对比的信号依赖可塑性:自主监督学习在尖端的神经回路
1Department of Computer Science, Rochester Institute of Technology, 1 Lomb Memorial Dr, Rochester, NY 14623, USA.
Science advances
|October 23, 2024
概括
研究人员开发了一种新方法来训练神经网络,灵感来自大脑. 这种对比的信号依赖可塑性方法提高了人工智能模型的适应性和能源效率.
科学领域:
- 神经科学和人工智能 人工智能
- 计算神经科学是一种神经科学.
- 机器学习 机器学习
背景情况:
- 现代深度神经网络往往缺乏生物可信性和能源效率.
- 尖端神经网络 (SNN) 通过模仿生物神经元提供了一个有希望的替代方案.
- 为SNN制定有效的学习规则仍然是一个重大挑战.
研究的目的:
- 为SNN提出一种新的神经生物学动机的突触可塑性规则.
- 增强基于事件的神经元架构的适应性和学习能力.
- 提高人工智能模型的能源效率.
主要方法:
- 引入了对比的信号依赖可塑性 (CSDP),一种自我监督的学习启发机制.
- 应用CSDP以促进当地适应并行,基于事件的神经元层.
- 使用建议的CSDP方法训练经常性增量网络.
主要成果:
- 在现有的生物学上可信的学习规则上,CSDP表现出了一致的优势.
- 这种方法有效地训练反复的尖端网络.
- CSDP 避免了需要额外的复杂结构,如反突触.
结论:
- 对比的信号依赖可塑性是训练SNN的一种可行和有效的方法.
- 这种方法通过提高适应性和效率来推进由大脑启发的机器智能.
- CSDP为开发先进的神经网络架构提供了一个更简单,更强大的替代方案.
相关概念视频
Neural Circuits
1.1K
Neural circuits and neuronal pools are two of the main structures found in the nervous system. Neural circuits are networks of neurons that work together to carry out a specific task or process. They consist of interconnected neurons and glial cells, which provide structural and metabolic support.
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
1.1K
Long-term Potentiation
2.7K
Long-term potentiation, or LTP, is one of the ways by which synaptic plasticity—changes in the strength of chemical synapses—can occur in the brain. LTP is the process of synaptic strengthening that occurs over time between pre and postsynaptic neuronal connections. The synaptic strengthening of LTP works in opposition to the synaptic weakening of long-term depression (LTD) and together are the main mechanisms that underlie learning and memory.
Hebbian LTP
LTP can occur when...
Hebbian LTP
LTP can occur when...
2.7K
Neuroplasticity
303
Neuroplasticity reflects the brain's remarkable capacity to adapt and evolve, responding dynamically to learning, experiences, or injury by reorganizing its neural circuitry. This reorganization involves creating new neural connections and refining old ones through a series of biological processes that contribute to the brain's lifelong development and adaptability.
303


