"The combination of Python, PyTorch, and fastai is working really well for us, and for our community. We have many ongoing projects using fastai for PyTorch [...] This stack will remain the main focus of our teaching and development.
It is very early days for Swift for TensorFlow. We definitely don’t recommend anyone tries to switch all their deep learning projects [...]"
You could think of this as being hyperparameter tuning, but that would be simplistic. Previous approaches have tried to hold most of architecture constant and then scientifically report the results of tweaking a particular variable for verifiable results. Quoc has been working with evolutionary approaches to performing these sort of experiments with large clusters. Most of the results so far have been technically superior, but at the cost of complexity/understandability. Here though, is the logical conclusion of this approach done at scale: using evolutionary approaches to explore a large swath of architecture space, finding an entirely new category of convolutional networks, then working backwards to a formal/clean architecture and paper.
We make mobile applications for companies big and small. Chances are, you've already used one of our apps!
We are looking to add more full time developers and designers in Columbia, MO!
https://quarkworks.co/careers/
Fill out the form at the URL above, or email hiring@quarkworks.co directly.