CIF: Small: Interpretable Machine Learning based on Deep Neural Networks: A Source Coding Perspective

CIF：小：基于深度神经网络的可解释机器学习：源编码视角

• 批准号: 2205004
• 负责人: Jia Li
• 金额: $ 60万
• 依托单位: Pennsylvania State Univ University Park
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-10-01 至 2025-09-30
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2205004&HistoricalAwards=false
• 关键词: CIF; Small; Interpretable; Machine; Learning

Deep neural networks (DNN) have become a core technology for building artificial intelligence (AI) systems, with numerous applications in critical domains such as manufacturing and medicine. Despite the phenomenal success of such networks, their usage has met resistance in many mission-critical tasks because it is difficult to explain the prediction model generated by the computer. For example, in some applications in public health and medicine, because only interpretable models are acceptable, users have stuck with classic machine-learning methods, which are often not as accurate as DNN models. Moreover, increased transparency in AI systems makes human inspection possible, a necessary trait for studying social justice and equity in AI. This project aims to develop theory, methods, and applications to achieve interpretability for machine-learning models based on DNN. Advancement in this project will broaden the usage of DNN in science, engineering, and industry, further unleashing its power. Besides developing fundamental methodologies, the investigators will advance the application area of automated emotion recognition. The ability to recognize and quantify emotion can help psychologists and clinical workers notice extreme distress and potential danger to oneself and others. Through this project, the research team will develop software packages for public access, graduate and undergraduate students will be trained to conduct interdisciplinary research, and the faculty members of the team will integrate the research results into their teaching activities.Although various post-hoc methods have been developed to interpret the decision of DNNs, the explanation is often unstable and highly localized by construction. More importantly, the explanation model exists in separation from the prediction model, whose high complexity remains despite the explanation. In this project, inspired by source coding, the investigators will draw an analogy between explaining a complex model and transmitting signals with a limited channel capacity. Similar to vector quantization to enable data transmission at an allowable rate, the prediction mapping is quantized so that the prediction can be described at a desired level of interpretability. To formalize the idea, the investigators propose a mixture of discriminative models, trained as an embedded part of a neural network. Function approximation theory will be developed for interpretable models based on neural networks. Besides testing and evaluating the proposed framework using benchmark datasets, such as images, videos, text, and biomedical data, the investigators will explore in greater depth the application for emotion recognition based on body movements and, in collaboration with psychology researchers, evaluate the insight gained from interpreting the prediction model.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.

深度神经网络（DNN）已成为构建人工智能（AI）系统的核心技术，在制造和医学等关键领域有着广泛的应用。尽管此类网络取得了巨大的成功，但它们的使用在许多关键任务中遇到了阻力，因为很难解释计算机生成的预测模型。例如，在公共卫生和医学领域的某些应用中，由于只有可解释的模型才是可接受的，因此用户一直坚持使用经典的机器学习方法，而这些方法通常不如 DNN 模型准确。此外，人工智能系统透明度的提高使得人工检查成为可能，这是研究人工智能社会正义和公平的必要特征。该项目旨在开发理论、方法和应用，以实现基于 DNN 的机器学习模型的可解释性。该项目的进展将扩大 DNN 在科学、工程和工业领域的应用，进一步释放其力量。除了开发基本方法之外，研究人员还将推进自动情绪识别的应用领域。识别和量化情绪的能力可以帮助心理学家和临床工作者注意到对自己和他人的极度痛苦和潜在危险。通过这个项目，研究团队将开发可供公众访问的软件包，培养研究生和本科生进行跨学科研究，团队教师将研究成果融入到他们的教学活动中。尽管各种事后方法虽然已经被开发来解释 DNN 的决策，但这种解释通常是不稳定的，并且通过构建而高度局部化。更重要的是，解释模型与预测模型分离存在，尽管有解释，预测模型仍然具有很高的复杂性。在这个项目中，受源编码的启发，研究人员将在解释复杂模型和以有限的信道容量传输信号之间进行类比。与使数据能够以允许的速率传输的矢量量化类似，预测映射被量化，以便可以以期望的可解释性水平来描述预测。为了形式化这个想法，研究人员提出了一种混合判别模型，作为神经网络的嵌入部分进行训练。函数逼近理论将被开发用于基于神经网络的可解释模型。除了使用图像、视频、文本和生物医学数据等基准数据集测试和评估所提出的框架外，研究人员还将更深入地探索基于身体运动的情绪识别的应用，并与心理学研究人员合作，评估洞察力通过解释预测模型获得的奖项。该奖项反映了 NSF 的法定使命，并且通过使用基金会的智力价值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

Unlocking the Emotional World of Visual Media: An Overview of the Science, Research, and Impact of Understanding Emotion

解锁视觉媒体的情感世界：理解情感的科学、研究和影响概述

• DOI: 10.1109/jproc.2023.3273517
• 发表时间: 2023-10
• 期刊: Proceedings of the IEEE. Institute of Electrical and Electronics Engineers
• 作者: James Ze Wang;Sicheng Zhao;Chenyan Wu;Reginald B. Adams;M. Newman;T. Shafir;Rachelle Tsachor
• 通讯作者: Rachelle Tsachor