All Work Published on Machine Learning
This explainer provides brief definitions for key terms associated with artificial intelligence, ranging from autonomous systems to deep learning and foundation models.
This explainer provides brief definitions for key terms associated with artificial intelligence, ranging from autonomous systems to deep learning and foundation models.
Stanford scientists in Senegal hunting for schistosomiasis—a parasitic disease infecting 200+ million people worldwide—used AI to transform local field work into satellite-powered disease mapping.
Stanford scientists in Senegal hunting for schistosomiasis—a parasitic disease infecting 200+ million people worldwide—used AI to transform local field work into satellite-powered disease mapping.
Interventions on model-internal states are fundamental operations in many areas of AI, including model editing, steering, robustness, and interpretability. To facilitate such research, we introduce pyvene, an open-source Python library that supports customizable interventions on a range of different PyTorch modules. pyvene supports complex intervention schemes with an intuitive configuration format, and its interventions can be static or include trainable parameters. We show how pyvene provides a unified and extensible framework for performing interventions on neural models and sharing the intervened upon models with others. We illustrate the power of the library via interpretability analyses using causal abstraction and knowledge localization. We publish our library through Python Package Index (PyPI) and provide code, documentation, and tutorials at ‘https://github.com/stanfordnlp/pyvene‘.
Interventions on model-internal states are fundamental operations in many areas of AI, including model editing, steering, robustness, and interpretability. To facilitate such research, we introduce pyvene, an open-source Python library that supports customizable interventions on a range of different PyTorch modules. pyvene supports complex intervention schemes with an intuitive configuration format, and its interventions can be static or include trainable parameters. We show how pyvene provides a unified and extensible framework for performing interventions on neural models and sharing the intervened upon models with others. We illustrate the power of the library via interpretability analyses using causal abstraction and knowledge localization. We publish our library through Python Package Index (PyPI) and provide code, documentation, and tutorials at ‘https://github.com/stanfordnlp/pyvene‘.
A New Direction for Machine Learning in Criminal Law
This brief proposes a machine learning approach to studying decision-making in the criminal legal system as a way to identify and reduce systemic inequalities.
This brief proposes a machine learning approach to studying decision-making in the criminal legal system as a way to identify and reduce systemic inequalities.
