AI Rewind 2018: Trends in Deep Learning with Jeremy Howard
EPISODE 214
|
DECEMBER
24,
2018
Watch
Follow
Share
About this Episode
In this episode of our AI Rewind series, we're bringing back one of your favorite guests of the year, Jeremy Howard, founder and researcher at Fast.ai.
Jeremy joins us to discuss trends in Deep Learning in 2018 and beyond. We cover many of the papers, tools and techniques that have contributed to making deep learning more accessible than ever to so many developers and data scientists.
About the Guest
Jeremy Howard
Fast.ai
Resources
- DAWNBench
- Paper: Super-Convergence: Very Fast Training of Neural Networks Using Large Learning Rates
- Paper: Fixing Weight Decay Regularization in Adam
- Jason Antic - DeOldify
- Paper: Improved Regularization of Convolutional Neural Networks with Cutout
- Paper: Addressing Function Approximation Error in Actor-Critic Methods
- Judy Gichoya
- Pytorch 1.0
- Fast AI 1.0
- Pytorch "Just in Time" Library
- A Highly Efficient and Modular Implementation of Gaussian Processes in PyTorch
- TVM Deep Learning Compiler
- Swift
- F#
- Julia
- Platform.ai
