Deep Learning Conf 2016

Deep learning is now within reach for anyone to use!
We will explore real-world applications of deep learning by showing demos of transfer learning and real-time object recognition. Deep learning models can be difficult to train, evaluate and compare. In this session we will explore how MATLAB addresses the most common challenges such as handling large sets of images and retraining existing network architectures.

Outline

We’ll highlight the computer vision workflow using Deep Learning with MATLAB including:
1.Accessing and managing large sets of images

2.Leveraging the use of pre-trained networks for transfer learning

3.Using standard computer vision techniques to augment the use of deep learning

4.Speeding up the training process using GPUs

Speaker bio

Amit Doshi, MathWorks India
Amit Doshi is an application engineer at MathWorks in the area of technical computing. He focuses on data acquisition, data presentation, statistical analysis, and parallel computing. Amit has over 9 years of experience in experimental test setup development, testing and validation, workflow automation, and system simulations. He previously worked at Suzlon Energy Limited in Pune and Germany, Texas Instruments in Germany, and IIT Bombay. Amit holds a bachelor’s degree in mechanical engineering and a master’s degree in mechatronics