快速协议驱动的设备校准的本地学习范式用于尖端神经网络
Saptarshi Bej1, Muhammed Sahad E2, Gouri Lakshmi S1
1School of Data Science, Indian Institute of Science Education and Research, Thiruvananthapuram, India.
概括
新的突触学习规则,尖端协议依赖可塑性 (SADP) 和尖端相关性依赖可塑性 (SCDP),使尖端神经网络 (SNN) 能够更快地学习. 这些生物启发的规则为下一代神经形态系统提供了高效的硬件实现.
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:
- 经典的尖峰时间依赖可塑性 (STDP) 依赖于精确的尖峰时间,限制计算效率.
- 尖端神经网络 (SNN) 为节能AI提供了潜力,但需要有效的学习规则.
- 生物启发的学习规则对于推进神经形态计算至关重要.
研究的目的:
- 引入新的突触学习规则:尖端协议依赖可塑性 (SADP) 和尖端相关性依赖可塑性 (SCDP).
- 与传统的STDP相比,评估SADP和SCDP的效率和有效性.
- 探索协议驱动的可塑性对神经形态系统的潜力.
主要方法:
- 开发了SADP和SCDP,专注于尖峰列车协议和相关性,而不是精确的时间.
- 实现了线性时间复杂性的SADP和SCDP,以实现高效的硬件实现.
- 在使用单层网络的MNIST和Fashion-MNIST数据集上验证了SADP和SCDP.
主要成果:
- 与STDP相比,SADP和SCDP的特征学习速度明显更快.
- 实现了强大的下游分类准确性,其训练时间减少了数量级.
- 通过事件驱动的,比特式逻辑展示了高效的硬件实现能力.
结论:
- 协议驱动的可塑性提供了一个快速,本地和生物可信的学习框架.
- SADP和SCDP是神经形态系统可行的无监督学习机制.
- 该框架为增强人工智能能力的监督学习范式提供了潜在的扩展.
相关概念视频
01:25Neural Circuits
3.1K
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...
3.1K
01:37Neural Regulation
44.0K
Digestion begins with a cephalic phase that prepares the digestive system to receive food. When our brain processes visual or olfactory information about food, it triggers impulses in the cranial nerves innervating the salivary glands and stomach to prepare for food.
44.0K