Media Summary: MIT 6.S897 Machine Learning for Healthcare, Spring 2019 Instructor: Peter Szolovits View the complete course: ... How can we reverse engineer what a neural network is doing? In this IASEAI '25 session, An Introduction to Mechanistic ... What's happening inside an AI model as it thinks? Why are AI models sycophantic, and why do they hallucinate? Are AI models ...

Medai 34 Optimizing For Interpretability - Detailed Analysis & Overview

MIT 6.S897 Machine Learning for Healthcare, Spring 2019 Instructor: Peter Szolovits View the complete course: ... How can we reverse engineer what a neural network is doing? In this IASEAI '25 session, An Introduction to Mechanistic ... What's happening inside an AI model as it thinks? Why are AI models sycophantic, and why do they hallucinate? Are AI models ... More explainability techniques (anchors, counterfactuals, prototypes, influential instances) but also discussions on gaming ... Title: Benchmarking saliency methods for chest X-ray interpretation Speaker: Adriel Saporta Abstract: Saliency methods, which ... Title: Reveal to Revise: How to Uncover and Correct Biases of Deep Models in Medical Applications Speaker: Maximilian Dreyer ...

This video discusses case based reasoning with neural networks and neural disentanglement. Presented by Cynthia Rudin. Abstract: With widespread use of machine learning, there have been serious societal consequences ... Is it possible to reverse-engineer a trained neural network? Why might it be useful to do so? This talk gives an overview of both the ... Machine Learning Performance is the key to building accurate, efficient, and reliable AI systems. In this video, you'll learn proven ... Six Sigma's DMAIC methodology has helped organizations solve complex problems for decades—but what if Artificial Intelligence ... Jascha Sohl-Dickstein (Google Brain) Frontiers of Deep Learning.

Photo Gallery

MedAI #34: Optimizing for Interpretability in Deep Neural Networks | Mike Wu
25. Interpretability
An Introduction to Mechanistic Interpretability – Neel Nanda | IASEAI 2025
Interpretability: Understanding how AI models think
SE4AI: Explainability and Interpretability (Part 2)
MedAI #63: Benchmarking saliency methods for chest X-ray interpretation | Adriel Saporta
MedAI #104: Reveal to Revise - How to Uncover and Correct Biases of Deep Models | Maximilian Dreyer
Interpretable Neural Networks for Computer Vision: Clinical Decisions that are Aided, not Automated
NC ASA Webinar: Interpretability versus Explainability in Machine Learning for High Stakes Decisions
⚡Interpreting Neural Networks - Avi S
Strategic Diagnostics to Improve ML Performance
Accelerating Continuous Improvement with AI-Powered DMAIC
View Detailed Profile
MedAI #34: Optimizing for Interpretability in Deep Neural Networks | Mike Wu

MedAI #34: Optimizing for Interpretability in Deep Neural Networks | Mike Wu

Title:

25. Interpretability

25. Interpretability

MIT 6.S897 Machine Learning for Healthcare, Spring 2019 Instructor: Peter Szolovits View the complete course: ...

An Introduction to Mechanistic Interpretability – Neel Nanda | IASEAI 2025

An Introduction to Mechanistic Interpretability – Neel Nanda | IASEAI 2025

How can we reverse engineer what a neural network is doing? In this IASEAI '25 session, An Introduction to Mechanistic ...

Interpretability: Understanding how AI models think

Interpretability: Understanding how AI models think

What's happening inside an AI model as it thinks? Why are AI models sycophantic, and why do they hallucinate? Are AI models ...

SE4AI: Explainability and Interpretability (Part 2)

SE4AI: Explainability and Interpretability (Part 2)

More explainability techniques (anchors, counterfactuals, prototypes, influential instances) but also discussions on gaming ...

MedAI #63: Benchmarking saliency methods for chest X-ray interpretation | Adriel Saporta

MedAI #63: Benchmarking saliency methods for chest X-ray interpretation | Adriel Saporta

Title: Benchmarking saliency methods for chest X-ray interpretation Speaker: Adriel Saporta Abstract: Saliency methods, which ...

MedAI #104: Reveal to Revise - How to Uncover and Correct Biases of Deep Models | Maximilian Dreyer

MedAI #104: Reveal to Revise - How to Uncover and Correct Biases of Deep Models | Maximilian Dreyer

Title: Reveal to Revise: How to Uncover and Correct Biases of Deep Models in Medical Applications Speaker: Maximilian Dreyer ...

Interpretable Neural Networks for Computer Vision: Clinical Decisions that are Aided, not Automated

Interpretable Neural Networks for Computer Vision: Clinical Decisions that are Aided, not Automated

This video discusses case based reasoning with neural networks and neural disentanglement.

NC ASA Webinar: Interpretability versus Explainability in Machine Learning for High Stakes Decisions

NC ASA Webinar: Interpretability versus Explainability in Machine Learning for High Stakes Decisions

Presented by Cynthia Rudin. Abstract: With widespread use of machine learning, there have been serious societal consequences ...

⚡Interpreting Neural Networks - Avi S

⚡Interpreting Neural Networks - Avi S

Is it possible to reverse-engineer a trained neural network? Why might it be useful to do so? This talk gives an overview of both the ...

Strategic Diagnostics to Improve ML Performance

Strategic Diagnostics to Improve ML Performance

Machine Learning Performance is the key to building accurate, efficient, and reliable AI systems. In this video, you'll learn proven ...

Accelerating Continuous Improvement with AI-Powered DMAIC

Accelerating Continuous Improvement with AI-Powered DMAIC

Six Sigma's DMAIC methodology has helped organizations solve complex problems for decades—but what if Artificial Intelligence ...

Meta-learning of Optimizers and Update Rules

Meta-learning of Optimizers and Update Rules

Jascha Sohl-Dickstein (Google Brain) https://simons.berkeley.edu/talks/tbd-60 Frontiers of Deep Learning.