能够实现元可塑性的石墨烯量子点设备,用于缓解人工神经网络中的灾难性遗忘
Xuemeng Fan1,2, Anzhe Chen1,2, Zongwen Li1,2
1School of Integrated Circuits, Zhejiang University, Hangzhou, Zhejiang, 311200, China.
Advanced materials (Deerfield Beach, Fla.)
|December 9, 2024
概括
石墨烯量子点能够实现具有元可塑性的人工突触,增强深度神经网络在不遗忘的情况下不断学习的能力. 这一突破模仿了生物学习,使人工智能系统更强大.
科学领域:
- 神经形态工程的神经形态工程
- 材料科学 材料科学 材料科学
- 人工智能的人工智能
背景情况:
- 由于生物神经回路的简化模型,深度神经网络难以持续学习.
- 灾难性遗忘限制了人工智能在学习时保留新信息的能力.
研究的目的:
- 引入具有表现出元可塑性的石墨烯量子点 (GQD) 的人工突触装置.
- 为了展示一种硬件解决方案,以克服深度神经网络中的灾难性遗忘.
主要方法:
- 开发了使用石墨烯量子点 (GQD) 实现超塑性的人工突触装置.
- 为了突触可塑性,利用了不对称的导电通路中的接口介导修改.
- 在深度神经网络中实现了超塑性原理,以提高概括性.
主要成果:
- 经GQD增强的设备表现出超塑性,调节记忆稳定性和学习可塑性.
- 在一个顺序任务 (第四个MNIST数据集) 中获得了97%的准确性,同时在之前的任务中保持了94%以上的准确性.
- 成功地解决了深度神经网络中的灾难性遗忘问题.
结论:
- 超塑性对于深层神经网络的概括至关重要,使流体能够适应新数据.
- 基于GQD的人工突触装置为神经形态系统提供了可行的硬件方法.
- 这项研究弥合了人造神经网络和生物神经网络学习能力之间的差距.
相关概念视频
Long-term Potentiation
54.8K
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.
54.8K
Neuroplasticity
295
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.
295
Forgetting
55
Forgetting is an intrinsic aspect of human memory, characterized by the gradual loss or inaccessibility of information over time. Hermann Ebbinghaus, a pioneering psychologist, extensively studied this phenomenon and formulated the forgetting curve. This curve illustrates that memory loss occurs rapidly immediately after learning and then decelerates over time. Several mechanisms contribute to forgetting, including encoding failure, storage decay, retrieval failure, and interference.
Encoding...
Encoding...
55


