Results for "neural networks"

Two-network setup where generator fools a discriminator.

Exact likelihood generative models using invertible transforms.

Attention between different modalities.

Temporal and pitch characteristics of speech.

CNNs applied to time series.

Low-latency prediction per request.

Running predictions on large datasets periodically.

Increasing model capacity via compute.

Mathematical foundation for ML involving vector spaces, matrices, and linear transformations.

Measures similarity and projection between vectors.

Vectors with zero inner product; implies independence.

Matrix of first-order derivatives for vector-valued functions.

Learned subsystem that optimizes its own objective.

Enables external computation or lookup.

Software pipeline converting raw sensor data into structured representations.

Predicts next state given current state and action.

Learned model of environment dynamics.

Interpreting human gestures.

Robots learning via exploration and growth.

AI applied to X-rays, CT, MRI, ultrasound, pathology slides.

Ability to correctly detect disease.

AI predicting crime patterns (highly controversial).

Predicting case success probabilities.

Identifying suspicious transactions.

AI applied to scientific problems.

AI discovering new compounds/materials.

AI capable of performing most intellectual tasks humans can.

Fast approximation of costly simulations.

AI limited to specific domains.

The field of building systems that perform tasks associated with human intelligence—perception, reasoning, language, planning, and decision-making—via algori...