INIS
decision tree analysis
100%
constraints
70%
learning
62%
accuracy
36%
machine learning
36%
neural networks
29%
prediction
28%
randomness
28%
vision
23%
metrics
23%
investigations
23%
forests
23%
nonlinear problems
23%
box models
23%
evaluation
23%
surveys
23%
computers
23%
enforcement
23%
datasets
19%
layers
15%
levels
15%
architecture
15%
artificial intelligence
14%
maps
12%
dimensions
11%
proposals
11%
sampling
11%
reduction
11%
mixtures
11%
applications
10%
data
9%
classification
7%
communities
7%
cities
7%
detection
7%
algorithms
7%
global analysis
5%
probabilistic estimation
5%
approximations
5%
distillation
5%
Keyphrases
Evaluation of Explainability
23%
XAI Methods
23%
Global Explanations
23%
Deep Convolutional Neural Network (deep CNN)
23%
Co-learning
23%
SegNet
23%
Knowledge Constraint
23%
Responsible AI
23%
Efficient Prediction
23%
T-distributed Stochastic Neighbor Embedding (t-SNE)
23%
Constraint Enforcement
23%
Fairness Constraints
23%
Decision Tree Forest
23%
Semantic Segmentation
23%
Diverse Families
15%
Gaussian Mixture
11%
Mixture Analysis
11%
Pixel-wise Semantic Segmentation
9%
Decision Tree Model
7%
Continuous Features
7%
One Target
7%
Binary Features
7%
Metric Value
7%
Saliency Map
7%
Explainable Artificial Intelligence
7%
Linear Programming Formulation
7%
Optimal Decision Trees
7%
Introduced Trees
7%
Explanation Fidelity
5%
Black Box Machine Learning
5%
Decision Lists
5%
Rule Learner
5%
Decision Set
5%
Knowledge Distillation
5%
Computer Science
Decision Trees
47%
Fairness Constraint
23%
Image Segmentation
23%
Deep Convolutional Neural Networks
23%
Explainable Artificial Intelligence
23%
Computer Vision
23%
Dimensionality Reduction
23%
Gaussian Mixture
23%
Random Decision Forest
23%
Domain Knowledge
23%
Machine Learning
15%
Unfairness
9%
Evaluation Metric
9%
Convolutional Neural Network
5%
Object Detection
5%
Autonomous Driving
5%
Embedded Systems
5%
Decision Tree Model
5%
Binary Feature
5%
Classification Task
5%
Linear Programming
5%
Deep Learning
5%
Discretization
5%
