Bookmark and Share

Deep Neural Network Fundamentals

The latest advances in image recognition are enabling a new wave of computer vision innovations, in applications ranging from medical devices to robotics to self-driving cars. The one thing they all have in common is they’ve been made possible with deep learning -- aka deep neural networks.

If you’re interested in deep neural networks and want to learn more about how they work and how to train them, check out these two videos from the May 2017 Embedded Vision Summit:

Demystifying Deep Neural Networks

What are deep neural networks, and how do they work? In this video, Shehrzad Qureshi, Senior Engineer at BDTI, provides an introduction to deep convolutional neural networks (CNNs), which have recently demonstrated impressive success on a wide range of vision tasks. Without using a lot of complex math, he introduces the basics of CNNs. He explores the differences between shallow and deep networks, and explains why deep learning has only recently become prevalent. He examines the different types of layers used in contemporary CNN designs and illustrates why networks composed of these layers are well suited to vision tasks.

Download the slides here (2.3 MByte PDF)

A Shallow Dive into Training Deep Neural Networks (with TensorFlow)

In this talk, Sammy Sidhu, Senior Engineer at DeepScale, introduces the basics of training deep neural network models for vision tasks. He begins by explaining fundamental training concepts and terms, including loss functions and gradients. He then provides an accessible explanation of how the training process works. Next, he highlights common challenges in training deep neural networks, such as overfitting, and explores proven techniques for addressing these challenges, including regularization and data augmentation. Throughout, he illustrates training techniques and challenges using examples taken from real-world applications.

Download the slides here (1.4 MByte PDF)

If you’re currently developing - or planning to develop - computer vision applications using deep learning, don’t miss our next training class:

Deep Learning for Computer Vision with TensorFlow
Hyatt Regency Santa Clara
July 13, 2017

If you’d like to see more of the great content presented at the Embedded Vision Summit, sign in or register for a new account.