Seminar: Research Revolution: How Deep Research is Changing the Paradigm of Search and Exploration

Europe/Ljubljana
ZOOM

ZOOM

https://uni-lj-si.zoom.us/j/96474402658
Janez Križaj, Janez Perš (UL FE)
Description

Date & time & place: March 13th, 13.05-14.00, Zoom.

Short description: This seminar offers a practical introduction to Deep Research, OpenAI's advanced AI tool designed to autonomously conduct in-depth research and generate comprehensive reports. Participants will learn how to effectively utilize Deep Research for tasks such as patent exploration, scientific literature reviews, and related work analysis in various engineering and scientific domains. Through live demonstrations and best practice showcases, attendees will gain hands-on experience in optimizing queries and interpreting results, enabling them to integrate AI-assisted research into their workflows efficiently.

Description: In the rapidly evolving landscape of artificial intelligence, OpenAI's Deep Research stands out as a groundbreaking tool that emulates human-like reasoning to autonomously perform complex research tasks. This seminar is tailored for engineers, researchers, and students eager to harness the power of AI-driven research assistance in their respective fields.

Deep Research leverages OpenAI's o3 model to autonomously search, analyse, and synthesize information from diverse online sources, including text, images, and PDFs. It operates independently, planning and executing multi-step research trajectories to deliver thorough, documented, and clearly cited reports on intricate topics within minutes. This capability is particularly beneficial for professionals engaged in patent searches, scientific literature reviews, and related work analysis, as it significantly reduces the time and effort required for comprehensive information gathering.

The seminar will commence with a live demonstration, where a real-time Deep Research query on a pertinent engineering topic will be executed, showcasing the tool's capabilities and computational requirements. Following this, a pre-prepared example will be presented to illustrate effective utilization of Deep Research, emphasizing strategies to optimize queries and efficiently interpret results. Subsequent sessions will explore multiple domains, including patent exploration and scientific literature reviews, demonstrating how Deep Research can be applied across various research needs.

By the end of the seminar, participants will have acquired the skills to leverage Deep Research for their projects, enhancing their ability to conduct thorough and efficient research. They will also gain insights into best practices for AI-assisted discovery, enabling them to integrate this advanced tool into their workflows effectively.

Difficulty: Intermediate

Language: English

Prerequisite knowledge: Participants should have a basic understanding of artificial intelligence concepts and familiarity with research methodologies. Prior experience with AI tools or platforms is advantageous but not mandatory.

Target audience: This seminar is designed for engineers, researchers, and students who are keen to enhance their research capabilities using AI-driven tools. It is particularly beneficial for those involved in technical innovation, academic research, or industry applications requiring comprehensive information retrieval and analysis. 

Skills to be gained:

  • Proficiency in utilizing Deep Research for autonomous, in-depth research tasks.
  • Ability to optimize research queries to maximize the efficiency and relevance of AI-generated reports.
  • Experience in interpreting and integrating AI-generated insights into various research workflows. 
  • Understanding of best practices for AI-assisted research, including ethical considerations and verification of AI outputs.

 

Workflow: The seminar will consist of a Deep Research demonstration (3 queries planned), analysis of best practices, and demonstration of its applications in 3 separate research domains (scientific literature search, patent search, technical research). We will start by submitting a first live query, allowing Deep Research to process the request while we discuss its capabilities and best practices, and submit additional queries as the tasks are finished. The session will conclude with a discussion and Q&A.

Virtual location: ZOOM - only registered participants will see ZOOM link!!

Organizer:

Lecturers:

Name: Janez Perš
  Janez Perš is an Associate Professor at the Faculty of Electrical Engineering at the University of Ljubljana. His research areas are computer, machine, and robotic vision, parallel and distributed systems, and human movement analysis. He is the course holder for Embedded Systems, Computer Vision, Imaging Technologies, and Communications in Automation. 
E-mail: janez.pers@fe.uni-lj.si 

 

Name: Janez Križaj
  Janez Križaj is a researcher at the Faculty of Electrical Engineering at the University of Ljubljana. His research areas are deep learning, computer vision, biometrics, face recognition, pattern recognition, and image processing. 
E-mail: janez.krizaj@fe.uni-lj.si 

Registration
Registration
    • 13:05 13:10
      Submitting a live query for processing
      Convener: Prof. Janez Perš (UL FE)
    • 13:10 13:20
      Introduction and overview of Deep Research
      Convener: Prof. Janez Perš (UL FE)
    • 13:20 13:40
      Presentation of best practices, another live query
      Convener: Prof. Janez Perš (UL FE)
    • 13:40 13:50
      Reviewing results of the live query and discussing its findings
      Convener: Prof. Janez Perš (UL FE)
    • 13:50 14:00
      Q&A

      Using appropriate tools you can have basic presentation of your paper ready in about five minutes.

      Convener: Prof. Janez Perš (UL FE)