About

XAI refers to methods and techniques in the application of artificial intelligence (AI) such that the results of the solution can be understood by humans. It contrasts with the concept of the "black box" in machine learning where even its designers cannot explain why an AI arrived at a specific decision. XAI may be an implementation of the social right to explanation. XAI is relevant even if there is no legal right or regulatory requirement—for example, XAI can improve the user experience of a product or service by helping end users trust that the AI is making good decisions. This way the aim of XAI is to explain what has been done, what is done right now, what will be done next and unveil the information the actions are based on. These characteristics make it possible (i) to confirm existing knowledge (ii) to challenge existing knowledge and (iii) to generate new assumptions.

Benchmarks

No evaluation results yet. Help compare methods by submit evaluation metrics.

Greatest papers with code

Proposed Guidelines for the Responsible Use of Explainable Machine Learning

8 Jun 2019jphall663/interpretable_machine_learning_with_python

Explainable machine learning (ML) enables human learning from ML, human appeal of automated model decisions, regulatory compliance, and security audits of ML models.

EXPLAINABLE ARTIFICIAL INTELLIGENCE

Towards Best Practice in Explaining Neural Network Decisions with LRP

22 Oct 2019sebastian-lapuschkin/lrp_toolbox

In this paper, we focus on a popular and widely used method of XAI, the Layer-wise Relevance Propagation (LRP).

EXPLAINABLE ARTIFICIAL INTELLIGENCE OBJECT DETECTION OBJECT LOCALIZATION

The Grammar of Interactive Explanatory Model Analysis

1 May 2020ModelOriented/modelStudio

Surprisingly, the majority of methods developed for explainable machine learning focus on a single aspect of the model behavior.

EXPLAINABLE ARTIFICIAL INTELLIGENCE

Do Not Trust Additive Explanations

27 Mar 2019ModelOriented/iBreakDown

Explainable Artificial Intelligence (XAI)has received a great deal of attention recently.

EXPLAINABLE ARTIFICIAL INTELLIGENCE

SoPa: Bridging CNNs, RNNs, and Weighted Finite-State Machines

15 May 2018Noahs-ARK/soft_patterns

Recurrent and convolutional neural networks comprise two distinct families of models that have proven to be useful for encoding natural language utterances.

CLASSIFICATION EXPLAINABLE ARTIFICIAL INTELLIGENCE REPRESENTATION LEARNING TEXT CLASSIFICATION

SCOUTER: Slot Attention-based Classifier for Explainable Image Recognition

14 Sep 2020wbw520/scouter

Explainable artificial intelligence has been gaining attention in the past few years.

DECISION MAKING EXPLAINABLE ARTIFICIAL INTELLIGENCE

Landscape of R packages for eXplainable Artificial Intelligence

24 Sep 2020MI2DataLab/XAI-tools

The growing availability of data and computing power fuels the development of predictive models.

EXPLAINABLE ARTIFICIAL INTELLIGENCE

Visualizing Adapted Knowledge in Domain Transfer

20 Apr 2021hou-yz/DA_visualization

We visualize the adapted knowledge on several datasets with different UDA methods and find that generated images successfully capture the style difference between the two domains.

EXPLAINABLE ARTIFICIAL INTELLIGENCE UNSUPERVISED DOMAIN ADAPTATION