raghu@dark-factory :~/kb/machine-unlearning $ cat

Machine Unlearning

Techniques for removing the influence of specific training data from an already-trained model without full retraining, in response to privacy, takedown, or consent demands.

grounded in: Latest AI/tech trends theme: 'Surveillance & AI-training data backlash — Institutions and users are actively rejecting mass surveillance and forced data harvesting for AI.'

Connected concepts

Data minimization, Data poisoning defense, Knowledge distillation, Content provenance & trust

Explore it live in the knowledge graph →