Oriol Vinyals
(6 articles)
One-Shot Learning
ML technique where a model learns information about object categories from a single training example.
Generality: 542

Seq2Seq
Sequence to Sequence
Sequence to Sequence
Neural network architecture designed to transform sequences of data, such as converting a sentence from one language to another or translating speech into text.
Generality: 830

Encoder-Decoder Models
Class of deep learning architectures that process an input to generate a corresponding output.
Generality: 750

Autoregressive Generation
Method where the prediction of the next output in a sequence is based on the previously generated outputs.
Generality: 760

Model Distillation
ML technique where a larger, more complex model (teacher) is used to train a smaller, simpler model (student) to approximate the teacher's predictions while maintaining similar performance.
Generality: 625

Non-Contrastive
ML approach that focuses on learning useful representations of data without explicitly contrasting positive examples against negative examples.
Generality: 525