%0 Generic %1 liu2020brainlike %A Liu, Tao %D 2020 %K Brain %T BHN: A Brain-like Heterogeneous Network %U http://arxiv.org/abs/2005.12826 %X The human brain works in an unsupervised way, and more than one brain region is essential for lighting up intelligence. Inspired by this, we propose a brain-like heterogeneous network(BHN) which can cooperatively learn distributed representations, like the cortex, and a global contextual representation, like the medial temporal lobe(MTL). By optimizing a distributed, self-supervised and gradient-isolated contrastive loss function in a discriminative adversarial fashion, our model successfully learns to extract useful representations from video data. Methods developed in this work may help to solve some key problems in pursuit of human-level intelligence.

@misc{liu2020brainlike, abstract = {The human brain works in an unsupervised way, and more than one brain region is essential for lighting up intelligence. Inspired by this, we propose a brain-like heterogeneous network(BHN) which can cooperatively learn distributed representations, like the cortex, and a global contextual representation, like the medial temporal lobe(MTL). By optimizing a distributed, self-supervised and gradient-isolated contrastive loss function in a discriminative adversarial fashion, our model successfully learns to extract useful representations from video data. Methods developed in this work may help to solve some key problems in pursuit of human-level intelligence.}, added-at = {2020-05-27T14:44:20.000+0200}, author = {Liu, Tao}, biburl = {https://www.bibsonomy.org/bibtex/209739882d84d559dd9b897d71b649870/thu27}, description = {BHN: A Brain-like Heterogeneous Network}, interhash = {9d99578be331533f21405e8cab9ba59b}, intrahash = {09739882d84d559dd9b897d71b649870}, keywords = {Brain}, note = {cite arxiv:2005.12826}, timestamp = {2020-05-27T14:44:20.000+0200}, title = {BHN: A Brain-like Heterogeneous Network}, url = {http://arxiv.org/abs/2005.12826}, year = 2020 }