WeAreDevelopers Logo WeAreDevelopers
Sign in
For You LIVE
WeAreDevelopers LIVE • Jun 1, 2023

Explainable machine learning explained

Karol Przystalski

A famous AI classified wolves based purely on snowy backgrounds. Learn how explainable AI tools like SHAP and LIME expose dangerous data leakage and make black-box models transparent.

Pause
Mute Enter Fullscreen
#1 about 3 min

History and growth of explainable artificial intelligence

The evolution of machine learning models creates a pressing need to understand how predictions are made.

#2 about 4 min

Need for explainability in regulated healthcare and finance

Regulated industries like healthcare and finance require transparent predictions before releasing software or hardware products.

#3 about 4 min

Core terminology and audiences for interpretable artificial intelligence

Understanding different terms like responsible artificial intelligence clarifies the unique needs of domain experts and regulatory agencies.

#4 about 3 min

Choosing the right method to explain machine learning models

Visual explanations, simplified logic, and feature relevance provide more practical insights than complex mathematical equations.

#5 about 2 min

Classifying skin cancer using visual feature importance

Identifying specific visual patterns like asymmetry and dots helps explain tumor classification to medical professionals.

#6 about 5 min

Analyzing catastrophic model failures through husky and wolf classifications

Models relying on background noise instead of actual entity features lead to severe errors and adversarial vulnerabilities.

#7 about 6 min

Differentiating white box models like simple decision trees

White box algorithms like linear regression and decision trees offer direct interpretability through clear boundaries and logic rules.

#8 about 4 min

Debugging models through data-centric feature engineering approaches

Improving dataset quality and analyzing functional features directly mitigates overfitting and prevents unintended data leakage.

#9 about 3 min

Enhancing model accuracy using text features in the Titanic dataset

Generating new tokens from text columns marginally increases predictive accuracy without acquiring external datasets.

#10 about 5 min

Visualizing boundaries in support vector machines and clustering methods

Plotting higher-dimensional boundaries clarifies how complex mathematical clustering and support vector machines arrive at predictions.

#11 about 5 min

Applying formal explainability methods like lime and shap

Game theory-based evaluation methods pinpoint the specific impact individual variables or image pixels have on predictions.

#12 about 3 min

Generating heatmaps for deep learning layers using class activation maps

Extracting feature influence across millions of parameters highlights exactly which image sections trigger specific neural classifications.

#13 about 4 min

Defending machine learning against adversarial image and pixel attacks

Minor adversarial noise or single altered pixels can severely disrupt target classifications in otherwise stable neural networks.

#14 about 4 min

Predicting the impact of quantum computing on artificial intelligence

The advent of commercial quantum computers will drastically accelerate artificial intelligence development beyond current classical limits.

#15 about 4 min

Applying machine learning to complex medical imaging processes

Combining video analysis with continuous biometrics yields advanced insights into cardiac vessel performance and operational health.

#16 about 5 min

Establishing ethical foundations and text watermarking strategies

Creating responsible generation systems requires strict governance and verifiable text watermarking to mitigate long-term industry risks.

Matching moments

2:32 min

Building user trust and finding insights via explainable AI

Bernhard Bernhard +1 · WWC 2025

3:40 min

Ensuring robustness and explainability in machine learning

Jan Zawadzki · LIVE

1:34 min

Justifying AI decisions to employees and end customers

Kilian Kluge +1 · WWC 2022

2:42 min

Mitigating data bias and explaining AI decisions

Werner Vogels Werner Vogels +1 · WWC Europe 2026

1:17 min

Educating users and business teams on AI complexities

Björn Bringmann Björn Bringmann +3 · WWC 2024

17:05 min

Navigating data privacy boundaries and adversarial model reliability

Alexandra Waldherr · LIVE

More from WeAreDevelopers LIVE

Aliens in Quarantine, Python Deprecates Loops, and AI Buys Old Books - Zbyszek Tenerowicz thumbnail
5:43
5 days ago

Aliens in Quarantine, Python Deprecates Loops, and AI Buys Old Books - Zbyszek Tenerowicz

Chris Heilmann, Daniel Cranney

WeAreDevelopers LIVE - Node and Package Security thumbnail
1:08:30
5 days ago

WeAreDevelopers LIVE - Node and Package Security

Chris Heilmann, Daniel Cranney, Zbyszek Tenerowicz

WeAreDevelopers LIVE - Streaming HTML thumbnail
1:10:26
12 days ago

WeAreDevelopers LIVE - Streaming HTML

Chris Heilmann, Daniel Cranney, Jad Joubran

WeAreDevelopers LIVE - CODE100 at WeAreDevelopers Europe thumbnail
1:02:34
19 days ago

WeAreDevelopers LIVE - CODE100 at WeAreDevelopers Europe

Chris Heilmann, Daniel Cranney, Justin Halsall, Werner Jeschko, Nicole Jeschko, Mirco Tomić

WeAreDevelopers LIVE - Web Performance in an AI World thumbnail
1:07:59
26 days ago

WeAreDevelopers LIVE - Web Performance in an AI World

Chris Heilmann, Daniel Cranney

FIFA Hack, Midjourney Does Ultrasounds, and Trampoline Traffic Lights - Nicole Jeschko and Werner Jeschko thumbnail
5:55
about 2 months ago

FIFA Hack, Midjourney Does Ultrasounds, and Trampoline Traffic Lights - Nicole Jeschko and Werner Jeschko

Chris Heilmann, Daniel Cranney

Upcoming sessions on this topic

Open session

World Congress 2026 North America

AI Decision Observability: Enabling Transparency and Trust in Intelligent Systems

Amjad Shaikh, Soumil Mandal

Amjad Shaikh
Soumil Mandal
Open session

World Congress 2026 North America

You Can’t Re-Run Sunlight: Designing ML Data Architectures for Physical AI

An Phan

Senior Data Infrastructure Engineer @ Hippo Harvest

An Phan
Open session

World Congress 2026 North America

Closing the Visibility Gap: Lessons from Safety Critical Agentic Systems

Vivek Pandit

Principal Engineer at Cadence

Vivek Pandit
Open session

World Congress 2026 North America

Evals Are Infra: Building AI Systems Developers Can Actually Trust

Phoebe Wang

Member of Technical Staff at OpenAI

Phoebe Wang
Open session

World Congress 2026 North America

The Things Your AI Isn't Telling You

Desmond Lamptey

Lead Software Engineer @ Capital One

Desmond Lamptey
Open session

World Congress 2026 North America

Making Science Larger, not just Faster

Yuval Dvir

Commercial Executive, SandboxAQ

Yuval Dvir

Related videos

Model Governance and Explainable AI as tools for legal compliance and risk management thumbnail
29:30
WWC 2022 • about 4 years ago

Model Governance and Explainable AI as tools for legal compliance and risk management

Kilian Kluge, Isabel Bär

Confuse, Obfuscate, Disrupt: Using Adversarial Techniques for Better AI and True Anonymity thumbnail
27:34
WWC 2025 • 12 months ago

Confuse, Obfuscate, Disrupt: Using Adversarial Techniques for Better AI and True Anonymity

David vonThenen

Solving the puzzle: Leveraging machine learning for effective root cause analysis thumbnail
24:31
WWC 2025 • 12 months ago

Solving the puzzle: Leveraging machine learning for effective root cause analysis

Bernhard, Varsha Venugopal

Getting Started with Machine Learning thumbnail
44:11
LIVE • almost 5 years ago

Getting Started with Machine Learning

Alexandra Waldherr

AI in High-Stakes Industries: Lessons Learned thumbnail
31:27
WWC Europe 2026 • about 1 month ago

AI in High-Stakes Industries: Lessons Learned

Alexandre Guenoun, Jaipal Singh, Nicolò Robba, Tomislav Tipurić

A hundred ways to wreck your AI - the (in)security of machine learning systems thumbnail
24:23
WWC 2023 • almost 3 years ago

A hundred ways to wreck your AI - the (in)security of machine learning systems

Balázs Kiss

Related articles

From learning to earning

Jobs that call for the skills explored in this talk.