在一个集成光子神经网络中出现的自我适应,以实现无反向传播的学习
Alessio Lugnan1, Samarth Aggarwal2, Frank Brückerhoff-Plückelmann3
1Photonics Research Group, Ghent University-imec, Ghent, 9052, Belgium.
Advanced science (Weinheim, Baden-Wurttemberg, Germany)
|November 20, 2024
概括
这项研究证明了光子神经网络中新兴的塑料自我适应和多尺度记忆. 这些硬件神经网络在没有外部控制器或奖励信号的情况下实现数字分类的高性能.
科学领域:
- 神经形态工程的神经形态工程
- 这是光子计算.
- 人工智能 硬件 硬件
背景情况:
- 生物大脑表现出塑性自我适应,非线性动力学和多尺度记忆,使高级学习和信息处理成为可能.
- 当前神经网络的硬件实现往往缺乏这些内在的,类似大脑的能力.
- 在硬件中自主实现这些功能对于开发更高效和生物可信的人工智能系统至关重要.
研究的目的:
- 通过实验证明塑料自我适应,非线性循环动力学和光子神经元阵列中的多尺度记忆.
- 在没有外部控制器或明确的奖励信号的情况下,在硬件神经网络中实现自主,新兴的学习.
- 为了评估这个光子系统在基准分类任务上的性能.
主要方法:
- 利用基于光子学的光子神经元阵列,用相变材料进行非挥发性记忆的微波共振器.
- 实现这些光子数组的层次结构与使用后勤回归的无反传播训练算法相结合.
- 在光子神经元阵列中实验证明了新兴的,自主学习特性.
主要成果:
- 在光子神经元阵列中成功实验证明了塑料自我适应,非线性反复动态和多尺度记忆.
- 在MNIST手写数字分类任务中实现了98.2%的性能.
- 该系统显示了紧,坚固和可扩展的特性,适合高速,生物可信的学习.
结论:
- 光子神经网络可以自主表现出类似大脑的学习特征,包括可塑性和记忆力.
- 开发的系统提供了一个新的平台,可以高效地,快速地实现生物灵感的人工智能.
- 这种方法绕过了复杂的外部控制和传统的反向传播的需要,为新的硬件AI范式铺平了道路.
相关概念视频
Neuroplasticity
298
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.
298
Neural Circuits
1.1K
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...
1.1K
Vision
52.9K
Vision is the result of light being detected and transduced into neural signals by the retina of the eye. This information is then further analyzed and interpreted by the brain. First, light enters the front of the eye and is focused by the cornea and lens onto the retina—a thin sheet of neural tissue lining the back of the eye. Because of refraction through the convex lens of the eye, images are projected onto the retina upside-down and reversed.
52.9K
Photoreceptors and Visual Pathways
5.7K
At the molecular level, visual signals trigger transformations in photopigment molecules, resulting in changes in the photoreceptor cell's membrane potential. The photon's energy level is denoted by its wavelength, with each specific wavelength of visible light associated with a distinct color. The spectral range of visible light, classified as electromagnetic radiation, spans from 380 to 720 nm. Electromagnetic radiation wavelengths exceeding 720 nm fall under the infrared category,...
5.7K
The Retina
67.7K
The retina is a layer of nervous tissue at the back of the eye that transduces light into neural signals. This process, called phototransduction, is carried out by rod and cone photoreceptor cells in the back of the retina.
67.7K


