Deep Learning For Vision Using CNNs and Caffe

Deep Learning for Vision Using CNNs and Caffe: A Hands-On Tutorial - September 22, 2016 - Cambridge, Mass

A quick, practical introduction to deep learning techniques for vision

Sensors subscribers— take 10% off registration with promo code, CNN16-SMW

Learn what convolutional neural networks (CNNs) are, how they are used for vision, and how to create, train, and deploy them with the Caffe framework. Caffe powers academic research projects, startup prototypes, and even large-scale industrial applications in vision, speech, and multimedia.

In the hands-on labs you will:

  • Run inference with off-the-shelf deep networks
  • Define, train, and test networks
  • Fine-tune a network to a new task and data
  • Use Caffe's extensive Python interface

This unique tutorial will be presented by the primary Caffe developers from the Berkeley Vision and Learning Center. See details, including bios of the presenters and a detailed outline. This is a great opportunity to learn about this popular technique from the people who created it.

  • Date/Time:  September 22, 2016 – 9 am to 5 pm (check-in opens at 8 am)
  • Location:  Hyatt Regency Cambridge, Cambridge, Massachusetts
  • Cost:  $795 (Use promo code, CNN16-SMW, for 10% off)

Register for “Deep Learning for Vision Using CNNs and Caffe: A Hands-on Tutorial”


About the Organizers

This tutorial is organized by the Embedded Vision Alliance and BDTI.

Find information and free resources for designing and building vision systems at

To learn how BDTI helps companies with technical analysis and engineering for embedded processing technologies, visit

Embedded Vision Alliance




Suggested Articles

Fieldscale’s SENSE development platform will lower design time and costs, companies claim

Avnet posted GAAP earnings per share from continuing operations of 5 cents per share on sales of $4.5 billion, down from a year ago.

Data Center group reached 4Q record at Intel, at $7.2 billion