Tutorial: Intelligent Learning Algorithms and Their Applications to Communications and Networking

Description

Approved for 3 CompTIA CEUs: A+, Network+

This tutorial aims to provide attendees with practical knowledge of advanced intelligent learning algorithms and how they can be applied to communications and networking problems. The tutorial will first provide attendees with an introduction to intelligent algorithms as well as a crash course on some of the theory behind intelligent algorithms. The tutorial will then provide an overview of many of the key types of learning algorithms, including machine learning algorithms, genetic algorithms, bio-inspired algorithms, deep learning, and then discuss the emerging field of multi-agent learning algorithms. The tutorial will then go on to compare and contrast the strengths and weaknesses of various types of algorithms, developing and presenting a detailed taxonomy of all the various mainstream forms of intelligent learning. The tutorial will then go on to highlight a plethora of areas of communications and networking in which intelligent learning algorithms have played a key role in technology development, including all layers of the protocol stack. Lastly, the tutorial will discuss existing machine learning tools and libraries available to today's practitioners such as TensorFlow, Python scikit-learn, Theano, etc.

Outline:

1. Introduction to Intelligent Algorithms • History and Background • Crash course on theory behind intelligent algorithms

2. Introduction to Types of Intelligent Algorithms • Intelligent Agents • Machine Learning Types • Bio-inspired and Evolutionary Computation(e.g., Genetic Algorithms and Genetic Programming) • Deep Learning: Neural Nets • Fuzzy-Logic-based Schemes • Bayesian Networks

3. Single agent vs. multi-agent learning algorithms • Multi-agent Planning Problem • Decentralized Planning, Communication, Coordination, and Cooperation • Heterogeneous versus Homogeneous Networks • Studies of Animal Social Behaviors (bird flocks, herds, ant colonies, insect swarms, etc.)

4. Applications of Intelligent Algorithms • Limitations, criticisms, and concerns

5. Example applications to communications • Modulation • Interleavers • Error control coding • Equalization • Antenna design

6. Example applications to networking • Routing protocols • Swarming behaviors

7. Existing machine learning tools and libraries

8. Concluding statements

Tracks:

• 
  Continuing Education
• 
  Technical Tutorials