jan. 12, 2019

Language: Английский

---

Old Brains Come Uncoupled in Sleep: Slow Wave-Spindle Synchrony, Brain Atrophy, and Forgetting

Neuron, Journal Year: 2017, Volume and Issue: 97(1), P. 221 - 230.e4

Published: Dec. 14, 2017

Language: Английский

---

The role of engram cells in the systems consolidation of memory

Nature reviews. Neuroscience, Journal Year: 2018, Volume and Issue: 19(8), P. 485 - 498

Published: July 3, 2018

Language: Английский

---

Parallel emergence of stable and dynamic memory engrams in the hippocampus

Nature, Journal Year: 2018, Volume and Issue: 558(7709), P. 292 - 296

Published: June 1, 2018

Language: Английский

---