小柯机器人

将Hebbian和预测可塑性相结合可对深度感官网络中不变对象进行表征，这一成果由瑞士弗里德里希·米歇尔生物医学研究所Friedemann Zenke团队经过不懈努力而取得。相关论文于2023年10月12日发表在《自然-神经科学》杂志上。

在本研究中，研究人员发现将Hebbian可塑性与预测可塑性相结合会产生深度神经网络模型中的不变表征。研究推导出了一个局部学习规律，该规律可推广到尖峰神经网络，并能解释几个突触可塑性实验中观察到的特性，包括再可塑性和尖峰时间依赖可塑性。最后，该模型可准确捕捉灵长类动物下颞叶皮层中观察到的神经元选择性变化，以响应视觉体验的改变。因此，研究人员提出了一个合理的理论，强调了预测可塑性对正确表征的重要性。

研究人员表示，从感官刺激中识别物体对于生存至关重要。为此，大脑中的感觉网络必须形成与不同刺激一致的物体表征，例如大小、方向和物体相关信息。尽管已知Hebbian可塑性会塑造感觉网络，但它无法在计算模型中创建不变的对象表征，这就产生了大脑如何实现这种处理的问题。

附：英文原文

Title: The combination of Hebbian and predictive plasticity learns invariant object representations in deep sensory networks

Author: Halvagal, Manu Srinath, Zenke, Friedemann

Issue&Volume: 2023-10-12

Abstract: Recognition of objects from sensory stimuli is essential for survival. To that end, sensory networks in the brain must form object representations invariant to stimulus changes, such as size, orientation and context. Although Hebbian plasticity is known to shape sensory networks, it fails to create invariant object representations in computational models, raising the question of how the brain achieves such processing. In the present study, we show that combining Hebbian plasticity with a predictive form of plasticity leads to invariant representations in deep neural network models. We derive a local learning rule that generalizes to spiking neural networks and naturally accounts for several experimentally observed properties of synaptic plasticity, including metaplasticity and spike-timing-dependent plasticity. Finally, our model accurately captures neuronal selectivity changes observed in the primate inferotemporal cortex in response to altered visual experience. Thus, we provide a plausible normative theory emphasizing the importance of predictive plasticity mechanisms for successful representational learning.

DOI: 10.1038/s41593-023-01460-y

Source: https://www.nature.com/articles/s41593-023-01460-y

Nature Neuroscience：《自然—神经科学》，创刊于1998年。隶属于施普林格·自然出版集团，最新IF：28.771
官方网址：https://www.nature.com/neuro/
投稿链接：https://mts-nn.nature.com/cgi-bin/main.plex