Posted: 12-10-2024

Title: Human-Guided System Adaptation

Location: Army Research Lab – Aberdeen Proving Ground – Aberdeen, MD

Description: AI is a quickly evolving tool, that when used properly, can assist both soldiers and civilians alike. But, AI is not yet able to adapt as efficiently or as effectively as humans. We (humans) are highly adaptable and can adjust to a wide variety of situations quickly and without any additional training. On the other hand, current AI systems need large amounts of situation-specific training to become effective and useful, and when the situation changes, it can completely confuse the system. This project will look at the creation and modification of human-guided adaptation approaches; a method that uses the human to inject adaptability into intelligent systems, reducing training time, cost, and errors. A few potential research questions include: How can humans intuitively adapt intelligent systems for new uses, environments, and situations? How can intelligent systems take in and use human feedback and experience?

Requirements: Programming skills are required. Additional consideration will be given to applicants with experience with psychology, data processing, machine learning, and systems engineering.

Level: Multiple Classifications

Required Major(s): Computer science, Data science, Psychology, and Engineering. Other relevant majors will be considered.

  • Find a Volunteering Opportunity

    Visit our Program Volunteers page for a tool to find the best opportunity for you.

    BROWSE OPPORTUNITIES

  • eCYBERMISSION Grants

    The eCYBERMISSION Mini-Grant is intended to support teachers/program leaders as they implement eCYBERMISSION with their teams. Educators (formal and informal) of students in grades 6-9 are encouraged to apply. Special consideration is given to Title 1 schools and to those with underserved/ under-represented populations.

    LEARN MORE

  • Latest AEOP News

    Guiding the Next Generation: Meet the Engineers Inspiring Young Minds at Picatinny Arsenal JSS, November 20, 2024

    See Story

  •