Research Connect

TL;DR

This book compiles leading research on the development of explainable and interpretable machine learning methods in the context of computer vision and machine learning.

Abstract

Authors

Hugo Jair Escalante

1 Paper

Sergio Escalera

1 Paper

Isabelle M Guyon

1 Paper

Xavier Baró

1 Paper

Yağmur Güçlütürk

1 Paper

Umut Güçlü

1 Paper

M. Gerven

1 Paper

TL;DR

Abstract

Authors

References432 items

Deep Residual Learning for Image Recognition

Adam: A Method for Stochastic Optimization

Mastering the game of Go with deep neural networks and tree search

ImageNet classification with deep convolutional neural networks

Pattern Recognition and Machine Learning

A Density-Based Algorithm for Discovering Clusters in Large Spatial Databases with Noise

Representation Learning: A Review and New Perspectives

Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation

Auto-Encoding Variational Bayes

GENERATIVE ADVERSARIAL NETS

Reinforcement Learning: An Introduction

A unified architecture for natural language processing: deep neural networks with multitask learning

Long Short-Term Memory

Multiple Classifier Systems

Gender Shades: Intersectional Accuracy Disparities in Commercial Gender Classification

Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings

Fairness through awareness

Causal Inference in the Presence of Latent Variables and Selection Bias

Network Dissection: Quantifying Interpretability of Deep Visual Representations

Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization

European Union Regulations on Algorithmic Decision-Making and a "Right to Explanation"

Learning Deep Features for Discriminative Localization

Becoming the expert - interactive multi-class machine teaching

Visualizing and Understanding Convolutional Networks

Methods for interpreting and understanding deep neural networks

Quantum-chemical insights from deep tensor neural networks

Finding Density Functionals with Machine Learning

Approximation by superpositions of a sigmoidal function

Dropout: a simple way to prevent neural networks from overfitting

Author ' s personal copy A Fast Quartet tree heuristic for hierarchical clustering

“Why Should I Trust You?”: Explaining the Predictions of Any Classifier

Explaining and Harnessing Adversarial Examples

Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations

Very Deep Convolutional Networks for Large-Scale Image Recognition

Understanding the difficulty of training deep feedforward neural networks

Histograms of oriented gradients for human detection

Fully convolutional networks for semantic segmentation

Conditional Generative Adversarial Nets

Distinctive Image Features from Scale-Invariant Keypoints

Learning Important Features Through Propagating Activation Differences

Evaluating the Visualization of What a Deep Neural Network Has Learned

Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps

Towards End-To-End Speech Recognition with Recurrent Neural Networks

Supervising Neural Attention Models for Video Captioning by Human Gaze Data

Human Attention in Visual Question Answering: Do Humans and Deep Networks look at the same regions?

Hierarchical Question-Image Co-Attention for Visual Question Answering

Action Recognition using Visual Attention

Show, Attend and Tell: Neural Image Caption Generation with Visual Attention

Bleu: a Method for Automatic Evaluation of Machine Translation

Learning Deep Representations of Fine-Grained Visual Descriptions

Compact Bilinear Pooling

The Caltech-UCSD Birds-200-2011 Dataset

On the Number of Linear Regions of Deep Neural Networks

Learning long-term dependencies with gradient descent is difficult

Explain Images with Multimodal Recurrent Neural Networks

Self-Critical Sequence Training for Image Captioning

Sequence Level Training with Recurrent Neural Networks

CIDEr: Consensus-based image description evaluation

Challenges in representation learning: A report on three machine learning contests

Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence Multi-Label Classification Using Conditional Dependency Networks

Dataset Shift in Machine Learning

Interpretable Learning for Self-Driving Cars by Visualizing Causal Attention

ALVINN, an autonomous land vehicle in a neural network

VQA: Visual Question Answering

Facial action coding system: a technique for the measurement of facial movement

On the importance of initialization and momentum in deep learning

On the difficulty of training recurrent neural networks

Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups

Comprehensible classification models: a position paper

Explanation and Justification in Machine Learning : A Survey Or

Semantics derived automatically from language corpora contain human-like biases

Classifier chains for multi-label classification

Discriminative Methods for Multi-labeled Classification

Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms

Right for the Right Reasons: Training Differentiable Models by Constraining their Explanations

Neural Module Networks