基于敏感性的模型不可知性可扩展的深度学习的解释
Manu Aggarwal1, N G Cogan2, Vipul Periwal1
1National Institutes of Health, Bethesda, MD.
bioRxiv : the preprint server for biology
|March 17, 2025
概括
SensX是一个新的可解释AI (XAI) 框架,它准确地揭示了深度神经网络 (DNN) 如何从数据中学习. 它有效地识别了关键特征,帮助生物学和医学的科学发现.
科学领域:
- 人工智能的人工智能
- 机器学习 机器学习
- 生物信息学是一种生物信息学.
背景情况:
- 深度神经网络 (DNN) 在预测方面表现出色,但缺乏透明度.
- 了解DNN的学习机制对于科学验证和健康应用至关重要.
研究的目的:
- 开发SensX,一个模型不可知可解释AI (XAI) 框架.
- 提高DNN在生物和临床环境中的可解释性.
- 在准确性,速度和一致性方面改进现有的XAI方法.
主要方法:
- 设计了SensX作为一个无模型的XAI框架.
- 评估SensX与最先进的XAI方法对比.
- 应用SensX来解释视觉变压器 (ViT) 模型和用于单细胞RNA-seq数据分析的DNN.
主要成果:
- 比目前的XAI,SensX实现了更高的精度 (高达52%) 和更快的计算 (高达158倍).
- 确定了输入特征的最佳子集,减少了维度.
- 成功解释了大规模ViT模型,并确定了细胞类型注释的关键基因.
结论:
- SensX为DNN解释性提供了一个可扩展和高效的解决方案.
- 该框架验证了学习的特征,并揭示了建筑偏见.
- 在数据驱动科学中,SensX促进了假设生成和模型验证.
相关概念视频
Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving
38
Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
38
Mechanistic Models: Compartment Models in Individual and Population Analysis
23
Mechanistic models are utilized in individual analysis using single-source data, but imperfections arise due to data collection errors, preventing perfect prediction of observed data. The mathematical equation involves known values (Xi), observed concentrations (Ci), measurement errors (εi), model parameters (ϕj), and the related function (ƒi) for i number of values. Different least-squares metrics quantify differences between predicted and observed values. The ordinary least...
23
Fundamental Attribution Error
12.8K
According to some social psychologists, people tend to overemphasize internal factors as explanations—or attributions—for the behavior of other people. They tend to assume that the behavior of another person is a trait of that person, and to underestimate the power of the situation on the behavior of others. They tend to fail to recognize when the behavior of another is due to situational variables, and thus to the person’s state. This erroneous assumption is...
12.8K


