意识到底是如何产生的?能通过技术手段进行读取吗?(8)

2023-05-21 来源:飞速影视
这一点很像机器学习中的注意力机制,但机器学习中很少主动构造一个全局工作空间
Luczak, Artur, Bruce L. McNaughton, and Yoshimasa Kubo. “Neurons Learn by Predicting Future Activity.” Nature Machine Intelligence 4, no. 1 (January 2022): 62–72. https://doi.org/10.1038/s42256-021-00430-y
Millidge, Beren, Alexander Tschantz, and Christopher L. Buckley. "Predictive coding approximates backprop along arbitrary computation graphs." Neural Computation 34.6 (2022): 1329-1368. https://direct.mit.edu/neco/article-abstract/34/6/1329/110646/Predictive-Coding-Approximates-Backprop-Along
Oizumi, Masafumi, Larissa Albantakis, and Giulio Tononi. “From the Phenomenology to the Mechanisms of Consciousness: Integrated Information Theory 3.0.” Edited by Olaf Sporns. PLoS Computational Biology 10, no. 5 (May 8, 2014): e1003588. https://doi.org/10.1371/journal.pcbi.1003588
IIT理论非常有意思——它有1.0、2.0、3.0版本。不同版本的公理还有所差别。这里引用的是IIT 3.0的公理
PyPhi - Github https://github.com/wmayner/pyphi
abHanson, J. R., & Walker, S. I. (2021). Formalizing falsification for theories of consciousness across computational hierarchies. Neuroscience of Consciousness, 2021(2), niab014.
相关影视
合作伙伴
本站仅为学习交流之用,所有视频和图片均来自互联网收集而来,版权归原创者所有,本网站只提供web页面服务,并不提供资源存储,也不参与录制、上传
若本站收录的节目无意侵犯了贵司版权,请发邮件(我们会在3个工作日内删除侵权内容,谢谢。)

www.fs94.org-飞速影视 粤ICP备74369512号