A Survey on Understanding, Visualizations, and Explanation of Deep Neural Networks
arXiv:2102.01792
Abstract
Recent advancements in machine learning and signal processing domains have resulted in an extensive surge of interest in Deep Neural Networks (DNNs) due to their unprecedented performance and high accuracy for different and challenging problems of significant engineering importance. However, when such deep learning architectures are utilized for making critical decisions such as the ones that involve human lives (e.g., in control systems and medical applications), it is of paramount importance to understand, trust, and in one word "explain" the argument behind deep models' decisions. In many applications, artificial neural networks (including DNNs) are considered as black-box systems, which do not provide sufficient clue on their internal processing actions. Although some recent efforts have been initiated to explain the behaviors and decisions of deep networks, explainable artificial intelligence (XAI) domain, which aims at reasoning about the behavior and decisions of DNNs, is still in its infancy. The aim of this paper is to provide a comprehensive overview on Understanding, Visualization, and Explanation of the internal and overall behavior of DNNs.
References in corpus (29)
- Sequence to Sequence Learning with Neural Networks
- LSTM: A Search Space Odyssey
- How transferable are features in deep neural networks?
- Brain Tumor Segmentation with Deep Neural Networks
- End to End Learning for Self-Driving Cars
- Instance Normalization: The Missing Ingredient for Fast Stylization
- Methods for Interpreting and Understanding Deep Neural Networks
- Understanding Neural Networks Through Deep Visualization
- Explaining NonLinear Classification Decisions with Deep Taylor Decomposition
- Character-Aware Neural Language Models
- Visualizing and Understanding Recurrent Networks
- SmoothGrad: removing noise by adding noise
- A Learned Representation For Artistic Style
- How to Explain Individual Classification Decisions
- Texture Networks: Feed-forward Synthesis of Textures and Stylized Images
- Visualizing Deep Convolutional Neural Networks Using Natural Pre-Images
- Semi-supervised Sequence Learning
- Understanding Neural Networks through Representation Erasure
- Visualizing Deep Neural Network Decisions: Prediction Difference Analysis
- Human Activity Recognition using Recurrent Neural Networks
- Visualizing and Understanding Neural Models in NLP
- Multifaceted Feature Visualization: Uncovering the Different Types of Features Learned By Each Neuron in Deep Neural Networks
- Gradients of Counterfactuals
- Representer Point Selection for Explaining Deep Neural Networks
- Explaining Deep Learning Models - A Bayesian Non-parametric Approach
- Interpreting CNNs via Decision Trees
- Understanding Hidden Memories of Recurrent Neural Networks
- Interpretable Convolutional Neural Networks
- Interpretable Convolutional Neural Networks via Feedforward Design