EAGER: Towards robust, interpretable deep learning via communication theory and neuro-inspiration

EAGER：通过沟通理论和神经灵感实现稳健、可解释的深度学习

• 批准号: 2224263
• 负责人: Upamanyu Madhow
• 金额: $ 25万
• 依托单位: University of California-Santa Barbara
• 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: 2022-07-01 至 2025-06-30
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2224263&HistoricalAwards=false
• 关键词: EAGER; Towards; robust; interpretable; deep

Deep neural networks (DNNs) are attaining great success in an increasing array of applications, yet there remain persistent concerns regarding their lack of interpretability and robustness. The standard approach to training DNNs is to optimize an end-to-end cost function based on variants of gradient descent. This simple approach is flexible, allowing innovation in architectures and applications, and scaling to neural networks with a large number of parameters, given enough data and computational power. Such end-to-end, or top-down training, however, does not provide control over, or understanding of, the features being extracted by the layers of the neural networks. The vulnerability of DNNs to adversarial attacks, for example, is a symptom of this phenomenon. The proposed research seeks to address these drawbacks using ideas from communication theory and neuroscience: the goal is to actively shape the features being extracted by individual layers of the neural network, in addition to training the overall network to attain an end-to-end goal. This research will contribute to curricular enhancements in signal processing and machine learning explored via courses, REU projects and senior capstone projects.The proposed technical approach leverages the existing computational infrastructure for training, while imposing layer-by-layer constraints aimed at producing sparse, strong activations. Drawing on ideas from communication theory, the goal is to learn “matched filters” which enhance the “signal-to-noise ratio (SNR)” at neuron outputs at each layer. One may show that this approach is consistent with Hebbian and anti-Hebbian (HAH) learning as posited in neuroscience, in which neurons that are strongly activated for an input are promoted, with less active neurons being demoted. This work posits enhanced robustness via such an SNR-maximizing strategy, together with additional nonlinear transformations such as divisive normalization borrowed from neuroscience. While preliminary visualizations indicate more interpretable neurons, there is reason to expect sparse, strong activations to be more amenable to quantitative interpretation via statistical and information-theoretic analysis. The goal of the proposed research is two-fold: to gain theoretical insight into HAH-based learning via toy models, and to demonstrate practical gains in robustness and interpretability relative to state of the art DNNs. Experimental evaluations will initially be conducted on image datasets which provide standard performance benchmarks.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）在烦恼的应用程序中取得了巨大的成功。给定足够的数据和计算机，无法控制神经网络的层次。 NEUROS塑造了K提取的功能，除了训练整个网络以实现端到端的目标，这项研究有助于通过课程处理和通过REU项目探索的信号处理和机器学习的增强项目。拟议的技术方法利用了他现有的计算基础架构进行培训，同时旨在逐层限制，旨在产生稀疏，强大的EAS。比率（SNR）“在每一层的神经元输出处。CH与神经科学中假定的Hebbian抗Hebbian（HAH）学习一致，其中促进了输入的神经元的神经元，促进了活性较低的神经元。这种SNR最大化的策略，以及诸如分裂归一化的添加性非传单，而初步的可视化表明，通过统计和理论上的研究表明，通过统计学上的解释更加可解释。模型，并在图像数据集中进行铝的实用性和IND解释性，以提供标准的表演。使用基金会的智力优点和更广泛的影响评估标准进行评估。

项目成果

Generalized Likelihood Ratio Test for Adversarially Robust Hypothesis Testing

• DOI: 10.1109/tsp.2022.3198169
• 发表时间: 2021-12
• 期刊: IEEE Transactions on Signal Processing
• 影响因子: 5.4
• 作者: Bhagyashree Puranik;Upamanyu Madhow;Ramtin Pedarsani

Dynamic Positive Reinforcement For Long-Term Fairness

动态正强化以实现长期公平

• 发表时间: 2022
• 期刊: ICML 2022 Workshop on Responsible Decision Making in Dynamic Environments
• 作者: Puranik, B.;Madhow, U.;Pedarsani, R.
• 通讯作者: Pedarsani, R.

A Dynamic Decision-Making Framework Promoting Long-Term Fairness

促进长期公平的动态决策框架

• DOI: 10.1145/3514094.3534127
• 发表时间: 2022
• 期刊: AIES 2022
• 作者: Puranik, Bhagyashree;Madhow, Upamanyu;Pedarsani, Ramtin
• 通讯作者: Pedarsani, Ramtin

Towards robust, interpretable neural networks via Hebbian/anti-Hebbian learning: A software framework for training with feature-based costs

通过赫布/反赫布学习实现稳健、可解释的神经网络：基于特征成本的训练软件框架

• DOI: 10.1016/j.simpa.2022.100347
• 发表时间: 2022
• 期刊: Software Impacts
• 作者: Cekic, Metehan;Bakiskan, Can;Madhow, Upamanyu
• 通讯作者: Madhow, Upamanyu

Early Layers Are More Important For Adversarial Robustness

• 发表时间: 2022
• 作者: Can Bakiskan;Metehan Cekic;Upamanyu Madhow