technique

interpretable machine learning

techniqueactiveinterpretable-machine-learning-231ca23a·1 events·first seen 28d ago

Aliases: interpretable machine learning

Co-occurring entities

More like this (12)

automated mechanistic interpretability interpretability neural network interpretability mechanistic interpretability Thinking Machines Interaction Model Machine Translation (MT)machine teaching Anatomy of Post-Training: Using Interpretability to Characterize Data and Shape the Learning Signal Structured Interactive Learning Thinking Machines meta-learning OpenML

Recent events (1)

3Openai Blog·28d ago·source ↗

Interpretable Machine Learning Through Teaching

OpenAI published a method in 2018 that trains AI systems to teach each other using examples that are also interpretable to humans. The approach automatically selects maximally informative examples to convey a concept, such as representative images for a category like 'dogs'. Experiments showed the method effective at teaching both AI systems and humans, bridging machine learning interpretability with pedagogical example selection.

AI Safety Research machine teaching interpretable machine learning OpenAI