CMIC Seminar: Machine Learning and Deep Learning in MATLAB

Speaker: Jasmina Lazic, Mathworks
UCL Contact: Dominique Drai (Visitors from outside UCL please email in advance).
Date/Time: 15 Nov 17, 13:00 - 14:00
Venue: Roberts 106

Abstract

Deep learning techniques have rapidly evolved over the past decade, and they are now being used in fields varying from autonomous systems to medical image processing. This session covers deep learning and machine learning techniques for solving problems such as object detection, object recognition, and classification, including:

• Accessing and managing large data sets

• Extract state-of-the-art visual features for machine learning workflows

• Using pretrained models to locate, detect and recognize objects in images and videos

• Transfer learning: how to speed up the training process using GPUs and Parallel Computing

• Leveraging pretrained convolutional neural networks for feature extraction