arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2303.02015q-bio.NCcs.RO
收藏

Grossberg代码:感知经验的通用神经网络签名

The Grossberg Code: Universal Neural Network Signatures of Perceptual Experience

Centre National de la Recherche Scientifique(法国国家科学研究中心);Strasbourg University(斯特拉斯堡大学)

Birgitta Dresp-Langley

摘要:

自适应共振理论的两个普遍功能原理模拟了所有生物学习和自适应智能的大脑代码。多感官刺激在其直接环境背景下的低级别表征是在自下而上激活的基础上形成的,并在自上而下匹配规则的控制下,这些规则集成了高级别的长期痕迹的上下文配置。这些普遍的编码原则导致所有生物物种(从猿类到灵长类)建立持久的感知经验大脑签名。他们在本文中重新访问的基础上,从原来的代码和一些最近的相关实证研究结果的背景下调制在大脑中的例子,突出了潜在的Grossberg的开拓性的见解和开创性的理论工作的智能解决方案领域的发展和认知机器人。

英文摘要:

Two universal functional principles of Adaptive Resonance Theory simulate the brain code of all biological learning and adaptive intelligence. Low level representations of multisensory stimuli in their immediate environmental context are formed on the basis of bottom up activation and under the control of top down matching rules that integrate high level long term traces of contextual configuration. These universal coding principles lead to the establishment of lasting brain signatures of perceptual experience in all living species, from aplysiae to primates. They are revisited in this paper here on the basis of examples drawn from the original code and from some of the most recent related empirical findings on contextual modulation in the brain, highlighting the potential of Grossberg's pioneering insights and groundbreaking theoretical work for intelligent solutions in the domain of developmental and cognitive robotics.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑