Real time unsupervised learning of visual stimuli in neuromorphic VLSI systems.
Real time unsupervised learning of visual stimuli in neuromorphic VLSI systems.
复制标题
DOI：
10.1038/srep14730
复制
发表时间：
2015-10-14
影响因子：
4.6
通讯作者：
del Giudice P
中科院分区：
文献类型：
--
作者：
Giulioni M;Corradi F;Dante V;del Giudice P
神经形态芯片将神经系统中运行的计算原理体现到微电子设备中。在这个领域中，识别理论和实验表明的通用且可重用的认知元素的计算原语非常重要。循环网络中的吸引子动力学提供了这样的元素之一。点吸引子是动态的平衡状态（直到波动），由网络的突触结构决定；吸引力“盆地”包含松弛时导致给定吸引子的所有初始状态，因此使吸引子动力学适合实现强大的联想记忆。初始网络状态由刺激决定，松弛到吸引子状态实现了相应记忆原型模式的检索。在之前的工作中，我们证明了由尖峰神经元和适当选择的固定突触组成的神经形态循环网络支持吸引子动力学。在这里，我们专注于学习：激活片上突触可塑性并使用理论驱动的策略来选择网络参数，我们表明，在重复呈现简单的视觉刺激后，自主学习可以形成支持刺激选择性吸引子的突触连接。联想记忆在芯片上发展是耦合刺激驱动的神经活动和随后的突触动力学的结果，学习和检索阶段之间没有人为分离。
Neuromorphic chips embody computational principles operating in the nervous system, into microelectronic devices. In this domain it is important to identify computational primitives that theory and experiments suggest as generic and reusable cognitive elements. One such element is provided by attractor dynamics in recurrent networks. Point attractors are equilibrium states of the dynamics (up to fluctuations), determined by the synaptic structure of the network; a ‘basin’ of attraction comprises all initial states leading to a given attractor upon relaxation, hence making attractor dynamics suitable to implement robust associative memory. The initial network state is dictated by the stimulus, and relaxation to the attractor state implements the retrieval of the corresponding memorized prototypical pattern. In a previous work we demonstrated that a neuromorphic recurrent network of spiking neurons and suitably chosen, fixed synapses supports attractor dynamics. Here we focus on learning: activating on-chip synaptic plasticity and using a theory-driven strategy for choosing network parameters, we show that autonomous learning, following repeated presentation of simple visual stimuli, shapes a synaptic connectivity supporting stimulus-selective attractors. Associative memory develops on chip as the result of the coupled stimulus-driven neural activity and ensuing synaptic dynamics, with no artificial separation between learning and retrieval phases.