Posts in category

Machine Learning


A new technique can predict the final size of wildfires from the moment of ignition, researchers report. Built around a machine learning algorithm, the model can help forecast whether a wildfire will be small, medium, or large by the time it has run its course—knowledge useful to those in charge of allocating scarce firefighting resources. …

TF Dev Summit ’19 | TensorFlow.js 1.0 TensorFlow.js A JavaScript library for training and deploying ML models in the browser and on Node.js. In this talk we highlight the major capabilities of the library as well as give a development update on the major changes since the project was launched in 2018. Speakers: Yannick Assogba, …

Android Dev Summit 2019 | On-device ML: Tackling Complex Use Cases with ML Kit ML Kit makes it easy to integrate ML powered solutions into your apps, either through our turn-key Vision and Natural Language processing APIs or with your own custom TF Lite models. Not only can you easily tackle singular tasks like Text …

TF Dev Summit ‘19 | TensorFlow Federated (TFF): Machine Learning on Decentralized Data TensorFlow Federated (TFF) is an open-source framework for machine learning and other computations on decentralized data. TFF has been developed to facilitate open research and experimentation with Federated Learning (FL), an approach to machine learning where a shared global model is trained …

TF Dev Summit ‘19 | Exascale Deep Learning for Climate Analytics Climate change will have fundamental socio-economic impact and it is imperative for us to understand it better. This talk will show how TensorFlow was utilized on the world’s fastest supercomputer in order to extract pixel level segmentation masks of extreme weather phenomena in climate …

TF Dev Summit ’19 | What’s new in TensorBoard TensorBoard provides the visualization needed for machine learning experimentation. This talk will cover some exciting new functionality on using TensorBoard within Colab, an improved hyperparameter tuning with TensorFlow, and more. Speaker: Gal Oshri, Product Manager

TF Dev Summit ’19 | Powered By TensorFlow: Helping Paleographers Transcribe Medieval Text Using Machine Learning Machine learning is helping to solve challenging, real-world problems around the world. See how In Codice Ratio (http://www.inf.uniroma3.it/db/icr/), a research project made up of engineers, paleographers, and archivists, is using machine learning powered by TensorFlow to help humanities scholars …

TF Dev Summit ‘19 | TensorFlow Lite TensorFlow Lite is TensorFlow’s solution for running machine learning across resource constrained platforms. In the talk we will go over the current state of TFLite, as well as the roadmap, from the point of view of four core competencies: conversion, optimization, acceleration, and usability. Speakers: Pete Warden, Software …

TF Dev Summit ’19 | Reinforcement Learning in TensorFlow with TF-Agents Learn how to use TensorFlow and Reinforcement Learning to solve complex tasks. Speakers: Sergio Guadarrama, Senior Software Engineer Eugene Brevdo, Software Engineer

TF Dev Summit ’19 | TensorFlow Hub: Reusable Machine Learning TensorFlow Hub is a library for reusable pieces of machine learning. In this talk we will refresh when you would want to use it, talk about how it integrates with TF-2.0, and present some new modules added to https://tfhub.dev since last year. Speaker: André Susano …