Events

The Pittsburgh Supercomputing Center is pleased to present a Machine Learning and Big Data workshop.

This workshop will focus on topics including big data analytics and machine learning with Spark, and deep learning using Tensorflow.

This will be an IN PERSON event hosted by various satellite sites, there WILL NOT be a direct to desktop option for this event.

Tentative Agenda

Tuesday, August 15
All times given are Eastern

11:00 Welcome
11:25 A Brief History of Big Data
12:20 Intro to Spark
1:00 Lunch break
2:00 More Spark and Exercises
3:00 Intro to Machine Learning
5:00 Adjourn

The Pittsburgh Supercomputing Center is pleased to present a Machine Learning and Big Data workshop.

This workshop will focus on topics including big data analytics and machine learning with Spark, and deep learning using Tensorflow.

This will be an IN PERSON event hosted by various satellite sites, there WILL NOT be a direct to desktop option for this event.

Tentative Agenda

Tuesday, August 13
All times given are Eastern

11:00  Machine Learning: Recommender System with Spark
1:00       Lunch break
2:00       Deep Learning with Tensorflow
5:00       Tying it All Together
5:30       Adjourn

In this workshop, we'll focus on three key pillars of Python development: error handling, user-defined functions, and database programming.

Firstly, we'll equip you with the tools to build robust and resilient code through comprehensive error handling techniques. Learn how to anticipate and gracefully manage errors, ensuring your programs not only function smoothly but also remain reliable in the face of unexpected challenges.

Next, we'll explore the power of user-defined functions, enabling you to create modular and reusable code. Dive into advanced function design, parameter handling, and return statements, empowering you to write efficient and maintainable programs.

Lastly, database programming will teach you how to interact with databases using Python. Learn to connect, query, and manipulate databases seamlessly, gaining a valuable skill set for real-world applications.

By the end of this session, you'll possess a deeper understanding of Python's capabilities, enabling you to write more sophisticated, error-resistant, and scalable programs.

To participate in the hands-on lab during the session, you will need to provide your own computer with a web browser and a reliable internet connection.

This event is not being recorded. Any materials provided by the presenter will be sent to all registrants by the end of the second business day after the conclusion of the event. Please email ResearchITEvents@ucf.edu to request access to the materials two business days after the completion of the event if you did not register.

Presented by John Aedo, Ph.D.

This workshop explores the evolving landscape of AI-powered conversational systems, focusing on chatbot development using Microsoft Azure and OpenAI services. Participants will gain hands-on insights into building intelligent, context-aware chatbots powered by large language models (LLMs) and enhanced through Retrieval-Augmented Generation (RAG)—a technique that enables models to produce more accurate, grounded responses by incorporating external knowledge.

In this session, I will demonstrate how to develop a RAG-based chatbot using the Azure and OpenAI ecosystem. The workshop will introduce the foundational components of a RAG pipeline and present a streamlined low-code/no-code approach for rapid prototyping and deployment using Azure tools and services.

This workshop offers a clear and simplified overview of how to integrate different types of data—such as documents and structured content—into language model-based systems to generate reliable, domain-specific outputs. Whether you're interested in educational technologies, research automation, or enterprise applications, this session will equip you with the knowledge and tools to design chatbots tailored to your specific datasets and use cases.

This workshop is designed for everyone who is interested in integrating AI into their work. While no prior experience with chatbot development is required, a basic understanding of cloud platforms like Azure or general AI terminology will be helpful. Basic familiarity with RAG and LLMs would also be helpful but is not mandatory. The session will be accessible to beginners and informative for those exploring Retrieval-Augmented Generation and large language models.

Presented by Nafisa Islam

Data and statistics play an important role in conducting research, yet understanding how to find, analyze, and manage data can be complicated. If you are interested in developing data skills, this session on finding data sources will provide an overview of introductory information to aid you on your path to being a data expert.

The workshop will introduce the basic concepts of data and examples of how it is used in supporting research, including copyright concerns to be aware of. Resources that are applicable in a variety of disciplines will be presented. Data source examples will also highlight open data sources, subscription-based sources available through the UCF Libraries, along with grey literature and preprint sources will be discussed.

Presented by Ven Basco, Rich Gause, Missy Murphey, Sarah Norris

The 2025 UCF Annual Research Computing Symposium will be held on Wednesday, October 1st at the Digital Learning Center, offering UCF faculty, post-docs, and students a platform to share research and ideas involving advanced computational tools. Topics include high-performance computing, quantum computing, cloud computing, and AI research enablement. The event features a keynote, faculty talks, and student poster presentations.

Please visit the 2025 UCF Research Computing Symposium web page (https://rci.research.ucf.edu/2025-ucf-research-computing-symposium/) for the full agenda and list of presenters.

Structured Query Language (SQL) is used for data retrieval, searching, modification, and reporting by relational database systems. This workshop is an introductory level course aimed at researchers and students new to databases. You will learn how to explore data stored in databases like Microsoft Access, Microsoft SQL Server, mySQL, Oracle, and SQLite using SQL. You will gain hands-on experience querying, sorting, formatting, and transforming data. You also will be introduced to various tools such as the Python and R programming languages for accessing and querying databases.

To participate in the hands-on lab during the session, you will need to provide your own computer with a web browser and a reliable internet connection.

This event is not being recorded. Any materials provided by the presenter will be sent to all registrants by the end of the second business day after the conclusion of the event. Please email ResearchITEvents@ucf.edu to request access to the materials two business days after the completion of the event if you did not register.

Presented by John Aedo, Ph.D.

This session will be an in-person session for attendees and the instructor will join on Zoom.

Topics included in this session:
- Best Practices For Document Structures
- Cross-referencing
- Math Typesetting
- Complex Tables
- Advanced Figures
- Reference Management with Mendeley/Zotero
- Using Templates

Presented by Tom Hejda, Lisa Delmonico

This hands-on workshop introduces researchers to Amazon SageMaker Unified Studio, a comprehensive platform that streamlines data analysis, machine learning model development, and AI-driven insights for research. Through an integrated environment, researchers can collaborate effectively while maintaining data governance and security, eliminating the challenges of fragmented tools and manual processes. In this workshop, you'll step into various roles to analyze data, build scalable data pipelines, develop predictive machine learning models, and create insights using Generative AI.

L200 - Recommended for researchers with familiarity with Jupyter notebooks and basic coding experience

Presented by Gabriel Brackman

Join this hands-on workshop to learn LaTeX, the document preparation system widely used in academia for scientific writing, including journals, theses, and presentations. This session is designed for LaTeX starters with little to no prior experience.

Workshop Requirements:

Platform: We will use Overleaf.

Account:

UCF provides an Overleaf premium license for its researchers. If you are a faculty, graduate student, or postdoctoral scholars, please create an Overleaf account before the workshop using instruction in the following link: https://rci.research.ucf.edu/resource/overleaf

If you are an undergrad, then please create one through this link: https://www.overleaf.com/register.

Equipment: You must provide your own laptop with a web browser and a reliable internet connection to participate in the hands-on activities.

Please note that this event will not be recorded. Presentation materials will be emailed to all registrants within two business days after the workshop. If you did not register, you may request the materials by emailing ResearchITEvents@ucf.edu two business days after the event.

Presented by Fahad Khan, Ph.D.

This hands-on workshop introduces researchers to Amazon Q Developer, a powerful AI coding assistant designed to accelerate research software development and data analysis workflows. Through practical exercises with the Q-Words application, you'll discover how AI-assisted development can transform your research tooling - from rapid prototyping to code optimization and debugging. You'll learn to leverage Amazon Q Developer's capabilities to understand complex codebases, implement new features efficiently, and optimize your applications across multiple programming languages including Java, Python, C#, and TypeScript. Whether you're developing data analysis tools, research applications, or computational models, this workshop will demonstrate how AI-assisted development can significantly reduce implementation time and technical overhead, allowing you to focus more on your core research objectives.

L200 – Recommended for researchers with basic coding experience

Presented by Gabriel Brackman

In this workshop, attendees will learn how to simplify their life as a researcher by automating the generation of LaTeX tables, plots, and figures directly as output from a data analysis pipeline in Python. This workflow enables researchers to "travel back in time" to when their paper was submitted if minor adjustments need to be made, without having to re-run the entire research workflow.

Participants will be contacted in advance of the workshop with instructions for creating an ACCESS account. Failing to respond in a timely manner may prevent attendees from being
able to work alongside the presenter in real time.

The registration for the workshop will close on 10/16/2025 to allow time to set-up user accounts.

Presented by Ben Keene

Prompt engineering is a critical skill for effectively leveraging large language models (LLMs) in both research and applied domains. This workshop provides a structured introduction to the principles and techniques of prompt design, focusing on how carefully crafted prompts can influence model behavior to yield accurate, relevant, and purpose-driven responses.

Participants will explore foundational strategies such as role-based prompting, task framing, step-by-step reasoning, and few-shot learning. The session emphasizes practical methodologies for enhancing the clarity, consistency, and reliability of outputs when interacting with large language models (LLMs).

It includes a walkthrough of example prompts, demonstrating how specific changes influence the model’s responses and highlighting key techniques for effective prompt engineering in real-world scenarios.

This workshop is intended for everyone who is interested in developing effective interactions with large language models. While the session is accessible and application-focused, participants are expected to have a basic understanding of prompt engineering concepts and terminology, AI concepts, GPT models or language models will be helpful. The session is designed to be accessible for beginners while offering valuable insights for those looking to apply prompt engineering techniques in academic, educational, or applied research contexts.

Presented by Nafisa Islam