当前位置: X-MOL 学术Trends Cogn. Sci. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Next-generation deep learning based on simulators and synthetic data
Trends in Cognitive Sciences ( IF 16.7 ) Pub Date : 2021-12-23 , DOI: 10.1016/j.tics.2021.11.008
Celso M de Melo 1 , Antonio Torralba 2 , Leonidas Guibas 3 , James DiCarlo 4 , Rama Chellappa 5 , Jessica Hodgins 6
Affiliation  

Deep learning (DL) is being successfully applied across multiple domains, yet these models learn in a most artificial way: they require large quantities of labeled data to grasp even simple concepts. Thus, the main bottleneck is often access to supervised data. Here, we highlight a trend in a potential solution to this challenge: synthetic data. Synthetic data are becoming accessible due to progress in rendering pipelines, generative adversarial models, and fusion models. Moreover, advancements in domain adaptation techniques help close the statistical gap between synthetic and real data. Paradoxically, this artificial solution is also likely to enable more natural learning, as seen in biological systems, including continual, multimodal, and embodied learning. Complementary to this, simulators and deep neural networks (DNNs) will also have a critical role in providing insight into the cognitive and neural functioning of biological systems. We also review the strengths of, and opportunities and novel challenges associated with, synthetic data.



中文翻译:

基于模拟器和合成数据的下一代深度学习

深度学习 (DL) 已成功应用于多个领域,但这些模型以最人工的方式学习:它们需要大量标记数据才能掌握简单的概念。因此,主要瓶颈通常是访问受监督的数据。在这里,我们强调了应对这一挑战的潜在解决方案的趋势:合成数据。由于渲染管道、生成对抗模型和融合模型的进步,合成数据变得可访问。此外,领域适应技术的进步有助于缩小合成数据和真实数据之间的统计差距。矛盾的是,这种人工解决方案也可能实现更自然的学习,如在生物系统中所见,包括持续、多模式和具身学习。与此相辅相成,模拟器和深度神经网络 (DNN) 在深入了解生物系统的认知和神经功能方面也将发挥关键作用。我们还回顾了合成数据的优势、机遇和新挑战。

更新日期:2022-01-19
down
wechat
bug