Explaining Deep Neural Networks
arXiv:2010.01496
Abstract
Deep neural networks are becoming more and more popular due to their revolutionary success in diverse areas, such as computer vision, natural language processing, and speech recognition. However, the decision-making processes of these models are generally not interpretable to users. In various domains, such as healthcare, finance, or law, it is critical to know the reasons behind a decision made by an artificial intelligence system. Therefore, several directions for explaining neural models have recently been explored. In this thesis, I investigate two major directions for explaining deep neural networks. The first direction consists of feature-based post-hoc explanatory methods, that is, methods that aim to explain an already trained and fixed model (post-hoc), and that provide explanations in terms of input features, such as tokens for text and superpixels for images (feature-based). The second direction consists of self-explanatory neural models that generate natural language explanations, that is, models that have a built-in module that generates explanations for the predictions of the model.
arXiv commentPhD Thesis, University of Oxford
References in corpus (27)
- Distributed Representations of Words and Phrases and their Compositionality
- Sequence to Sequence Learning with Neural Networks
- Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
- Axiomatic Attribution for Deep Networks
- Learning Important Features Through Propagating Activation Differences
- Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings
- Understanding Black-box Predictions via Influence Functions
- Learning to Communicate with Deep Multi-Agent Reinforcement Learning
- Skip-Thought Vectors
- Reasoning about Entailment with Neural Attention
- Sanity Checks for Saliency Maps
- Generating Natural Adversarial Examples
- e-SNLI: Natural Language Inference with Natural Language Explanations
- Neural Natural Language Inference Models Enhanced with External Knowledge
- Distilling a Neural Network Into a Soft Decision Tree
- GANSynth: Adversarial Neural Audio Synthesis
- Natural Language Inference over Interaction Space
- The Power of Depth for Feedforward Neural Networks
- Enabling Factorized Piano Music Modeling and Generation with the MAESTRO Dataset
- Model Agnostic Supervised Local Explanations
- A Surprisingly Robust Trick for Winograd Schema Challenge
- Seq2Sick: Evaluating the Robustness of Sequence-to-Sequence Models with Adversarial Examples
- A Game Theoretic Approach to Class-wise Selective Rationalization
- Can I Trust the Explainer? Verifying Post-hoc Explanatory Methods
- Towards a Robust Deep Neural Network in Texts: A Survey
- e-SNLI-VE: Corrected Visual-Textual Entailment with Natural Language Explanations
- Learning Attitudes and Attributes from Multi-Aspect Reviews