A neural network trained for prediction mimics diverse features of biological neurons and perception.

A neural network trained for prediction mimics diverse features of biological neurons and perception.
复制标题

DOI:
10.1038/s42256-020-0170-9
复制
发表时间:
2020-04
影响因子:
23.8
通讯作者:
Cox D
Cox D
中科院分区:
计算机科学1区
文献类型:
--
作者:
Lotter W;Kreiman G;Cox D

文献摘要

参考文献

被引文献

相似文献

最近的工作表明,在图像识别任务上训练的卷积神经网络(CNN)可以作为预测灵长类视觉皮层神经反应的有价值的模型。然而,这些模型通常需要生物学上不可行的标记训练数据水平,因此这种相似性必须至少通过不同的路径产生。此外,大多数流行的CNN仅仅是前馈的,缺乏时间和递归的概念,而视觉皮层中的神经元即使对静态输入也会产生复杂的时变响应。为了解决这些与生物学的不一致,在这里我们研究了一个循环生成网络的新兴特性,该网络经过训练,可以以自我监督的方式预测未来的视频帧。值得注意的是,由此产生的模型能够捕捉到在视觉皮层中观察到的各种各样看似不同的现象,从单个单元反应动态到复杂的感知运动错觉,即使在受到高度贫困的刺激时也是如此。这些结果表明,递归预测神经网络模型与大脑中的计算之间存在潜在的深层联系,为丰富这两个领域提供了新的线索。
Recent work has shown that convolutional neural networks (CNNs) trained on image recognition tasks can serve as valuable models for predicting neural responses in primate visual cortex. However, these models typically require biologically-infeasible levels of labeled training data, so this similarity must at least arise via different paths. In addition, most popular CNNs are solely feedforward, lacking a notion of time and recurrence, whereas neurons in visual cortex produce complex time-varying responses, even to static inputs. Towards addressing these inconsistencies with biology, here we study the emergent properties of a recurrent generative network that is trained to predict future video frames in a self-supervised manner. Remarkably, the resulting model is able to capture a wide variety of seemingly disparate phenomena observed in visual cortex, ranging from single-unit response dynamics to complex perceptual motion illusions, even when subjected to highly impoverished stimuli. These results suggest potentially deep connections between recurrent predictive neural network models and computations in the brain, providing new leads that can enrich both fields.
DOI: 10.1016/j.neuron.2012.10.038
发表时间: 2012-11-21
期刊: Neuron
影响因子: 16.2
作者:
Bastos AM;Usrey WM;Adams RA;Mangun GR;Fries P;Friston KJ
通讯作者: Friston KJ
DOI: 10.1371/journal.pcbi.1003258
发表时间: 2013
影响因子: 4.3
作者:
Boerlin M;Machens CK;Denève S
通讯作者: Denève S
DOI: 10.1098/rstb.2005.1622
发表时间: 2005-04-29
影响因子: 6.3
作者:
Friston, KJ
通讯作者: Friston, KJ
DOI: 10.1126/science.287.5460.2036
发表时间: 2000-03-17
期刊: SCIENCE
影响因子: 56.9
作者:
Eagleman, DM;Sejnowski, TJ
通讯作者: Sejnowski, TJ
DOI: 10.1207/s15516709cog1402_1
发表时间: 1990-04-01
期刊: COGNITIVE SCIENCE
影响因子: 2.5
作者:
ELMAN, JL
通讯作者: ELMAN, JL