|
所在平台: Coursera |
课程主页: https://www.coursera.org/learn/cdss3
课程评论：没有评论
课程名称：健康护理中的可解释深度学习模型 - CDSS 3 课程概述： 本课程将介绍机器学习应用中的可解释性和解释性概念。学习者将理解全球解释、局部解释、模型无关解释和模型特定解释之间的区别。同时，课程将详细讲解并应用最新的可解释性方法，如置换特征重要性（PFI）、局部可解释模型无关解释（LIME）和SHapley加性解释（SHAP）于时间序列分类中。接下来，将解释并实施模型特定的解释方法，如类激活映射（CAM）和梯度加权类激活映射（Gradient-Weighted CAM）。学习者将理解公理归因及其重要性。最后，将在递归层后引入注意力机制，并可视化注意力权重，以生成模型的局部解释。 课程大纲： 1. 可解释与可解释机器学习模型在健康护理中的应用 - 深度学习模型复杂，难以理解其决策。解释性方法旨在揭示深度学习决策，增强信任、避免错误并确保人工智能的伦理使用。解释可以被分为全球、局部、模型无关和模型特定。置换特征重要性是一种全球、模型无关的可解释性方法，提供与哪些输入变量与输出更相关的信息。 2. 深度学习模型的局部可解释性方法 - 局部可解释性方法为模型如何做出特定决策提供解释。LIME通过使用更简单、可解释的模型局部近似原始模型。而SHAP在此基础上扩展，并旨在解决输入特征的多重共线性问题。LIME和SHAP均为局部、模型无关的解释方法。相对而言，CAM是一种类区分可视化技术，专门旨在为深度神经网络提供局部解释。 3. 梯度加权类激活映射和积分梯度 - GRAD-CAM是CAM的扩展，旨在更广泛地应用于深度神经网络架构。尽管它是解释深度神经网络决策的最流行方法之一，但它违反了一些关键的公理性质，如灵敏性和完整性。积分梯度是一种公理归因方法，旨在弥补这一缺陷。 4. 深度学习中的注意力机制 - 深度神经网络中的注意力机制模仿人类的注意力，将计算资源分配给一小部分感官输入，以便在有限的处理能力内处理特定信息。本周，我们讨论如何在递归神经网络和自编码器中融入注意力机制。进一步地，我们将可视化注意力权重，以提供决策过程的内在解释。
Name:Interpretable vs Explainable Machine Learning Models in Healthcare
Description:Deep learning models are complex and it is difficult to understand their decisions. Explainability methods aim to shed light to the deep learning decisions and enhance trust, avoid mistakes and ensure ethical use of AI. Explanations can be categorised as global, local, model-agnostic and model-specific. Permutation feature importance is a global, model agnostic explainabillity method that provide information with relation to which input variables are more related to the output.
Name:Local Explainability Methods for Deep Learning Models
Description:Local explainability methods provide explanations on how the model reach a specific decision. LIME approximates the model locally with a simpler, interpretable model. SHAP expands on this and it is also designed to address multi-collinearity of the input features. Both LIME and SHAP are local, model-agnostic explanations. On the other hand, CAM is a class-discriminative visualisation techniques, specifically designed to provide local explanations in deep neural networks.
Name:Gradient-weighted Class Activation Mapping and Integrated Gradients
Description:GRAD-CAM is an extension of CAM, which aims to a broader application of the architecture in deep neural networks. Although, it is one of the most popular methods in explaining deep neural network decisions, it violates key axiomatic properties, such as sensitivity and completeness. Integrated gradients is an axiomatic attribution method that aims to cover this gap.
Name:Attention mechanisms in Deep Learning
Description:Attention in deep neural networks mimics human attention that allocates computational resources to a small range of sensory input in order to process specific information with limited processing power. In this week, we discuss how to incorporate attention in Recurrent Neural Networks and autoencoders. Furthermore, we visualise attention weights in order to provide a form of inherent explanation for the decision making process.
This course will introduce the concepts of interpretability and explainability in machine learning applications. The learner will understand the difference between global, local, model-agnostic and model-specific explanations. State-of-the-art explainability methods such as Permutation Feature Importance (PFI), Local Interpretable Model-agnostic Explanations (LIME) and SHapley Additive exPlanation (SHAP) are explained and applied in time-series classification. Subsequently, model-specific explanations such as Class-Activation Mapping (CAM) and Gradient-Weighted CAM are explained and implemented. The learners will understand axiomatic attributions and why they are important. Finally, attention mechanisms are going to be incorporated after Recurrent Layers and the attention weights will be visualised to produce local explanations of the model.
