CAREER: Understanding visual learning with self-supervised neural network models

职业：通过自监督神经网络模型理解视觉学习

• 批准号: 1844724
• 负责人: Daniel Yamins
• 金额: $ 60万
• 依托单位: Stanford University
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2019
• 资助国家: 美国
• 起止时间: 2019-09-01 至 2024-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1844724&HistoricalAwards=false
• 关键词: CAREER; Understanding; visual; learning; self

A central problem in artificial intelligence today is that machine learning algorithms often require supervised training with huge amounts of hand-curated data. As a result, such algorithms are largely limited in scope to domains where well-funded organizations can build massive, expertly-annotated, and typically proprietary, labelled datasets. In contrast, real biological systems such as human infants learn much more efficiently, combining a small amount of explicit supervision with powerful -- but not fully understood -- mechanisms of self-supervision. This proposal seeks to build biologically-inspired general-purpose self-supervised systems that can learn without needing to be spoon-fed millions of labeled examples. The basic strategy to achieve this goal will be to develop and refine techniques in the emerging field of unsupervised deep learning, in which neural networks train themselves to capture the subtle statistical patterns present in their sensory surroundings. These networks will be augmented to operate as agents in a rich interactive physical domain, where they will seek out challenging but ultimately solvable self-supervised "goals" that will teach them to flexibly represent and respond to their environment. If successful, such systems will have the ability to use the wealth of unlabeled data that is ubiquitously available in the physical world. The proposal also seeks to use these algorithmic ideas as hypotheses for quantitative models of learning in real biological systems. Using recently developed techniques from computational neuroscience, the neural networks will be compared to neural and behavioral data collected using a wide spectrum of experimental paradigms. It will then be determined which self-supervised neural network learning models best capture the empirical data -- and equally importantly, where the most glaring mismatches between experiment and computational models lie. Quantifying these model-data comparisons will in turn allow for feedback to build better neural network algorithms. The ultimate goal of this work is to set up a tight loop between experimental observation and computational algorithm development, accelerating progress both in artificial intelligence and neuroscience.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

当今人工智能的一个核心问题是，机器学习算法通常需要使用大量手工管理的数据进行有监督的训练。因此，这种算法的范围在很大程度上局限于资金充足的组织可以构建大量、经过专业注释的、通常是专有的标记数据集的领域。相比之下，真正的生物系统，如人类婴儿，学习效率要高得多，它将少量的显性监督与强大的--但尚未完全理解--的自我监督机制结合在一起。这项提议寻求建立受生物启发的通用自我监督系统，该系统可以学习，而不需要用勺子灌输数百万个有标签的例子。实现这一目标的基本策略将是开发和改进无监督深度学习这一新兴领域的技术，在该领域中，神经网络通过训练自己来捕获存在于其感觉环境中的微妙统计模式。这些网络将被扩展为在丰富的交互物理领域中作为代理运行，在那里他们将寻找具有挑战性但最终可解决的自我监督的“目标”，这些目标将教会他们灵活地表示和响应他们的环境。如果成功，这样的系统将有能力利用物理世界中无处不在的大量未标记数据。该提案还试图将这些算法思想用作真实生物系统中学习的量化模型的假设。利用计算神经科学最近开发的技术，神经网络将与使用广泛实验范例收集的神经和行为数据进行比较。然后，将确定哪种自我监督神经网络学习模型最好地捕捉经验数据--同样重要的是，实验模型和计算模型之间最明显的不匹配之处。量化这些模型-数据比较将反过来允许反馈，以构建更好的神经网络算法。这项工作的最终目标是在实验观察和计算算法开发之间建立一个紧密的循环，加速人工智能和神经科学的进步。这一奖项反映了NSF的法定使命，并通过使用基金会的智力优势和更广泛的影响审查标准进行评估，被认为值得支持。

项目成果

Two Routes to Scalable Credit Assignment without Weight Symmetry

• 发表时间: 2020-02
• 期刊: ArXiv
• 作者: D. Kunin;Aran Nayebi;Javier Sagastuy-Breña;S. Ganguli;Jonathan M. Bloom;Daniel L. K. Yamins

Developmental Curiosity and Social Interaction in Virtual Agents.

虚拟代理中的发展好奇心和社交互动。

• 发表时间: 2023
• 期刊: Program of the annual conference of the Cognitive Science Society
• 作者: Doyle C, Shader S

Unsupervised Segmentation in Real-World Images via Spelke Object Inference

• DOI: 10.48550/arxiv.2205.08515
• 发表时间: 2022-05
• 作者: Honglin Chen;R. Venkatesh;Yoni Friedman;Jiajun Wu;J. Tenenbaum;Daniel L. K. Yamins;Daniel Bear

How Well Do Unsupervised Learning Algorithms Model Human Real-time and Life-long Learning?

• 发表时间: 2022
• 期刊: Advances in neural information processing systems
• 作者: Chengxu Zhuang;Ziyu Xiang;Yoon Bai;Xiaoxuan Jia;N. Turk-Browne;K. Norman;J. DiCarlo;Daniel Yamins

Active World Model Learning in Agent-rich Environments with Progress Curiosity

• 发表时间: 2020-07
• 作者: Kuno Kim;Megumi Sano;Julian De Freitas;Nick Haber;Daniel L. K. Yamins