相关实验视频
Updated: May 5, 2026

An Operant Intra-/Extra-dimensional Set-shift Task for Mice
Published on: January 22, 2016
在上下文依赖的集成-切换中学习和储存的反复动态的几何和效率
1A. V. Gaponov-Grekhov Institute of Applied Physics of the Russian Academy of Sciences, Nizhny Novgorod 603950, Russia.
可训练的循环神经网络 (RNN) 通过学习有效地组织其内部动态来优于固定储备模型. 这使得它们能够以更少的参数实现更高的准确性,与效率较低的固定网络不同.
科学领域:
- 计算神经科学是一种计算神经科学.
- 机器学习是机器学习.
- 动态系统是动态系统.
背景情况:
- 循环神经网络 (RNN) 对于连续的数据处理至关重要.
- 存在两个主要的RNN范式:固定储备库计算和端到端可训练的RNN.
- 了解它们在状态空间动态中编码的计算策略是关键.
研究的目的:
- 调查固定水库和可训练的RNN之间的根本差异.
- 为了比较一个正规的上下文依赖的整合任务的性能.
- 为了揭示RNN效率背后的机制.
主要方法:
- 系统地比较回声状态网络,封闭循环单元,长期短期记忆网络和线性模型.
- 使用动态系统和多元理论进行分析.
- 内在的维度和光谱分析.
主要成果:
- 可训练的RNN可以在更少的参数下实现更高的准确性.
- 可训练的网络将内部动态塑造成低维的,与任务一致的多元体.
- 固定水库使用高维,纠的表示,证明效率较低.
结论:
- 学习将任务结构提炼成一个紧的表示是有效的循环计算的关键.
- 可训练的RNN通过动态雕塑展示了一个更有效的计算策略.
- 发现将普遍性的理论原则与生物神经重绘联系起来.
更多相关视频
05:22Dissociation of the Confounding Influences of Expectancy and Integrative Difficulty Residing in Anomalous Sentences in Event-related Potential Studies
Published on: May 9, 2019
11:09RBDT: A Computerized Task System based in Transposition for the Continuous Analysis of Relational Behavior Dynamics in Humans
Published on: July 17, 2021
相关概念视频
Woodward–Hoffmann Selection Rules and Microscopic Reversibility
Integration of Synaptic Events
Classification of Systems-II
Multi-input and Multi-variable systems
In the absence of...
Parameters Affecting Nonlinear Elimination: Zero-Order Input, First-Order Absorption and Two-Compartment Model
When a drug is administered through a constant intravenous infusion and eliminated via nonlinear pharmacokinetics, it follows zero-order input. For example, oral drugs undergo first-order absorption upon administration and are eliminated through nonlinear pharmacokinetics.
In the case of subcutaneously administered drugs,...
Associative Learning
Classical conditioning, also known...