Skip to main content
University of California San Francisco
About UCSF
QBI - Workshop
Link copied to clipboard
Woot!
Fundamentals of Deep Learning for Multiple Data Types
Fundamentals of Deep Learning for Multiple Data Types
Aug 14, 2019 - Aug 14, 2019
8:30 AM - 3:00 PM

Speakers

Dima Lituiev

Host

NVIDIA DLI

NVIDIA DLI offers hands-on training for developers, data scientists, and researchers looking to solve challenging problems with deep learning and accelerated computing.

In this workshop you will learn how to train convolutional neural networks (CNNs) and recurrent neural networks (RNNs) to generate captions from images and video using TensorFlow and the Microsoft Common Objects in Context (COCO) dataset.

Familiarity with basic Python (functions and variables),

Understanding of fundamentals of convolutional neural networks for computer vision (e.g. see material here or here)

Prior experience training neural networks (in any framework, e.g. see this simple example in keras)

Tools And Frameworks: TensorFlow

8:30 - 8:45 Breakfast

8:45 - 10:15 Part 1: Segmentation

10:15 - 10:30 Coffee break

10:30 - 12:00 Part 2: Word Generation

12:00 - 1:00 Lunch

1:00 - 3:00 Part 3: Image & Video Captioning

Dima Lituiev, PhD,

Bakar Computational Health Sciences Institute, UCSF

Certified NVIDIA Deep Learning Institute Ambassador