Interpretable Machine Learning
188 papers with code • 1 benchmarks • 4 datasets
The goal of Interpretable Machine Learning is to allow oversight and understanding of machine-learned decisions. Much of the work in Interpretable Machine Learning has come in the form of devising methods to better explain the predictions of machine learning models.
Source: Assessing the Local Interpretability of Machine Learning Models
Benchmarks
These leaderboards are used to track progress in Interpretable Machine Learning
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
Libraries
Use these libraries to find Interpretable Machine Learning models and implementations
CUB-200-2011
Morph Call
Controversial News Topic Datasets
SkinCon
Most implemented papers
Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization
For captioning and VQA, we show that even non-attention based models can localize inputs.
Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting
google-research/google-research
•
•
Multi-horizon forecasting problems often contain a complex mix of inputs -- including static (i. e. time-invariant) covariates, known future inputs, and other exogenous time series that are only observed historically -- without any prior information on how they interact with the target.
Axiomatic Attribution for Deep Networks
ankurtaly/Attributions
•
•
ICML 2017
We study the problem of attributing the prediction of a deep network to its input features, a problem previously studied by several other works.
"Why Should I Trust You?": Explaining the Predictions of Any Classifier
Despite widespread adoption, machine learning models remain mostly black boxes.
SmoothGrad: removing noise by adding noise
Explaining the output of a deep network remains a challenge.
A Unified Approach to Interpreting Model Predictions
slundberg/shap
•
•
NeurIPS 2017
Understanding why a model makes a certain prediction can be as crucial as the prediction's accuracy in many applications.
Learning Important Features Through Propagating Activation Differences
Here we present DeepLIFT (Deep Learning Important FeaTures), a method for decomposing the output prediction of a neural network on a specific input by backpropagating the contributions of all neurons in the network to every feature of the input.
RISE: Randomized Input Sampling for Explanation of Black-box Models
eclique/RISE
•
•
We compare our approach to state-of-the-art importance extraction methods using both an automatic deletion/insertion metric and a pointing metric based on human-annotated object segments.
BreastScreening: On the Use of Multi-Modality in Medical Imaging Diagnosis
This paper describes the field research, design and comparative deployment of a multimodal medical imaging user interface for breast screening.
Understanding Neural Networks Through Deep Visualization
yosinski/deep-visualization-toolbox
•
•
The first is a tool that visualizes the activations produced on each layer of a trained convnet as it processes an image or video (e. g. a live webcam stream).
