Explainable artificial intelligence

Use the mouse wheel or two fingers (on touchscreens) to zoom in and out of the map.

Export map as:

Research this topic

Explore the main themes, entities and connections around Explainable artificial intelligence. Start with the topic map, then use the sections below for research and deeper semantic analysis.

Explore this topic

Start with a few of the strongest sections from the source topic. These are research directions, not a list of keywords you must use.

History and methods

Symbolic reasoning systems MYCIN Bacteremia Intelligent tutoring systems SPICE

17 related topics

Explainability and interpretability techniques

Classification Regression Shapley values Multitask learning Saliency maps

24 related topics

Background

Machine learning White-box Medicine Defense Finance

10 related topics

Goals

Agents Algorithms Clinical decision support systems Image recognition Supervised learning

9 related topics

Topics to explore

Browse the full topic structure. Each item opens a new analysis centered on that subject.

Overview

Background

Machine learning
White-box White-box testing
Medicine
Defense Defense industry
Finance
Law
Supervised machine learning
Symbolic regression
Assessing how positive Sentiment analysis
Daniel Day-Lewis

Goals

Agents Agency (sociology)
Algorithms Algorithm
Clinical decision support systems Clinical decision support system
Image recognition
Supervised learning
DARPA
Glass box
Human-in-the-loop
Knowledge extraction

Explainability and interpretability techniques

Classification Statistical classification
Regression Regression analysis
Shapley values Shapley value
Multitask learning
Saliency maps Saliency map
Language models Language model
Generative pretrained transformers Generative pre-trained transformer
Attention Attention (machine learning)
Circuit Circuit (neural network)
Alignment AI alignment
Mechanistic interpretability
Reverse-engineering Reverse engineering
Artificial neural networks
Foundation models Foundation model
Neural network Neural network (machine learning)
Dictionary learning
Safety AI safety
Frontier AI models Frontier model
Convolutional neural networks Convolutional neural network
DeepDream
Transformer-based models Transformer (deep learning)
Knowledge
Inference Statistical inference
MLP Multilayer perceptron

History and methods

Symbolic reasoning systems Symbolic artificial intelligence
MYCIN
Bacteremia
Intelligent tutoring systems
SPICE
Truth maintenance systems Truth-maintenance systems
Rule-based Rule-based system
Expert systems Expert system
Marvin Minsky
Deep learning
Decision trees Decision tree
Bayesian networks Bayesian network
Linear models Linear model
Association for Computing Machinery Conference on Fairness, Accountability, and Transparency (ACM FAccT) ACM Conference on Fairness, Accountability, and Transparency
Software neurons Artificial neuron
Clustering techniques Cluster analysis
Automated pain recognition

Regulation

Criticism

Evidence-based medicine
Lossy compression Lossy compression artefact

Explainability in social choice

Advanced semantic analysis

Deeper signals for content research, entity SEO and topical coverage. The plain-language headings explain what each technical view is useful for.

Map overview Semantic statistics

Nodes86

Edges85

Triples52

Avg. degree1.98

Density0.023256

Components1

How this topic connects Entity context

See the strongest relationship patterns around the current topic before diving into the raw triples.

Explainable artificial intelligence

Top relations

related to External links · 33

Explainable artificial intelligence → Accountability, ACM Conference, AI, AI's, Artificial Intelligence, DARPA, Dipankar, Electronics, Explainable AI, Explaining How End-to-End Deep, FAccT, Fairness, Fernando, Global, Knight, Leaders, Learning Steers, Local Interpretation, Making, Mazumdar

related to Regulation · 18

Explainable artificial intelligence → AI-based, Artificial Intelligence, As, Digital Republic Act, GDPR, General Data Protection Regulation, However, In, In France, International Joint Conference, It, Loi, République, The, The European Union, United States, Workshop, XAI

Important terminology Word statistics

Use these terms to understand the vocabulary surrounding the topic, not as a checklist for keyword stuffing.

Important terminology

ai explanations algorithms knowledge explanation model xai models systems users explainability learning system trust explain explainable decisions interpretability machine may

Entity relationships Subject–Predicate–Object triples

Subject	Predicate	Object	Confidence	Src
SOPHIE that could act as an	instance of	Research in intelligent tutoring systems resulted in developing systems	0.80	text
Explainable artificial intelligence	related to External links	Leaders	0.60	section
Explainable artificial intelligence	related to External links	AI	0.60	section
Explainable artificial intelligence	related to External links	October	0.60	section
Explainable artificial intelligence	related to External links	World Conference	0.60	section
Explainable artificial intelligence	related to External links	Artificial Intelligence	0.60	section
Explainable artificial intelligence	related to External links	ACM Conference	0.60	section
Explainable artificial intelligence	related to External links	Fairness	0.60	section
Explainable artificial intelligence	related to External links	Accountability	0.60	section
Explainable artificial intelligence	related to External links	Transparency	0.60	section
Explainable artificial intelligence	related to External links	FAccT	0.60	section
Explainable artificial intelligence	related to External links	Mazumdar	0.60	section

Related concept clusters Concept neighborhoods

These clusters group vocabulary that occurs around closely connected concepts in the source material.

Connections between topic areas Semantic bridges

Bridges can reveal useful research angles that are easy to miss in a flat list of related terms.

Min side: 3

Research this topic

Explore this topic

History and methods

Explainability and interpretability techniques

Background

Goals

Key facts & relationships

Topics to explore

Overview

Background

Goals

Explainability and interpretability techniques

History and methods

Regulation

Criticism

Explainability in social choice

Advanced semantic analysis

Map overview Semantic statistics

Explainable artificial intelligence

How this topic connects Entity context

Explainable artificial intelligence

Top relations

Important terminology Word statistics

Important terminology

Entity relationships Subject–Predicate–Object triples

Related concept clusters Concept neighborhoods

Connections between topic areas Semantic bridges