DeepMind Paper Challenges Generative Models’ Judgement | Synced

It’s known that deep neural network models — mostly discriminative models — are prone to making poor predictions with high confidence when they encounter data distribution scenarios that vary...

By · · 1 min read

Source: Synced | AI Technology & Industry Review

It’s known that deep neural network models — mostly discriminative models — are prone to making poor predictions with high confidence when they encounter data distribution scenarios that vary too much from their training data.