通过梯度和结构的学习延迟:在尖端神经网络中出现时空模式的出现
Balázs Mészáros1, James C Knight1, Thomas Nowotny1
1Sussex AI, School of Engineering and Informatics, University of Sussex, Brighton, United Kingdom.
Frontiers in computational neuroscience
|January 6, 2025
概括
我们开发了尖端神经网络 (SNN) 模型,具有可学习的突触延迟. 动态修剪优于其他方法,保留时空模式,以便有效处理时间数据.
科学领域:
- 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:
- 尖端神经网络 (SNN) 是生物启发的计算模型.
- 突触延迟对于SNN的时间处理至关重要,但很难学习.
- 高效的SNN需要优化连接和时间动态.
研究的目的:
- 引入和评估两种新的方法,用于纳入SNN中可学习的突触延迟.
- 研究延迟学习对SNN内部时空动态的影响.
- 为了比较不同延迟学习策略在关键词发现任务上的表现.
主要方法:
- 开发了一种每突触延迟学习方法,使用可学习间隔的扩展卷积 (DCLS).
- 实施了延迟学习的动态修剪策略,包括连接选择,修剪 (DEEP R) 和重新布线 (RigL).
- 在原始海德堡数字数据集上训练并评估了这两种方法,使用时间向后传播与替代梯度.
主要成果:
- 分析显示,在训练后,突触刺激和抑制在空间和时间上自然聚集在一起.
- 动态修剪方法在稀疏网络中表现优于每突触延迟学习.
- 动态修剪方法在优化过程中成功保存了学习的时空模式.
结论:
- 将突触延迟学习与动态修剪相结合,为开发对时间数据的高效SNN提供了有效的策略.
- 动态修剪方法在维持关键的时空动态方面表现出强大.
- 这些发现为通过优化SNN推进神经形态计算应用提供了基础.
更多相关视频
10:45Time-dependent Increase in the Network Response to the Stimulation of Neuronal Cell Cultures on Micro-electrode Arrays
Published on: May 29, 2017
9.8K
08:05Measuring Statistical Learning Across Modalities and Domains in School-Aged Children Via an Online Platform and Neuroimaging Techniques
Published on: June 30, 2020
7.4K
相关概念视频
Graded Potential
11.9K
Graded potentials are localized fluctuations in the cell membrane's electrical charge, commonly found in the dendrites of neurons. The magnitude of these potential changes depends on the strength of the initiating stimulus. In a membrane at its resting potential, a graded potential signifies a voltage shift either above -70 mV or below -70 mV.
Graded potentials fall into two categories: depolarizing and hyperpolarizing. Depolarizing graded potentials typically occur when sodium (Na+) or...
Graded potentials fall into two categories: depolarizing and hyperpolarizing. Depolarizing graded potentials typically occur when sodium (Na+) or...
11.9K
Propagation of Action Potentials
15.4K
The propagation of an action potential refers to the process by which a nerve impulse, or "action potential," travels along a neuron.
Neurons (nerve cells) have a resting membrane potential, with a slightly negative charge inside compared to outside. This is maintained by ion channels, such as sodium (Na+) and potassium (K+) channels, which control the flow of ions. When a stimulus, like a touch or a signal from another neuron, triggers the neuron, sodium channels open, allowing sodium ions to...
Neurons (nerve cells) have a resting membrane potential, with a slightly negative charge inside compared to outside. This is maintained by ion channels, such as sodium (Na+) and potassium (K+) channels, which control the flow of ions. When a stimulus, like a touch or a signal from another neuron, triggers the neuron, sodium channels open, allowing sodium ions to...
15.4K
Neural Circuits
3.0K
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...
3.0K
Neuroplasticity
2.6K
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.
2.6K
