Interpretability Techniques for Deep Learning
11 papers with code • 1 benchmarks • 1 datasets
CausalGym
Most implemented papers
What Do Compressed Deep Neural Networks Forget?
google-research/google-research
•
•
However, this measure of performance conceals significant differences in how different classes and images are impacted by model compression techniques.
Exploration of Interpretability Techniques for Deep COVID-19 Classification using Chest X-ray Images
The outbreak of COVID-19 has shocked the entire world with its fairly rapid spread and has challenged different sectors.
Contextual Explanation Networks
Our results on image and text classification and survival analysis tasks demonstrate that CENs are not only competitive with the state-of-the-art methods but also offer additional insights behind each prediction, that can be valuable for decision support.
DeepNNK: Explaining deep models and their generalization using polytope interpolation
STAC-USC/DeepNNK_polytope_interpolation
•
•
Modern machine learning systems based on neural networks have shown great success in learning complex data patterns while being able to make good predictions on unseen data points.
DISSECT: Disentangled Simultaneous Explanations via Concept Traversals
asmadotgh/dissect
•
•
ICLR 2022
Explaining deep learning model inferences is a promising venue for scientific understanding, improving safety, uncovering hidden biases, evaluating fairness, and beyond, as argued by many scholars.
A Semi-supervised Deep Transfer Learning Approach for Rolling-Element Bearing Remaining Useful Life Prediction
Deep learning techniques have recently brought many improvements in the field of neural network training, especially for prognosis and health management.
A Novel Deep Learning Model for Hotel Demand and Revenue Prediction amid COVID-19
To this end, it is essential to develop an interpretable forecast model that supports managerial and organizational decision-making.
Learning the Dynamics of Physical Systems from Sparse Observations with Finite Element Networks
martenlienen/finite-element-networks
•
•
ICLR 2022
We propose a new method for spatio-temporal forecasting on arbitrarily distributed points.
Less is More: Fewer Interpretable Region via Submodular Subset Selection
ruoyuchen10/smdl-attribution
•
•
For incorrectly predicted samples, our method achieves gains of 81. 0% and 18. 4% compared to the HSIC-Attribution algorithm in the average highest confidence and Insertion score respectively.
CausalGym: Benchmarking causal interpretability methods on linguistic tasks
Language models (LMs) have proven to be powerful tools for psycholinguistic research, but most prior work has focused on purely behavioural measures (e. g., surprisal comparisons).
