EXplainable Neural-Symbolic Learning (X-NeSyL) methodology to fuse deep learning representations with expert knowledge graphs: the MonuMAI cultural heritage use case.
Natalia Díaz RodríguezAlberto LamasJules SanchezGianni FranchiIvan DonadelloSiham TabikDavid FilliatPolicarpo CruzRosana MontesFrancisco HerreraPublished in: CoRR (2021)
Keyphrases
- deep learning
- expert knowledge
- cultural heritage
- unsupervised feature learning
- expert systems
- prior knowledge
- unsupervised learning
- deep belief networks
- learned knowledge
- reinforcement learning
- learning algorithm
- learning process
- fuzzy logic
- domain knowledge
- database
- higher order
- domain specific
- active learning
- computer vision
- learning strategies
- bayesian networks
- training data
- weakly supervised
- artificial intelligence
- restricted boltzmann machine
- genetic algorithm
- deep architectures
- neural network