Designed for: Test Officers, Engineers and IT Specialists

Format: Instructor-led, 3 days

Course Objectives

Upon completion of this course, students will be able to:

  • Learn the importance of data
  • Know the methods used by AI tools to retrieve data from various sources
  • Match a data set with the most promising inductive learning algorithms
  • Train the machine with the given data to derive a particular conclusion
  • Recognize the methods used to determine the best result
  • Understand classification of data

Example-based “No Code” Learning focused on AI, Machine, & Deep Learning:

  1. Selecting Source Data: Determining the best Data Source for a given task
  2. Preprocessing Data: Integration, transformation, reduction, and cleaning
  3. Data Wrangling: Data Leakage and Deep Learning
  4. Data Smoothing: Missing, noisy, and inconsistent data
  5. Image Processing: Categories of images and their classification
  6. Image Processing Methods: Examples and strategies used in AI
  7. Image Processing Techniques: Rotation, Translation, Color, Zooming, & Flipping
  8. Image Recognition: Pixel, Image Type, Iterators, Code Execution & Result Processing
  9. Deep Learning: Defined
  10. Image Processing Algorithm CNN: Layers of CNN; Convolutional, Pooling, and Fully-Connected
  11. Object Recognition: Using MNIST for handwritten digit recognition
  12. Intelligent Document Processing (IDP) & Deep Neural Networks for Image Processing: Analog and Digital Image Processing
  13. Image Processing Phases: Acquisition, Enhancement, Restoration, Processing, Recognition, Representation & Description

Contact Dr. John DeLalla at 520-626-6389 or jd@arizona.edu to learn more.