arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1902.02399cs.AIcs.LGcs.NE
收藏

神经启发的创造性解码器

Toward A Neuro-inspired Creative Decoder

IBM Research(IBM研究院);Columbia University(哥伦比亚大学)

Payel Das, Brian Quanz, Pin-Yu Chen, Jae-wook Ahn, Dhruv Shah

摘要:

创造力是一个产生新颖和有意义想法的过程,涉及人脑中任务积极(控制)和任务消极(默认)网络之间的联系。受这一开创性发现的启发,在这项研究中,我们提出了一个创造性的解码器在一个深的生成框架,其中涉及直接调制的神经元激活模式后,从学习的潜在空间采样。所提出的方法是完全无监督的,可以使用现成的。使用几个新颖性度量和人工评估来评估深度解码器的创造能力。我们在不同图像数据集(MNIST,FMNIST,MNIST+FMNIST,WikiArt和CelebA)上的实验表明,深度解码器中高度激活和弱激活神经元的非典型共激活促进了新的和有意义的伪影的生成。

英文摘要:

Creativity, a process that generates novel and meaningful ideas, involves increased association between task-positive (control) and task-negative (default) networks in the human brain. Inspired by this seminal finding, in this study we propose a creative decoder within a deep generative framework, which involves direct modulation of the neuronal activation pattern after sampling from the learned latent space. The proposed approach is fully unsupervised and can be used off-the-shelf. Several novelty metrics and human evaluation were used to evaluate the creative capacity of the deep decoder. Our experiments on different image datasets (MNIST, FMNIST, MNIST+FMNIST, WikiArt and CelebA) reveal that atypical co-activation of highly activated and weakly activated neurons in a deep decoder promotes generation of novel and meaningful artifacts.

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。

↑