AI/ML Cross-cutting challenges: Ethics, Explainability (XAI), Safety, Accountability, SDG (Green AI)
Collection by Thomas Telandro
medium.com
How to Measure Dataset Similarity
~15 min read · Jun 16th · Understanding the impact of drift on ML models though measures of dataset similarities.
Reader View · Shared by 5, including Thomas Telandro
twitter.com
JavaScript is not available.
Jun 14th · We’ve detected that JavaScript is disabled in this browser. Please enable JavaScript or switch to a supported browser to continue using twitter.com. You can see a list of supported browsers in our…
Shared by 5, including Thomas Telandro
pub.towardsai.net
Trends in AI — May 2022
~19 min read · Jun 1st · A monthly selection of news and research papers: open-source DALLE·2, Meta openly shares a 175B GPT-3 clone, Video Diffusion Models…
Reader View · Shared by 9, including Thomas Telandro
AI Papers
Planting Undetectable Backdoors in Machine Learning Models
1 min read · Apr 18th · Given the computational cost and technical expertise required to train machine learning models, users may delegate the task of learning to a service provider. We show how a malicious learner can plant…
Reader View · Shared by 35, including Dr. Marigo Raftopoulos, Derek Lowe, Cory Doctorow, Tactical Tech, Gary Marcus 🇺🇦, AIKing.Eth - Vincent Boucher, Oliver Raduner, Thomas Telandro, tante
AI Papers
The Carbon Footprint of Machine Learning Training Will Plateau, Then Shrink
1 min read · Jun 2nd · Machine Learning (ML) workloads have rapidly grown in importance, but raised concerns about their carbon footprint. Four best practices can reduce ML training energy by up to 100x and CO2 emissions up…
Shared by 8, including Yann LeCun, Thomas Telandro
blog.google
Improving skin tone representation across Google
5 min read · May 11th · We're introducing a next step in our commitment to image equity and improving representation across our products.
Reader View · Shared by 13, including Tibor Martini 🇺🇦, Bernardo van Olst, Thomas Telandro
pair-code.github.io
What-If Tool
5 min read · From 2018 · Building effective machine learning systems means asking a lot of questions. It's not enough to train a model and walk away. Instead, good practitioners act as detectives, probing to understand their…
Reader View · Shared by 10, including Thomas Telandro, Mara Averick
github.com
uber/manifold: A model-agnostic visual debugging tool for machine learning
2021-08-23 · A model-agnostic visual debugging tool for machine learning - GitHub - uber/manifold: A model-agnostic visual debugging tool for machine learning
Shared by 9, including Thomas Telandro, Nico Müller 🇺🇦
github.com
cleverhans-lab/cleverhans
2021-05-21 · An adversarial example library for constructing attacks, building defenses, and benchmarking both - cleverhans-lab/cleverhans
Shared by 8, including Thomas Telandro, Nico Müller 🇺🇦
github.com
marcotcr/checklist
2020-10-10 · Beyond Accuracy: Behavioral Testing of NLP models with CheckList - marcotcr/checklist
Shared by 10, including Thomas Telandro, Nico Müller 🇺🇦
debug-ml-iclr2019.github.io
Overview
5 min read · Apr 25th · [“ICLR 2019 workshop, May 6, 2019, New Orleans”, “9.50am - 6.30pm, Room R03”]
Reader View · Shared by 5, including Thomas Telandro
O'Reilly Media
Machine Learning for High-Risk Applications
1 min read · Apr 22nd · Chapter 1. Contemporary Model Governance A Note for Early Release Readers With Early Release ebooks, you get books in their earliest form—the author’s raw and unedited content as they write—so … -…
Reader View · Shared by 5, including Thomas Telandro
github.com
awesome-machine-learning-interpretability/README.md at master
From 2019 · A curated list of awesome machine learning interpretability resources. - jphall663/awesome-machine-learning-interpretability
Shared by 8, including Cameron Yick, Thomas Telandro
github.com
jphall663/awesome-machine-learning-interpretability
From 2019 · A curated list of awesome machine learning interpretability resources. - jphall663/awesome-machine-learning-interpretability
Shared by 20, including Grégoire Japiot 🌻, Nico Müller 🇺🇦, Jose Luis Calvo, Thomas Telandro, Cameron Yick
github.com
daviddao/awful-ai
From 2018 · awful-ai - Awful AI is a curated list to track current scary usages of AI - hoping to raise awareness
Shared by 32, including Thomas Telandro, Josep M. Ganyet, Vikram Dutt, Moritz Klack
romanlutz.github.io
Learning from the past to create Responsible AI
1 min read · From 2020 · A collection of at least controversial, and often unethical use cases
Shared by 15, including Gengo 🦁, John C. Havens (he/him), AIKing.Eth - Vincent Boucher, Thomas Telandro
