LISA: Explaining Recurrent Neural Network Judgments via Layer-wIse Semantic Accumulation and Example to Pattern Transformation.
Pankaj GuptaHinrich SchützePublished in: CoRR (2018)
Keyphrases
- recurrent neural networks
- complex valued
- neural network
- feed forward
- pattern matching
- recurrent networks
- feedforward neural networks
- hidden layer
- reservoir computing
- artificial neural networks
- echo state networks
- pairwise
- semantic network
- intermediate representations
- multi layer
- semantic information
- natural language
- high level
- long short term memory
- semantic similarity
- neural model
- semantic web
- real time
- hebbian learning
- neural network structure
- support vector