短期的Hebbian学习可以实现类似变压器的注意力
1Department of Neurobiology and Behavior, Cornell University, Ithaca, NY, United States of America.
PLoS computational biology
|January 26, 2024
概括
神经元可以使用一种新的匹配和控制原理来执行类似注意力的计算. 这种机制利用了短期的Hebbian突触强化,在神经回路中进行高效的关键查询比较.
科学领域:
- 计算神经科学是一种神经科学.
- 机器学习 机器学习
- 人工智能的人工智能
背景情况:
- 变压器在语言和视觉方面显著提升了机器学习.
- 变压器注意力机制的神经生物学基础在很大程度上仍未被探索.
- 传统的神经回路在实施注意层所需的质量比较方面面临挑战.
研究的目的:
- 提出一种神经生物学上可信的机制,用于神经元中类似注意力的计算.
- 为了弥合变压器模型和神经科学之间的差距.
- 为了引入神经注意力的匹配和控制原则.
主要方法:
- 模拟神经元实施注意力类计算.
- 利用短期的赫比亚语突触强化作为核心机制.
- 将键和查询表示为尖列车,以便在单个树突中进行比较.
主要成果:
- 证明神经元可以通过匹配和控制原理执行类似注意力的计算.
- 展示了同步活动 (匹配) 如何导致短暂的突触强化 (控制).
- 表明单个棘可以高效地执行许多关键查询比较.
结论:
- 匹配和控制原理为理解神经计算提供了一个新的框架.
- 这种机制为神经网络中的注意提供了潜在的生物基础.
- 这些发现表明,人工智能与神经科学之间存在更直接的联系.
相关概念视频
Long-term Potentiation
2.8K
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.
Hebbian LTP
LTP can occur when...
Hebbian LTP
LTP can occur when...
2.8K
Higher Mental Functions of Brain: Learning and Memory
809
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...
809
Chunking and Rehearsal in Sensory Memory
213
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...
213
Cognitive Learning
243
Cognitive learning is based on purposive behavior, incidental learning, and insight learning.
E. C. Tolman's theory of purposive behavior emphasizes that much behavior is goal-directed. He argued that to understand behavior, we must look at the entire sequence of actions leading to a goal. For instance, high school students study hard, not just due to past reinforcement but also to achieve the goal of getting into a good college.
Tolman introduced the idea that behavior is influenced by...
E. C. Tolman's theory of purposive behavior emphasizes that much behavior is goal-directed. He argued that to understand behavior, we must look at the entire sequence of actions leading to a goal. For instance, high school students study hard, not just due to past reinforcement but also to achieve the goal of getting into a good college.
Tolman introduced the idea that behavior is influenced by...
243
Long-term Depression
30.9K
Long-term depression, or LTD, is one of the ways by which synaptic plasticity—changes in the strength of chemical synapses—can occur in the brain. LTD is the process of synaptic weakening that occurs over time between pre and postsynaptic neuronal connections. The synaptic weakening of LTD works in opposition to synaptic strengthening by long-term potentiation (LTP) and together are the main mechanisms that underlie learning and memory.
30.9K
Transformers
1.1K
A device that transforms voltages from one value to another using induction is called a transformer. A transformer consists of two separate coils, or windings, wrapped around the same soft iron core. However, they are electrically insulated from each other.
The iron core has a substantial relative permeability. Therefore, the magnetic field lines generated due to the current in one winding are almost entirely confined within the core, such that the same magnetic flux permeates each turn of both...
The iron core has a substantial relative permeability. Therefore, the magnetic field lines generated due to the current in one winding are almost entirely confined within the core, such that the same magnetic flux permeates each turn of both...
1.1K


