[1905.10037] Brain-mediated Transfer Learning of Convolutional Neural Networkscontact arXivarXiv Twitter

The human brain can effectively learn a new task from a small number of samples, which indicate that the brain can transfer its prior knowledge to solve tasks in different domains. This function is analogous to transfer learning (TL) in the field of machine learning. TL uses a well-trained feature space in a specific task domain to improve performance in new tasks with insufficient training data. TL with rich feature representations, such as features of convolutional neural networks (CNNs), shows high generalization ability across different task domains. However, such TL is still insufficient in making machine learning attain generalization ability comparable to that of the human brain. To examine if the internal representation of the brain could be used to achieve more efficient TL, we introduce a method for TL mediated by human brains. Our method transforms feature representations of audiovisual inputs in CNNs into those in activation patterns of individual brains via their associati

1 mentions: @PMinervini
Date: 2020/02/14 11:20

Related Entries

Read more [Data Augmentation 第1回] mixup 事始め | 技ラボ
0 users, 0 mentions 2018/07/02 12:23
Read more [1907.02893] Invariant Risk Minimization
0 users, 7 mentions 2019/07/11 00:47
Read more [1906.06423] Fixing the train-test resolution discrepancy
0 users, 4 mentions 2019/08/07 05:17
Read more [2001.11822] Cat Swarm Optimization Algorithm -- A Survey and Performance Evaluationcontact arXivarX...
0 users, 1 mentions 2020/02/03 05:21
Read more chainer.training.extensions.Evaluator — Chainer 7.1.0 documentation
0 users, 1 mentions 2020/02/18 06:51