"It's Time Deep Learning Learned from Software Engineering" with Jeremy Howard
CrossMind.ai logo
Speech Abstract: The world of deep learning has traditionally been an academic world, drawing from mathematics, statistics, and operations research. This has meant great advances in the development of theory and algorithms, but software engineering best practices have sometimes been left behind. In this talk, the creator of fastai will explain how bringing software engineering best practices, such as layered API design and decoupling, have allowed him to provide a deep learning library that is both easier to use for beginners, at the same time as being more deeply hackable for experts, and also increasing performance. He will be drawing from research discussed in the peer reviewed paper describing the principles of fastai. Speaker Bio: Jeremy Howard Founding Researcher, fast.ai; Distinguished Research Scientist, University of San Francisco Jeremy Howard is a data scientist, researcher, developer, educator, and entrepreneur. Jeremy is a founding researcher at fast.ai, a research institute dedicated to making deep learning more accessible. He is also a Distinguished Research Scientist at the University of San Francisco, the chair of WAMRI, and is Chief Scientist at platform.ai. Previously, Jeremy was the founding CEO of Enlitic, which was the first company to apply deep learning to medicine, and was selected as one of the world’s top 50 smartest companies by MIT Tech Review two years running. He was the President and Chief Scientist of the data science platform Kaggle, where he was the top ranked participant in international machine learning competitions 2 years running. He was the founding CEO of two successful Australian startups (FastMail and Optimal Decisions Group, purchased by Lexis-Nexis). Before that, he spent eight years in management consulting, at McKinsey & Co, and AT Kearney. Jeremy has invested in, mentored, and advised many startups, and contributed to many open source projects. He has many media appearances, including writing for the Guardian, USA Today, and the Washington Post, appearing on ABC (Good Morning America), MSNBC (Joy Reid), CNN, Fox News, BBC, and was a regular guest on Australia’s highest-rated breakfast news program. His talk on TED.com, “The wonderful and terrifying implications of computers that can learn,” has over 2.5 million views. He is a co-founder of the global Masks4All movement. Paper Abstract: fastai is a deep learning library which provides practitioners with high-level components that can quickly and easily provide state-of-the-art results in standard deep learning domains, and provides researchers with low-level components that can be mixed and matched to build new approaches. It aims to do both things without substantial compromises in ease of use, flexibility, or performance. This is possible thanks to a carefully layered architecture, which expresses common underlying patterns of many deep learning and data processing techniques in terms of decoupled abstractions. These abstractions can be expressed concisely and clearly by leveraging the dynamism of the underlying Python language and the flexibility of the PyTorch library. fastai includes: a new type dispatch system for Python along with a semantic type hierarchy for tensors; a GPU-optimized computer vision library which can be extended in pure Python; an optimizer which refactors out the common functionality of modern optimizers into two basic pieces, allowing optimization algorithms to be implemented in 4–5 lines of code; a novel 2-way callback system that can access any part of the data, model, or optimizer and change it at any point during training; a new data block API; and much more. We used this library to successfully create a complete deep learning course, which we were able to write more quickly than using previous approaches, and the code was more clear. The library is already in wide use in research, industry, and teaching.