Deep Learning Progress
François and Daniel discuss the progress of deep learning, highlighting the need for large amounts of data and compute power to acquire specific skills. While there are periods of fast progress, there are also challenges that require alternative approaches. They also explore how exponential progress can be achieved in certain verticals where adding more data and compute leads to breakthroughs. However, this does not apply to all problem domains, such as robotics and self-driving, where adaptability is crucial.In this clip
From this podcast
The Gradient
François Chollet: Keras and Measures of Intelligence
Related Questions