← Back to Submind

Topic

attention mechanisms

Sequence to Sequence Deep Learning (Quoc Le, Google)

Lex Fridman

Quoc Le introduces Sequence to Sequence (Seq2Seq) learning through a practical example of an automatic email reply system, illustrating how variable-length inputs can be mapped to variable-length outputs. He begins with simple Bag-of-Words representations using logistic regression but highlights the …

Deep Learning State of the Art (2019)

Lex Fridman

The lecture outlines the state of the art in deep learning as of 2019, emphasizing significant breakthroughs that occurred between 2017 and 2018 rather than just benchmark results on standard tasks like ImageNet or NLP. The speaker identifies 2018 specifically as "the year of natural language proces …