DESCRIPTION

Nowadays, Artificial Intelligence, notably Advanced Machine Learning (ML) drives scientific and economic growth worldwide. They are essentially massive ‘learning by experience/examples’ systems. However, as our tasks and the world change, such systems should adapt to new domains/tasks and continue learning. Knowledge should be transferred from one DNN systems to other ones. Distributed DNN training should be performed though Federated Learning, e.g., for privacy protection. New Learning modes should be explored, by reward maximation, as it is done in Deep Reinforcement Learning and Imitation Learning.

This advanced ML module covers all the above-mentioned topics: Deep Reinforcement Learning, Imitation Learning, Explainable AI, Continual Learning, Domain Adaptation, Transfer Learning, Federated Learning. Their applications span and revolutionize many domains:

  • Autonomous Systems (cars, drones),
  • Social Media Analytics,
  • Game development,
  • Financial Engineering (forecasting and analytics), Big Data Analytics,
  • Robotics/Control
  • Intelligent Human-Machine Interaction, Anthropocentric (human-centered), Computing
  • Smart Cities/Buildings and Assisted living.

Deep Reinforcement Learning for drone cinematography.

Explainable AI models.

LECTURE LIST

  1. Deep Reinforcement Learning
  2. Imitation Learning
  3. Explainable AI
  4. Continual Learning
  5. Domain Adaptation
  6. Transfer Learning
  7. Federated Learning
  8. Decentralized DNN Architectures
CVML WEB LECTURE MODULE SCHEDULE

This module has been designed to be mastered within 1 month (or less), if you have proper background (at least early undergraduate student in an EE, ECE, CS, CSE or any Engineering or Exact Sciences Department).
We propose that you follow the above mentioned  Lecture order. You may want to skip few Lectures that might not be of immediate interest to you for later study.

On average you can study 4 lectures per week. The related effort is as follows:
Lecture pdf study and filling the related understanding questionnaire: 1-2 hours per lecture (on average, depending on your background).

Theme: Illdy. Copyright © 2018 Icarus. All Rights Reserved.