Deep Learning for Artificial Intelligence

Deep Learning for Artificial Intelligence

Artificial Intelligence is more than just the next wave of hi-tech. It is transforming nearly every sector of the economy. The applications of AI are limitless, and whatever your interest level, you can increase your working knowledge of AI through this professional development short course.

Enter your email to get notified when more dates become available!

This course offers a top-down approach to the study of deep neural network-based solutions, beginning with introducing basic concepts and applications. Course participants are then guided through the implementation of common architectures and corresponding training and prediction procedures, which includes a simple environment setup and interactive participation using Anaconda Jupyternotebooks. The underlying principles are then reviewed to provide the foundation necessary for deeper understanding and interrogation of these large, complex mathematical models. We conclude this short course by revisiting notable applications to discuss lessons learned.

Details about this course

  • Build consistent terminology for Artificial Intelligence (AI) concepts and Machine Learning (ML) & Deep Learning (DL) tools
  • Understand neural network components to interrogate the “black box” problem-solving paradigm
  • Examine neural network-based solutions and understand which applications are suitable for Deep Learning
  • Gain familiarity with common deep neural network architectures for classification, detection, and data generation
  • Learn to set up a simple working environment, implement basic deep neural networks, and evaluate algorithm performance

Ask your human resource manager about the opportunity to get reimbursed for this course.

Instructor

Derek J. Walvoord, P.h.D.

Dr. Derek J. Walvoord is a Senior Image Scientist for the Geospatial Integrated Products, Systems, and Analytics (IPSA) Division of L3Harris. With almost 12 years at the company, Derek has experience in photogrammetric sensor modeling for exotic imaging systems, Bayesian Belief Networks (BBNs) for rare event analysis, and machine learning for a variety of image enhancement and exploitation problems.