CAP 1931 - Artificial Intelligence for All

Spring 2026


Course description:



In this hands-on class students will learn to use various AI technologies including prediction, classification, image processing, image generation, computer vision and natural language processing. The class will also make the students aware of the limitations and risks posed by these technologies.

Student learning outcomes: After successful completion of this course, students will be able to:
  • Identify opportunities for the use of artificial intelligence in their professional life
  • Able to deploy AI techniques to solve specific problems
  • Understand the limitations and risks associated with the use of AI technology
Instructor: Dr. Lotzi Bölöni
Office Location: HEC - 319
E-mail: Ladislau.Boloni@ucf.edu (preferred means of communication)
Team: TBD
Web Site: http://www.cs.ucf.edu/~lboloni/Teaching/CAP1931_Spring2026/index.html
The assignments and the other announcements will be posted on the course web site
Classroom: HEC 119
Class hours: Mon, Wed 3:00pm - 4:15pm
Office hours: Mon, Wed 4:30pm - 6:00pm (in HEC 319)
Enrollment requirements: Programming skills are not required for this class, though basic computer literacy is expected. The AI tools are presented as “black boxes,” with students learning about input and output formats and, when relevant, understanding how training data impacts performance.
Grading:
  • 80%: 8 assignments involving trying out AI technologies
  • each worth 10%, 20%: final exam.
Required texts: There is no required textbook.
Verification of engagement: As of Fall 2014, all faculty members are required to document students' academic activity at the beginning of each course. In order to document that you began this course, please complete the following academic activity by the end of the first week of classes, or as soon as possible after adding the course. Failure to do so will result in a delay in the disbursement of your financial aid.
To satisfy this requirement, you must finish the first quiz posted online. Log in to Webcourses, choose CAP 1931, and submit your answers online.

Syllabus

Date
Topic
Lecture Notes, Readings, Homeworks
Mon., Jan. 12
 Introduction
  • Class requirements
  • Brief history of AI
Wed., Jan. 14
 Using Jupyter notebooks
  • vscode text editor
  • Writing in markdown
  • Jupyter notebooks
  • Entering data

Mon., Jan. 19.
 Martin Luther King day, no class.
Wed., Jan. 26
 Using Jupyter notebooks (cont'd)
  • Evaluating expressions
  • Running python snippets
  • Plotting graphs
  • Showing pictures

Mon., Jan. 26
 Machine Learning: Classification
  • Classification problems
  • One, two and many dimensions
  • Classification techniques: linear classification, nearest neighbor
  • Try it out: house vs. mansion
  • Dangers and pitfalls: fairness
Wed., Jan. 28
 Machine Learning: Regression
  • Regression problems
  • Regression techniques: linear regression, neural network regression
Mon., Feb. 2
 Machine Learning: Regression (cont'd)
  • Try it out: predict house prices in Orlando
Wed., Feb. 4 Computer Vision: Image classification
  • Image classification problems
  • ImageNet and other datasets
  • How it works: engineered features
  • How it works: convolutional neural networks
Mon., Feb. 9
 Computer Vision: Image classification (cont'd)
  • Try it out: kitten or puppy
  • Dangers and pitfalls: Illegal surveillance
Wed., Feb. 11
 Computer Vision: Object detection and segmentation
  • Object detection applications
  • Segmentation applications
  • How it works: convnet based object detection
  • How it works: transformer based object detection
Mon., Feb. 16
 Computer Vision: Object detection (cont'd)
  • Try it out: segment anything
  • Dangers and pitfalls: overtrust
Wed., Feb. 18
 Natural Language Processing: Sentiment analysis
  • Applications of sentiment analysis
  • How it works: deep neural nets
Mon., Feb. 23
 Natural Language Processing: Sentiment analysis (cont'd)
  • How it works: LLM based sentiment analysis
  • Try it out: movie review sentiment
  • Dangers and pitfalls: political applications
Wed., Feb. 25
 Large Language Models: Summarization
  • What is a large language model?
  • Application: summarizing articles
  • How it works: training an LLM, datasets
Mon., Mar. 2
 Large Language Models: Summarization (cont'd)
  • How it works: prompting an LLM
  • Try it out: summarize newspaper articles
  • Dangers and pitfalls: societal impact, deep vs. shallow reading
Wed., Mar. 4
 Large Language Models: Text reformulation
  • Application: ELI5
  • Application: machine translation
  • How it works: traditional machine translation approaches
  • How it works: instruction following and alignment
Mon., Mar. 9
 Large Language Models: Text reformulation (cont'd)
  • Try it out: prose to poetry
  • Try it out: prompting
Wed., Mar. 11
 Large Language Models: Question answering
  • Application: chatbots
  • How it works: data sources
  • How it works: retrieval augmented generation (RAG)
Mon., Mar. 16
 Spring break, no classes.
Mon., Mar. 18
 Spring break, no classes.
Mon., Mar. 23
 Large Language Models: Question answering (cont'd)
  • Try it out: prompt-based few shot learning
  • Try it out: RAG
  • Dangers and pitfalls: Hallucinations
Mon., Mar. 25
 Large Language Models: Generating text
  • Application: writing a letter on a given topic
  • Application: writing fiction in a certain style
  • How it works: long contexts
  • Try it out: writing fan fiction
Mon., Mar. 30
 Large Language Models: Generating text (cont'd)
  • Try it out: writing official letters
  • Dangers and pitfalls: Copyright violation
Wed., Apr. 1
 Computer Graphics: Style transfer
  • Application: transfer the style of a painting to a photo
  • Application: augmenting training data for a self-driving car
  • How it works: neural style transfer
Mon., Apr. 6
 Computer Graphics: Style transfer (cont'd)
  • Try it out: photos in the style of famous painters
  • Dangers and pitfalls: Societal implications of a race to bottom in art
Wed., Apr. 8
 Computer Graphics: Image Inpainting
  • Application: repairing old photos
  • Application: removing distracting details from pictures
  • How it works: encoder/decoder models
  • Try it out: removing people from images
  • Dangers and pitfalls: censorship
Mon., Apr. 13
 Computer Graphics: Image From Text
  • Application: generate pictures on certain topics
  • How it works: diffusion models
  • How it works: steering image generation
Wed., Apr. 15
 Computer Graphics: Image from text (cont'd)
  • Try it out: generating images on given subjects
  • Dangers and pitfalls: generating harmful content
Mon., Apr. 20
 Video processing: Video from text
  • Application: generating short videos
  • How it works: text conditioning in video space
  • How it works: challenges of operating in the image space vs. physical models
  • Try it out: short video sequences
Wed., Apr. 22
 Video processing: Deepfakes
  • Application: Forrest Gump
  • Application: political messaging
  • How it works: traditional models
Mon., Apr. 27
 Video processing: Deepfakes (cont'd)
  • Try it out: generating a deepfake
  • Dangers and pitfalls: erosion of trust