2022-11-18 カリフォルニア大学サンディエゴ校(UCSD)
このスパイキング・ニューラル・ネットワークを新しいタスクで訓練する際、睡眠を模倣したオフラインの時間を時々設けると、壊滅的な忘却が緩和されることが判明したのである。研究チームは、人間の脳と同様に、ネットワークが「睡眠」をとることで、古い学習データを明示的に使用せずに、古い記憶を再生することが可能になると述べている。
シナプスの可塑性、つまり変化や成形される能力は、睡眠中もあり、記憶を表すシナプスの重量パターンをさらに強化し、忘却の防止や古いタスクから新しいタスクへの知識の伝達を可能にするのに役立つ。
研究者達が、このアプローチを人工ニューラルネットワークに適用したところ、ネットワークが壊滅的な忘却を回避するのに役立つことがわかった。
つまり、このネットワークは、人間や動物のように、継続的に学習することができる。
<関連情報>
- https://today.ucsd.edu/story/artificial-neural-networks-learn-better-when-they-spend-time-not-learning-at-all
- https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1010628
睡眠はシナプス結合重み表現の形成により、スパイク神経回路網における破局的忘却を防止する Sleep prevents catastrophic forgetting in spiking neural networks by forming a joint synaptic weight representation
Ryan Golden ,Jean Erik Delanois ,Pavel Sanda,Maxim Bazhenov
PLOS Computational Biology Published: November 18, 2022
DOI:https://doi.org/10.1371/journal.pcbi.1010628
Abstract
Artificial neural networks overwrite previously learned tasks when trained sequentially, a phenomenon known as catastrophic forgetting. In contrast, the brain learns continuously, and typically learns best when new training is interleaved with periods of sleep for memory consolidation. Here we used spiking network to study mechanisms behind catastrophic forgetting and the role of sleep in preventing it. The network could be trained to learn a complex foraging task but exhibited catastrophic forgetting when trained sequentially on different tasks. In synaptic weight space, new task training moved the synaptic weight configuration away from the manifold representing old task leading to forgetting. Interleaving new task training with periods of off-line reactivation, mimicking biological sleep, mitigated catastrophic forgetting by constraining the network synaptic weight state to the previously learned manifold, while allowing the weight configuration to converge towards the intersection of the manifolds representing old and new tasks. The study reveals a possible strategy of synaptic weights dynamics the brain applies during sleep to prevent forgetting and optimize learning.
Author summary
Artificial neural networks can achieve superhuman performance in many domains. Despite these advances, these networks fail in sequential learning; they achieve optimal performance on newer tasks at the expense of performance on previously learned tasks. Humans and animals on the other hand have a remarkable ability to learn continuously and incorporate new data into their corpus of existing knowledge. Sleep has been hypothesized to play an important role in memory and learning by enabling spontaneous reactivation of previously learned memory patterns. Here we use a spiking neural network model, simulating sensory processing and reinforcement learning in animal brain, to demonstrate that interleaving new task training with sleep-like activity optimizes the network’s memory representation in synaptic weight space to prevent forgetting old memories. Sleep makes this possible by replaying old memory traces without the explicit usage of the old task data.
