提高利用神经发生的稀疏关联记忆的回忆
Katy Warr1, Jonathon Hare2, David Thomas3
1Electronics and Computer Science, University of Southampton, Southampton SO17 1BJ, U.K. k.s.warr@soton.ac.uk.
Neural computation
|January 9, 2025
概括
这项研究引入了由神经生成启发的优化稀疏联想记忆 (SAM) 网络,用于神经形态计算. 这些网络显著提高了低功耗人工智能应用程序的内存容量和噪声强度.
科学领域:
- 神经形态工程的神经形态工程
- 计算神经科学是一种神经科学.
- 人工智能的人工智能
背景情况:
- 开发低功耗的神经形态系统需要专门的算法,如尖端神经网络 (SNN).
- 从噪音数据中回忆学习的模式是SNN的一个关键挑战.
- 受神经编码启发的稀疏联想记忆 (SAM) 模型和神经发生学启发的终身学习提供了潜在的解决方案,但面临着容量和噪声弹性方面的局限性.
研究的目的:
- 提出一个统一的框架来表征SAM网络预先训练与神经生成启发的学习策略.
- 为了提高性能,正式定义网络拓和值优化方法.
- 为了提高神经形态联想记忆中的记忆能力和噪声强度.
主要方法:
- 开发了一个统一的框架来描述SAM网络.
- 定义网络拓和值优化技术.
- 采用了一种学习策略,用于预训练,该策略包含神经发生模型.
主要成果:
- 与以前的方法相比,实现了超过10^4倍的内存容量改善.
- 证明内部神经元连接性降低,同时保持高回忆效率.
- 验证了提议的优化方法的有效性.
结论:
- 拟议的框架和优化方法在神经形态应用中显著提升了SAM网络.
- 这些进步为神经形态平台上的更高效,更强大的低功耗关联记忆铺平了道路.
- 这项研究有助于在人工系统中开发有效的终身学习能力.
相关概念视频
Higher Mental Functions of Brain: Learning and Memory
658
Memory is one of the most vital higher mental functions of the brain. Memory is closely related to learning because it enables us to retain information and experiences from our past to use them in our present life. It also helps us to remember facts, events, and skills, such as riding a bike or swimming. There are two types of memory — declarative memory, which involves memorizing facts or events, and procedural memory, which enables us to remember how to do something like writing or...
658
Chunking and Rehearsal in Sensory Memory
151
Improving short-term memory can be achieved through techniques like chunking and rehearsal. Chunking involves organizing information into larger, more manageable units. This technique is particularly useful for information that exceeds the typical memory span of between five and nine items. For instance, logging into an online account with a password like "ta89vq0179gz" involves grouping letters and numbers into three chunks—ta89, vq01, and 79gz. It makes large amounts of...
151
Neuroplasticity
284
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.
284
Storage
69
A schema is a mental framework that helps individuals organize and interpret information. Schemata, formed from previous experiences, influence how we process new information: how we encode it, the inferences we make, and how we retrieve it. For instance, a schema for what a typical classroom looks like might include desks, a teacher's desk, a whiteboard, and students in such an environment. This expectation helps us quickly understand and navigate new classrooms without needing to analyze...
69
Neurogenesis and Regeneration of Nervous Tissue
706
In the CNS, neurogenesis, the birth of new neurons from stem cells, is limited to the hippocampus in adults. In other regions of the brain and spinal cord, neurogenesis is almost non-existent due to inhibitory influences from neuroglia, especially oligodendrocytes, and the absence of growth-stimulating cues. The myelin produced by oligodendrocytes in the CNS inhibits neuronal regeneration. Furthermore, astrocytes proliferate rapidly after neuronal damage, forming scar tissue that physically...
706
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


