大脑启发的神经电路进化为神经网络的尖端
Guobin Shen1,2, Dongcheng Zhao1, Yiting Dong1,2
1Brain-inspired Cognitive Intelligence Lab, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China.
概括
这项研究介绍了一种由大脑启发的方法,以演变具有多样化的神经回路的尖端神经网络. 这种方法提高了图像分类和强化学习任务的性能,提高了人工智能能力.
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
- 机器学习 机器学习
背景情况:
- 目前的尖端神经网络 (SNN) 经常使用深度学习结构,主要是前,限制了它们在复杂任务上的潜力.
- 生物神经系统表现出自我组织和多样化的神经元类型,形成复杂的回路用于认知功能,这种丰富的现有SNN设计没有完全捕捉到.
- 将生物神经电路动力学整合到SNN结构中仍然是一个重大挑战.
研究的目的:
- 为设计SNNs开发一个更具生物学可信性的进化框架.
- 通过结合各种神经回路类型和生物启发的学习规则来增强SNN的能力.
- 为了提高复杂任务的性能,如图像分类和强化学习.
主要方法:
- 提出了一个新的进化空间,将前和反连接与激发性和抑制性神经元结合起来.
- 利用局部尖峰时间依赖的可塑性 (STDP) 和全球错误信号以适应性地演变神经回路 (例如,前进/反抑制,侧向抑制).
- 实施神经电路进化策略 (NeuEvo) 来构建用于图像分类和强化学习的SNN.
主要成果:
- 进化后的SNN在感知和强化学习任务中表现出显著增强的能力.
- 纽埃沃在基准数据集上取得了最先进的结果,包括CIFAR10,DVS-CIFAR10,DVS-Gesture和N-Caltech101,以及ImageNet上的高级性能.
- 当与深度强化学习算法相结合时,进化的SNN实现了与传统人工神经网络相美的性能.
结论:
- 灵感来自大脑的NeuEvo策略有效地发展出具有丰富神经电路类型的复杂SNN,克服当前SNN设计范式的局限性.
- 这种方法为创建更复杂的人工神经网络提供了基础,灵感来自生物系统.
- 进化的尖端神经回路为复杂网络进化的未来进步为各种功能应用铺平了道路.
相关概念视频
Neural Circuits
1.3K
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...
1.3K
The Role of Ion Channels in Neuronal Computation
3.2K
A postsynaptic neuron usually receives numerous impulses from several other presynaptic neurons. The axon hillock of the postsynaptic neuron integrates all these signals and determines the likelihood of firing an action potential.
Sometimes a single EPSP is strong enough to induce an action potential in the postsynaptic neuron. However, multiple presynaptic inputs must often create EPSPs around the same time for the postsynaptic neuron to be sufficiently depolarized to fire an action potential....
Sometimes a single EPSP is strong enough to induce an action potential in the postsynaptic neuron. However, multiple presynaptic inputs must often create EPSPs around the same time for the postsynaptic neuron to be sufficiently depolarized to fire an action potential....
3.2K
Propagation of Action Potentials
5.9K
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...
5.9K
Integration of Synaptic Events
1.6K
Synaptic integration mainly includes the summation of graded potentials. Graded potentials, regardless of their type, cause subtle alterations in membrane voltage, resulting in either depolarization or hyperpolarization. These incremental changes, when combined or summed, can propel the neuron toward its threshold. Consider, for example, a membrane experiencing a +15 mV shift, causing it to depolarize from -70 mV to -55 mV. In this scenario, graded potentials govern the membrane's ability to...
1.6K
Neuroplasticity
444
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.
444


