Evolution of Machine Learning
Tim discusses the shift towards treating machine learning as a software engineering discipline, emphasizing the importance of abstraction without sacrificing performance. He explores the concept of differentiable computing and views deep learning models as computer programs, inspired by the idea of software 2.0.In this clip
From this podcast
Machine Learning Street Talk (MLST)
#046 The Great ML Stagnation (Mark Saroufim and Dr. Mathew Salvaris)
Related Questions
How do layers work in deep learning as discussed in the episode Fast.ai, AutoML, and Software Engineering for ML: Jeremy Howard // Coffee Session #47 and the clip Building Layers of Abstraction?
How do you learn in layers as discussed in the episode Fast.ai, AutoML, and Software Engineering for ML: Jeremy Howard // Coffee Session #47 and the clip Building Layers of Abstraction?