Course Abstract

Convolutional Neural Networks (CNNs) are responsible for unprecedented advances in the field of Computer Vision since they have achieved impressive performance in challenging tasks such as image classification, attribute recognition, object detection and segmentation, among others. In this course, we will take a deep dive of the inner workings of CNNs.

DIFFICULTY LEVEL: INTERMEDIATE

Learning Objectives

  • Understanding what are Convonutional Neural Networks.

  • Understanding what exactly do CNNs compute

  • Why and when do CNNs work well

  • How do CNNs learn

  • Explore common architectures

  • Application on multi-label attribute recognition

Instructor

Instructor Bio:

Co-founder | MACTY.EU | Content A

Susana Zoghbi, PhD

Susana Zoghbi, Co-Founder & CEO, Macty. Susana is a researcher and entrepreneur in a quest to help businesses grow with Artificial Intelligence. She received a PhD in Computer Science and her research focused on cross-modal processing of textual and visual Information. She designed deep neural network architectures and probabilistic graphical models to understand visual and textual content from e-commerce and social media. Her work has been published in top conferences and journals in Artificial Intelligence. She has worked for NASA’s Frontier Development Lab as a Deep Learning Researcher to automatically search for long-period comets that might impact Earth. She has also worked for Microsoft Research in Cambridge, where she focused on machine learning for optimizing environments for large scale software development. Before her PhD, she obtained two Masters degrees, one in Mechanical Engineering from the University of British Columbia, where her research focused on human-robot interaction technologies, and one in Mathematical Physics, where she focused on gravitational fluctuations in Domain Wall Spacetimes. In 2014, she was granted a Google Anita Borg award for her contributions in Computer Science and her community.

Background knowledge

  • This course is for current and aspiring Data Scientists, Deep Learning and Machine Learning Engineers, and AI Product Managers

  • Knowledge of following tools and concepts is useful:

  • Linear Algebra, Python, Keras,

  • some familiarity with feed-forward neural networks might be beneficial but not required.

Real-world applications

  • CNNs are actively used Image Classification tasks for Search Engines, Recommender Systems and Social Media

  • Some of the face recognition applications of CNNs and RNNs are in Social Media, Identification procedures, Surveillance

  • Legal, Banking, Insurance, Document digitization uses CNNs for optical character recognition.