All Segments
François Chollet: History of Keras and TensorFlow | AI Podcast Clips
6 segments available
This is a clip from a conversation with Francois Chollet from Sep 2019. New full episodes every Mon & Thu and 1-2 new clips or a new non-podcast video on all other days. You can watch the full conversation here: https://www.youtube.com/watch?v=Bo8MY4JpiXE (more links below) Podcast full episodes playlist: https://www.youtube.com/playlist?list=PLrAXtmErZgOdP_8GztsuKi9nrraNbKKp4 Podcasts clips playlist: https://www.youtube.com/playlist?list=PLrAXtmErZgOeciFP3CBCIEElOJeitOr41 Podcast website: https://lexfridman.com/ai Podcast on iTunes: https://apple.co/2lwqZIr Podcast on Spotify: https://spoti.fi/2nEwCF8 Podcast RSS: https://lexfridman.com/category/ai/feed/ Note: I select clips with insights from these much longer conversation with the hope of helping make these ideas more accessible and discoverable. Ultimately, this podcast is a small side hobby for me with the goal of sharing and discussing ideas. For now, I post a few clips every Tue & Fri. I did a poll and 92% of people either liked or loved the posting of daily clips, 2% were indifferent, and 6% hated it, some suggesting that I post them on a separate YouTube channel. I hear the 6% and partially agree, so am torn about the whole thing. I tried creating a separate clips channel but the YouTube algorithm makes it very difficult for that channel to grow unless the main channel is already very popular. So for a little while, I'll keep posting clips on the main channel. I ask for your patience and to see these clips as supporting the dissemination of knowledge contained in nuanced discussion. If you enjoy it, consider subscribing, sharing, and commenting. François Chollet is the creator of Keras, which is an open source deep learning library that is designed to enable fast, user-friendly experimentation with deep neural networks. It serves as an interface to several deep learning libraries, most popular of which is TensorFlow, and it was integrated into TensorFlow main codebase a while back. Aside from creating an exceptionally useful and popular library, François is also a world-class AI researcher and software engineer at Google, and is definitely an outspoken, if not controversial, personality in the AI world, especially in the realm of ideas around the future of artificial intelligence. Subscribe to this YouTube channel or connect on: - Twitter: https://twitter.com/lexfridman - LinkedIn: https://www.linkedin.com/in/lexfridman - Facebook: https://www.facebook.com/lexfridman - Instagram: https://www.instagram.com/lexfridman - Medium: https://medium.com/@lexfridman - Support on Patreon: https://www.patreon.com/lexfridman
Segments Timeline
The Birth of Keras
François Chollet shares the origins of Keras, detailing how he began working on it in February 2015. He discusses the landscape of deep learning at the time, highlighting the popularity of the Caffe library and his motivation to create a user-friendly tool for neural networks, particularly focusing on LSTM networks. Chollet emphasizes the importance of Python in Keras's design, contrasting it with the static configuration files used by other libraries.
"let's go from the philosophical to the practical I can give me a history of Karis and all the major deep learning frameworks that you kind of remember in relation to chaos and in general tensorflow si..."
Keras vs. Caffe: A Design Choice
Chollet explains the design philosophy behind Keras, particularly the decision to define models using Python code instead of configuration files. He reflects on the challenges of this approach in a landscape dominated by Caffe and other libraries, and how Keras aimed to combine different neural network architectures seamlessly. This segment highlights the innovative spirit behind Keras and its user-centric design.
"decision at the time that was Canon are obvious is that the models would be defined yeah a Python code which was kind of like going against the mainstream at the time because cafe thailand who wants o..."
The Rise of Keras in the Deep Learning Community
François Chollet discusses the early adoption of Keras within the deep learning community, noting its timing coincided with a growing interest in neural networks. He recounts his transition to Google and the exposure to TensorFlow, which prompted him to adapt Keras for this new framework. This segment captures the excitement and challenges of integrating Keras into a rapidly evolving field.
"magical in the sense that it's delightful yeah right yeah I'm actually quite surprised I didn't know that it was born out of desire to implement our hands in lc/ms it was that's fascinating so you wer..."
Integrating Keras with TensorFlow
In this segment, Chollet describes his journey of porting Keras to TensorFlow after its release in November 2015. He explains the technical aspects of abstracting backend functionalities to allow Keras to run on multiple platforms. This transition marked a significant milestone for Keras, enhancing its usability and performance in the deep learning ecosystem.
"intrigued by the capabilities of O&N on and so NLP so it it grew from there then I joined Google months later and that was actually completely unrelated to took care of actually joined a research team..."
Keras: From Side Project to Core Library
Chollet reflects on how Keras evolved from a side project to a core component of TensorFlow. He shares insights into his collaboration with the TensorFlow team and the integration of Keras's API into TensorFlow. This segment highlights the growth of Keras and its impact on making deep learning more accessible to a broader audience.
"so what is there was a natural as a natural transition yeah absolutely so what I mean that still carries is the side almost fun project right yeah so it it was not my job assignment it's not I was doi..."
The Future of Keras and TensorFlow 2.0
In this final segment, Chollet discusses the advancements in TensorFlow 2.0 and the exciting features that enhance Keras's usability. He emphasizes the balance between high-level usability and low-level flexibility, catering to a diverse range of users from researchers to data scientists. This segment encapsulates the ongoing evolution of Keras and its role in the future of deep learning.
"things but so Tessa flow 2.0 it's kind of there's a sprint I don't know how long I'll take but there's a sprint towards the finish what do you look what are you working on these days what are you exci..."