Presented By O'Reilly and Cloudera
Make Data Work
22–23 May 2017: Training
23–25 May 2017: Tutorials & Conference
London, UK

TensorFlow and deep learning (without a PhD)

Martin Görner (Google)
14:0514:45 Thursday, 25 May 2017
Data science and advanced analytics
Location: Hall S21/23 (A)
Secondary topics:  Deep learning, PyData
Level: Intermediate
Average rating: ****.
(4.75, 12 ratings)

Who is this presentation for?

  • Developers and data scientists

Prerequisite knowledge

  • Basic knowledge of mathematics
  • Previous experience with neural networks or Python not required

What you'll learn

  • Gain an overview of implementing neural networks using TensorFlow

Description

With TensorFlow, deep machine learning has transitioned from an area of research into mainstream software engineering. Martin Görner walks you through building and training a neural network that recognizes handwritten digits with >99% accuracy using Python and TensorFlow. Along the way, Martin discusses many standard deep learning techniques such as minibatching, learning rate decay, dropout, convolutional networks, and more and demonstrates how to implement them in TensorFlow.

Photo of Martin Görner

Martin Görner

Google

Martin Görner works in developer relations at Google, where he focuses on parallel processing and machine learning. Passionate about science, technology, coding, algorithms, and everything in between, Martin’s first role was in the Computer Architecture Group at STMicroelectronics. He also spent 11 years shaping the nascent ebook market, starting at Mobipocket, which later became the software part of the Amazon Kindle and its mobile variants. He holds a degree from Mines Paris Tech.

Comments on this page are now closed.

Comments

Picture of Martin Görner
Martin Görner | DEVELOPER RELATIONS
3/07/2017 11:28 BST

Slides: https://goo.gl/pHeXe7
Tutorial: https://codelabs.developers.google.com/codelabs/cloud-tensorflow-mnist/#0

Kajetan Olszewski | DATA SCIENTIST
23/06/2017 11:04 BST

Hi Martin, could you upload slides for your talk?