A Pyramidal Approach for Designing Deep Neural Networks and its Applications
Details
We are delighted to welcome Dr. Ihsan Ullah from NUIG for our 3rd ML Galway event. Ihsan’s talk will focus on a pyramidal approach for designing deep neural networks and its applications.
-- SCHEDULE --
6:30 PM Introduction to ML Galway by Niall O’Hara
6:40 PM TALK "A Pyramidal Approach for Designing Deep Neural Networks & its Applications"
7:30 PM Q&A
8:00 PM Closing
-- TALK--
Developing an intelligent system, capable of learning discriminative high-level features from high dimensional data lies at the core of solving many computer vision and machine learning tasks. One of the most widely used deep learning technique is convolutional neural network or its variations, e.g. ConvNet, 3DCNN, C3D. CNN kernel scheme reduces the number of parameters with respect to fully connected Neural Networks. Recent deep CNNs have more layers and more kernels for each layer with respect to early CNNs, and as a consequence, they result in a large number of parameters. This presentation will discuss pyramidal deep models and their applications. These models helped in reducing size of the network without degrading its performance. End of the presentation will discuss how we used virtual reality and machine learning in ROCSAFE.
-- SPEAKERS --
Ihsan Ullah is a Senior Post-Doctoral Researcher in Data Mining & Machine Learning Group, College of Engineering & Informatics, in NUIG. His research area is computer vision and deep learning. He has 7 year of experience in designing deep models with pyramid structure. Beside vision based applications, he also worked on text and signal processing. He published multiple conference, indexed journal, and workshop papers. Currently, he is working as the Project Manager of H2020 project called ROCSAFE.
-- THANK YOU --
Thank you to the team at the Portershed for helping us to host the meetup in their lovely space.
-- COMMUNITY --
Follow on Twitter: https://twitter.com/MLGalway