Overview

This site contains learning materials for two AI Workshops run by Mississippi State University Geosystems Research Institute. Participants are introduced to basic concepts via powerpoint lecture and guided through hands-on programming in an interactive jupyter notebook framework. Participants are encouraged to actively modify and expand the provided python code, and to bring their own imagery for analysis.

AI Workshop I:

Introduction to Image Processing and Classical Machine Learning

Scope: This is a 3-day workshop that will be facilitated through WebEx
Target Audience: Research scientists interested in machine learning applied to images
Prerequisites: Proficiency in python programming

This three-day workshop will cover the basics of image processing and classical machine learning using Python. Participants will be introduced to the basic concepts via PowerPoint lecture and guided through hands-on programming in an interactive Jupyter notebook framework. Participants will be encouraged to actively modify and expand the provided python code. Topics in image processing will include the basics of image processing, including conventions of image representation and image manipulations. Topics in classical machine learning will include the basics of feature extraction and labels; training, testing, and validation; and common methods for image classification. Topics in deep learning will include the basics of convolutional neural networks; training, testing, and validation in deep learning; and transfer learning.

AI Workshop II:

Advanced Topics in Deep Learning

Scope: This is a 2-day workshop that will be facilitated through WebEx
Target Audience: Research scientists interested in deep learning applied to images
Prerequisites: Proficiency in Python programming; experience with topics from AI Workshop I

This two-day workshop will provide more in-depth exploration of some common deep learning architectures used in image processing. Participants will be introduced to the basic concepts via PowerPoint lecture and guided through hands-on programming in an interactive Jupyter notebook framework. Participants will be encouraged to actively modify and expand the provided python code. The first day will cover methods to explore, visualize, and modify network architectures. The second day will cover extensions to the convolutional neural network for such tasks as image segmentation, object detection, and spatio-temporal analysis.

Learning Goals

By the end of Workshop 1 participants should be able to:

1. display and interpret grayscale and color images,
2. apply common image transforms and filters to images,
3. extract hand-designed features from an image dataset and format those features for use in machine learning,
4. apply common machine learning classifiers to an image dataset and assess performance,
5. define a convolutional neural network (CNN) for classification of images, including pre-processing of the input data,
   and
6. train and test a CNN for classification of images, including implementation of a simple transfer learning.

By the end of Workshop 2 participants should be able to:

1. visualize characteristics of a CNN to help interpret performance,
2. modify a CNN architecture for application to new data (application of more complex transfer learning), and
3. apply methods learned for classification CNNs to other forms of CNNs, e.g., image segmentation, object detection.