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

Mastering computer vision problems with state-of-the art deep learning architectures, MXNet, and GPU virtual machines

14:0514:45 Wednesday, 24 May 2017
Secondary topics:  Deep learning
Level: Intermediate
Average rating: ***..
(3.33, 3 ratings)

Who is this presentation for?

  • Anyone interested in deep learning

Prerequisite knowledge

  • A basic understanding of machine learning

What you'll learn

  • Learn how to train an advanced deep neural net and how to use this system in a business use case related to image identification

Description

Deep learning has been especially successful in computer-vision tasks such as image classification because convolutional neural nets (CNNs) can create hierarchical levels of representations in an image. One of the most remarkable advances is ResNet, the CNN that surpassed human-level accuracy for the first time in history.

ImageNet competition has become the de facto benchmark for image classification in the research community. The “small” ImageNet data contains more than 1.2 million images distributed in 1,000 classes.

Miguel González-Fierro explains how to train a state-of-the-art deep neural network, ResNet, using Microsoft RSever and MXNet with the ImageNet dataset. (While most of the deep learning libraries are programmed in C++ and Python, only MXNet offers an API for R programmers.) Miguel then demonstrates how to operationalize this training for real-world business problems related to image classification.

Photo of Miguel Gonzalez-Fierro

Miguel Gonzalez-Fierro

Microsoft

Miguel González-Fierro is a senior data scientist at Microsoft UK, where he helps customers leverage their processes using big data and machine learning. Previously, he was CEO and founder of Samsamia Technologies, a company that created a visual search engine for fashion items, allowing users to find products using images instead of words, and founder of the Robotics Society of Universidad Carlos III, which developed different projects related to UAVs, mobile robots, small humanoids competitions, and 3D printers. Miguel also worked as a robotics scientist at Universidad Carlos III of Madrid and King’s College London, where his research focused on learning from demonstration, reinforcement learning, computer vision, and dynamic control of humanoid robots. He holds a BSc and MSc in electrical engineering and an MSc and PhD in robotics.

Comments on this page are now closed.

Comments

spdload com |
30/04/2018 13:40 BST

I think it’s a great idea to create web service, or huge e-commerce portal, or even an application for mobile phones based on virtual reality on the topic of real estate. I understand that you would like to develop a free application and monetize it in the future or for business immediately?
Look, I recommend you talk with the professionals of your business https://spdload.com/

Picture of Miguel Gonzalez-Fierro
Miguel Gonzalez-Fierro | SENIOR DATA SCIENTIST
26/05/2017 10:09 BST

Here you can find a blog post with more detailed information: https://blogs.technet.microsoft.com/machinelearning/2016/11/15/imagenet-deep-neural-network-training-using-microsoft-r-server-and-azure-gpu-vms/

Picture of Miguel Gonzalez-Fierro
Miguel Gonzalez-Fierro | SENIOR DATA SCIENTIST
26/05/2017 10:06 BST

Here you can find the slides of the talk: https://www.slideshare.net/MiguelFierro1/mastering-computer-vision-problems-with-stateoftheart-deep-learning