René's URL Explorer Experiment


Title: Explainable AI Course

direct link

Domain: interpretable-ml-class.github.io

authorHima Lakkaraju

Links:

this formhttps://forms.gle/s9WniBW6oV9PVBLV6
Webpagehttps://himalakkaraju.github.io/
Twitterhttps://twitter.com/hima_lakkaraju
Webpagehttps://www.jiaqima.com/
Twitterhttps://twitter.com/Jiaqi_Ma_
Webpagehttps://suraj-srinivas.github.io/
Twitterhttps://twitter.com/Suuraj
Towards a Rigorous Science of Interpretable Machine Learninghttps://arxiv.org/abs/1702.08608
Transparency: Motivation and Challengeshttps://arxiv.org/abs/1708.01870
The Mythos of Model Interpretabilityhttps://arxiv.org/abs/1606.03490
Slides 1https://interpretable-ml-class.github.io/slides/Lecture_1.pptx
Slides 2https://interpretable-ml-class.github.io/slides/Lecture_2.pptx
Human Factors in Model Interpretability: Industry Practices, Challengeshttps://arxiv.org/abs/2004.11440
Interpreting Interpretability: Understanding Data Scientists’ Use of Interpretability Tools for Machine Learninghttp://www-personal.umich.edu/~harmank/Papers/CHI2020_Interpretability.pdf
Human Evaluation of Models Built for Interpretabilityhttps://ojs.aaai.org/index.php/HCOMP/article/view/5280/5132
Measuring and Manipulating Model Interpretabilityhttps://arxiv.org/abs/1802.07810
Slides 1https://interpretable-ml-class.github.io/slides/Lecture_3.pdf
Slides 2https://interpretable-ml-class.github.io/slides/Lecture_4.pptx
Interpretable Classifiers Using Rules and Bayesian Analysishttps://arxiv.org/abs/1511.01644
Interpretable Decision Setshttps://www-cs-faculty.stanford.edu/people/jure/pubs/interpretable-kdd16.pdf
Intelligible Models for Healthcarehttp://people.dbmi.columbia.edu/noemie/papers/15kdd.pdf
Deep Learning for Case Based Reasoning Through Prototypeshttps://arxiv.org/abs/1710.04806
Slides 1https://interpretable-ml-class.github.io/slides/Lecture_5.pptx
Slides 2https://interpretable-ml-class.github.io/slides/Lecture_6.pptx
Learning Optimized Risk Scoreshttps://arxiv.org/abs/1610.00168
Why should I trust you? Explaining the Predictions of Any Classifierhttps://arxiv.org/abs/1602.04938
A Unified Approach to Interpreting Modelshttps://papers.nips.cc/paper/7062-a-unified-approach-to-interpreting-model-predictions.pdf
Smoothgrad: Removing noise by adding noisehttps://arxiv.org/abs/1706.03825
Axiomatic Attribution for Deep Networkshttps://arxiv.org/abs/1703.01365
Slides 1https://interpretable-ml-class.github.io/slides/Lecture_7_LIME.pptx
Slides 2https://interpretable-ml-class.github.io/slides/Lecture_7_SHAP.pptx
Slides 3https://interpretable-ml-class.github.io/slides/Lecture_8_SmoothGrad.pptx
Slides 4https://interpretable-ml-class.github.io/slides/Lecture_8_IntegratedGradients.pptx
Learning Important Features through Propagating Activation Differenceshttps://arxiv.org/abs/1704.02685
Fooling LIME and SHAPhttps://arxiv.org/abs/1911.02508
Explanations can be manipulated and geometry is to blamehttps://arxiv.org/abs/1906.07983
Sanity Checks for Saliency Mapshttps://arxiv.org/abs/1810.03292
OpenXAI: Towards a Transparent Evaluation of Model Explanationshttps://arxiv.org/abs/2206.11104
Slides 1https://interpretable-ml-class.github.io/slides/Lecture_9_Fooling_LIME_SHAP.pptx
Slides 2https://interpretable-ml-class.github.io/slides/Lecture_9_Explanations_Manipulated.pptx
Slides 3https://interpretable-ml-class.github.io/slides/Lecture_10_Adebayo_Sanity_Checks.pptx
Slides 4https://interpretable-ml-class.github.io/slides/Lecture_10_Agarwal_OpenXAI.pptx
The Disagreement Problem in Explainable Machine Learninghttps://arxiv.org/abs/2202.01602
Stop Explaining Black Box Modelshttps://arxiv.org/abs/1811.10154
What Makes a Good Explanation? A Harmonized View of Properties of Explanationshttps://arxiv.org/abs/2211.05667
Use-Case-Grounded Simulations for Explanation Evaluationhttps://arxiv.org/abs/2206.02256
Counterfactual Explanations Without Opening the Black Boxhttps://arxiv.org/abs/1711.00399
Algorithmic Recourse: From Counterfactual Explanations to Interventionshttps://arxiv.org/abs/2002.06278
Towards Robust and Reliable Algorithmic Recoursehttps://arxiv.org/abs/2102.13620
Probabilistically Robust Recourse: Navigating the Trade-offs between Costs and Robustness in Algorithmic Recoursehttps://arxiv.org/abs/2203.06768
Slides 1https://interpretable-ml-class.github.io/slides/Lecture_11_Wachter_Algorithmic_Recourse.pptx
Slides 2https://interpretable-ml-class.github.io/slides/Lecture_11_Karimi_Causal_Recourse.pptx
Slides 3https://interpretable-ml-class.github.io/slides/Lecture_12_ROAR.pptx
Slides 4https://interpretable-ml-class.github.io/slides/Lecture_12_PROBE.pptx
Learning Model-Agnostic Counterfactual Explanations for Tabular Datahttps://arxiv.org/abs/1910.09398
Beyond Individualized Recourse: Interpretable and Interactive Summaries of Actionable Recourseshttps://arxiv.org/abs/2009.07165
Actionable Recourse in Linear Classificationhttps://arxiv.org/abs/1809.06514
Explainable Prediction of Medical Codes from Clinical Texthttps://www.aclweb.org/anthology/N18-1100.pdf
Attention is not Explanationhttps://arxiv.org/abs/1902.10186
Network Dissection: Quantifying Interpretability of Deep Visual Representationshttp://netdissect.csail.mit.edu/final-network-dissection.pdf
Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectorshttps://arxiv.org/abs/1711.11279
Slides 1https://interpretable-ml-class.github.io/slides/Lecture_13_Convolutional_Attention.pptx
Slides 2https://interpretable-ml-class.github.io/slides/Lecture_13_Attention_Not_Explanation.pptx
Slides 3https://interpretable-ml-class.github.io/slides/Lecture_14_Network_Dissection.pdf
Slides 4https://interpretable-ml-class.github.io/slides/Lecture_14_TCAV.pptx
Understanding Black Box Predictions via Influence Functionshttps://arxiv.org/abs/1703.04730
What is your data worth? Equitable Valuation of Datahttps://arxiv.org/abs/1904.02868
Explainable Active Learning (XAL): Toward AI Explanations as Interfaces for Machine Teachershttps://arxiv.org/abs/2001.09219
TalkToModel: Explaining Machine Learning Models with Interactive Natural Language Conversationshttps://arxiv.org/abs/2207.04154
Slides 1https://interpretable-ml-class.github.io/slides/Lecture_15_Influence_Function.pptx
Slides 2https://interpretable-ml-class.github.io/slides/Lecture_15_DataShapley.pdf
Slides 3https://interpretable-ml-class.github.io/slides/Lecture_16_XAL.pptx
Slides 4https://interpretable-ml-class.github.io/slides/Lecture_16_Talk_to_Model.pptx
Explaining by Removing: A Unified Framework for Model Explanationhttps://www.jmlr.org/papers/volume22/20-1316/20-1316.pdf
Which Explanation Should I Choose? A Function Approximation Perspective to Characterizing Post hoc Explanationshttps://arxiv.org/abs/2206.01254
Interpreting the Latent Space of GANs for Semantic Face Editinghttps://arxiv.org/abs/1907.10786
GANSpace: Discovering Interpretable GAN Controlshttps://arxiv.org/abs/2004.02546
Slides 1https://interpretable-ml-class.github.io/slides/Lecture_17_Explaining_by_Removing.pptx
Slides 2https://interpretable-ml-class.github.io/slides/Lecture_17_LFA.pdf
Slides 3https://interpretable-ml-class.github.io/slides/Lecture_18_GANSpace.pdf
Slides 4https://interpretable-ml-class.github.io/slides/Lecture_18_Latent_Space_GAN.pdf
A Learning Theoretic Perspective on Local Explainabilityhttps://arxiv.org/abs/2011.01205
Do Input Gradients Highlight Discriminative Features?https://arxiv.org/abs/2102.12781
On the Privacy Risks of Algorithmic Recoursehttps://arxiv.org/abs/2211.05427
Explainability for Fair Machine Learninghttps://arxiv.org/abs/2010.07389
Towards Bridging the Gaps between the Right to Explanation and the Right to be Forgottenhttps://arxiv.org/abs/2302.04288
Slides 1https://interpretable-ml-class.github.io/slides/Lecture_19_DiffROAR.pptx
Slides 2https://interpretable-ml-class.github.io/slides/Lecture_19_Privacy_Risk.pdf
Slides 3https://interpretable-ml-class.github.io/slides/Lecture_20_Explainability_Fair_ML.pdf
Slides 4https://interpretable-ml-class.github.io/slides/Lecture_20_ROCERF.pdf
Fairness via Explanation Quality: Evaluating Disparities in the Quality of Post hoc Explanationshttps://arxiv.org/abs/2011.01205
An Introduction to Circuitshttps://distill.pub/2020/circuits/zoom-in/
Mechanistic Interpretability, Variables, and the Importance of Interpretable Baseshttps://transformer-circuits.pub/2022/mech-interp-essay/index.html
Tracr: Compiled Transformers as a Laboratory for Interpretabilityhttps://arxiv.org/abs/2301.05062
Slides 1https://interpretable-ml-class.github.io/slides/Lecture_21_Mechanistic_Interpretability.pptx
Slides 2https://interpretable-ml-class.github.io/slides/Lecture_22_Tracr.pdf
Chain of Thought Prompting Elicits Reasoning in Large Language Modelshttps://arxiv.org/abs/2201.11903
Can language models learn from explanations in context?https://arxiv.org/abs/2204.02329
Explain Yourself! Leveraging Language Models for Common Sense Reasoninghttps://arxiv.org/abs/1906.02361
Interpreting Language Models with Contrastive Explanationshttps://arxiv.org/abs/2202.10419
Slides 1https://interpretable-ml-class.github.io/slides/Lecture_23_CoT.pdf
Slides 2https://interpretable-ml-class.github.io/slides/Lecture_23_Explanations_In_Context.pptx
Slides 3https://interpretable-ml-class.github.io/slides/Lecture_24_Explain_Yourself.pptx
Slides 4https://interpretable-ml-class.github.io/slides/Lecture_24_Contrastive_Explanation.pdf
Language Models can Explain Neurons in Language Modelshttps://openaipublic.blob.core.windows.net/neuron-explainer/paper/index.html
Acquisition of Chess Knowledge in Alpha Zerohttps://arxiv.org/abs/2111.09259
What the DAAM: Interpreting Stable Diffusion Using Cross Attentionhttps://arxiv.org/abs/2210.04885
DALL-EVAL: Probing the Reasoning Skills and Social Biases of Text-to-Image Generative Modelshttps://arxiv.org/abs/2202.04053
Slides 1https://interpretable-ml-class.github.io/slides/Lecture_25_AlphaZero.pptx
Slides 2https://interpretable-ml-class.github.io/slides/Lecture_25_DAAM.pptx
Slides 3https://interpretable-ml-class.github.io/slides/Lecture_26_DALL_EVAL.pptx

Viewport: width=device-width, initial-scale=1.0

URLs of crawlers that visited me.