Presented By O’Reilly and Intel AI
Put AI to work
8-9 Oct 2018: Training
9-11 Oct 2018: Tutorials & Conference
London, UK

Sponsored by:
Google Cloud

TensorFlow at the AI Conference

Google Cloud Platform and the TensorFlow team present four days of education focused on TensorFlow and machine learning at the AI Conference in London. Entry is available to any conference registrant, including Pavilion Plus pass holders. To join us, please register here

Overview

Monday: Serverless Machine Learning with TensorFlow on GCP

A full day introduction to designing and building machine learning models on Google Cloud Platform. Read more.

Tuesday: End-to-End Machine Learning with TensorFlow on GCP

Spend the day working through the process of building a complete machine learning pipeline covering ingest, exploration, training, evaluation, deployment, and prediction. Read more.

Wednesday & Thursday: TensorFlow Sessions

Two days of conference sessions covering major TensorFlow topics, such as distributed training, TF Lite, TensorFlow.js, and more, accompanied by a focus on ML offerings from Google Cloud, such as AutoML, CMLE, TPUs, and Kubeflow. We hope you will join us to dive deeper into TensorFlow!

Schedule

9:00–17:00 Monday, 8 October 2018
Location: Windsor Suite
Benoit Dherin (Google)
Average rating: *****
(5.00, 1 rating)
Benoit Dherin leads an introduction to designing and building machine learning models on Google Cloud Platform. Through a combination of presentations, demos, and hand-ons labs, you'll learn machine learning (ML) and TensorFlow concepts and develop skills in developing, evaluating, and productionizing ML models. Read more.
9:00–17:00 Tuesday, 9 October 2018
Location: Windsor Suite
Melinda King (ROI Training)
Melinda King walks you through the process of building a complete machine learning pipeline, from ingest and exploration to training, evaluation, deployment, and prediction. Read more.
11:05–11:45 Wednesday, 10 October 2018
Location: Buckingham Room - Palace Suite
Sandeep Gupta (Google), Edd Wilder-James (Google)
TensorFlow is one of the world’s biggest open source projects, and it continues to grow in adoption and functionality. Sandeep Gupta and Edd Wilder-James share major recent developments, highlight some future directions, and explain how you can become more involved in the TensorFlow community. Read more.
11:55–12:35 Wednesday, 10 October 2018
Location: Buckingham Room - Palace Suite
Amit Patankar (Google)
Building machine learning models is a multistage process. TensorFlow's high-level APIs make this process smooth and easy, whether you are starting small or going big. Amit Patankar walks you through building, training, and debugging a model and then exporting it for serving using these APIs. Read more.
13:45–14:25 Wednesday, 10 October 2018
Location: Buckingham Room - Palace Suite
Ryan Sepassi (Google)
Ryan Sepassi offers an overview of Tensor2Tensor, an open source library of datasets and models and a framework for training, evaluation, and decoding, built on top of TensorFlow. Tensor2Tensor is actively used and maintained by scientists and engineers within Google Brain. Read more.
14:35–15:15 Wednesday, 10 October 2018
Location: Buckingham Room - Palace Suite
Joshua Dillon (Google Research), Wolff Dobson (Google)
Joshua Dillon and Wolff Dobson discuss core TensorFlow Probability (TFP) abstractions and demo some of TFP's modeling power and convenience. They also share some of the recent results from Project Magenta, a research project exploring the role of machine learning in the process of creating art and music. Read more.
16:00–16:40 Wednesday, 10 October 2018
Location: Buckingham Room - Palace Suite
Lucio Floretta (Google Cloud)
Cloud AutoML is a suite of machine learning products that enables developers with limited machine learning expertise to train high-quality models specific to their business needs, leveraging Google’s state-of-the-art transfer learning and neural architecture search technology. Lucio Floretta demonstrates the power and ease of use of AutoML Vision, Translate, and Natural Language. Read more.
16:50–17:30 Wednesday, 10 October 2018
Location: Buckingham Room - Palace Suite
Zack Akil (Google)
Average rating: *****
(5.00, 1 rating)
Zack Akil shares pragmatic techniques and useful tools that can help you avoid common pitfalls when building ML, including tools for notebook collaboration and version control that will help prevent you and your teammates from stepping on each others' toes as well as an iterative ML model development approach that will prevent your project from stagnating. Read more.
11:05–11:45 Thursday, 11 October 2018
Location: Buckingham Room - Palace Suite
Daniel Smilkov (Google), Nikhil Thorat (Google)
TensorFlow.js is the recently released JavaScript version of TensorFlow that runs in the browser and Node.js. Daniel Smilkov and Nikhil Thorat offer an overview of the TensorFlow.js ML framework and share a demo of a complete machine learning workflow, including training, client-side deployment, and transfer learning. Read more.
11:55–12:35 Thursday, 11 October 2018
Location: Buckingham Room - Palace Suite
Brian Lee (Google Brain), Priya Gupta (Google)
TensorFlow AutoGraph automatically converts plain Python code into its TensorFlow equivalent, using source code transformation. Brian Lee and Priya Gupta demonstrate how to distribute your training in TensorFlow easily across multiple accelerators and machines. Read more.
13:45–14:25 Thursday, 11 October 2018
Location: Buckingham Room - Palace Suite
Thomas Norrie (Google)
Training complex machine learning models with large amounts of data can take a very long time. Thomas Norrie explores methods for accelerating this process by distributing training across multiple accelerators and machines and leads a technical deep dive into Google Cloud’s TPU accelerators. Read more.
14:35–15:15 Thursday, 11 October 2018
Location: Buckingham Room - Palace Suite
Pete Warden (Google)
Pete Warden discusses the surprising effectiveness of deep learning on low-power devices. Read more.
16:00–16:40 Thursday, 11 October 2018
Location: Buckingham Room - Palace Suite
Kenny Song (Google), Quentin de Laroussilhe (Google)
As machine learning evolves from experimentation to serving production workloads, so does the need to effectively manage the end-to-end training and serving workflow. Kenny Song and Quentin de Laroussilhe offer an overview of TensorFlow Extended, the end-to-end machine learning platform for TensorFlow that powers products across all of Google. Read more.
16:50–17:30 Thursday, 11 October 2018
Location: Buckingham Room - Palace Suite
Sara Robinson (Google)
Whether you’re new to machine learning (ML) or you’re already an expert, Google Cloud Platform (GCP) has a variety of tools to help you. Sara Robinson starts with the basics: how to use a pretrained ML model with a single API call. She then demonstrates how to customize a pretrained model with AutoML. Sara concludes by explaining how to train and serve a custom TensorFlow model on GCP. Read more.