Experts explore TensorFlow 2.0's machine learning capabilities as well as the broader tools and applications of TensorFlow.
Ankur Narang discusses sticker recommendations with multilingual support, a key innovation driven by sophisticated natural language processing (NLP) algorithms.
Anna Roth discusses human and technical factors and suggests future directions for training machine learning models.
Tony Jebara explains how Spotify improved user satisfaction by building components of the TFX ecosystem into its core ML infrastructure.
Sandeep Gupta and Joseph Paul Cohen introduce the TensorFlow.js library.
Konstantinos Katsiapis and Anusha Ramesh dive into the insights and approach that helped TensorFlow Extended (TFX) reach its current popularity within Alphabet.
Chris Lattner and Tatiana Shpeisman explain how MLIR addresses the complexity caused by software and hardware fragmentation.
Mike Liang discusses TensorFlow Hub, a platform where developers can share and discover pretrained models and benefit from transfer learning.
Jared Duke and Sarah Sirajuddin explore on-device machine learning and the latest updates to TensorFlow Lite.
Theodore Summe offers a glimpse into how Twitter employs machine learning throughout its product.
Megan Kacholia explains how Google’s latest innovations provide an ecosystem of tools for developers, enterprises, and researchers who want to build scalable ML-powered applications.
Jeff Dean explains why Google open-sourced TensorFlow and discusses its progress.
Kemal El Moujahid reveals new developments for the TensorFlow community.