Adaptive Tests for Memory Training using Asymmetric Search Point Location

Memory training exercises are known to have a positive effect on improving the memorability of humans. A memory training task can be as simple as trying to remember a password of increasing complexity or a number of varying length.
Master

Memorability concept has been mostly investigated on the images using Machine Learning [1]. However, there is no measure available in the literature that can assess the difficulty of remembering a given password (word) or number. In this project, we will conduct a controlled experiment on sets of students in order to come up with a new difficulty measure that quantifies the memorability of a string (whether it is - a word or a number). As an alternative way forward we might rather use images ranked according to their memorability using Machine Learning as a way for ranking memorability [1].

We will also devise an adaptive method for varying the difficulty of the tests in an online manner based upon the ability of the subject to pass or fail in a test [2]. The approach is based on asymmetric version of the Search Point Location (SPL) [2] which is different from the main stream of work which falls under the class of symmetric SPL.

Goal

The outcomes of the project has potential for being published in a conference or journal venue.

Learning outcome

  • Insight into advanced techniques of machine learning
  • Working on a real world application
  • Collaboration with researchers in the topic of machine learning, specifically deep learning
  • Possibility to implement and research a novel approach

Qualifications

  • Mathematics
  • Programming
  • Motivation

Supervisors

Collaboration partners

  • OsloMet
  • Epigram

References

[1] Isola, P., Xiao, J., Torralba, A., Oliva, A. What makes an image memorable? IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2011. Pages 145-152.
[2] Asieh Abolpour Mofrad, Anis Yazidi, and Hugo Lewi Hammer. "Solving Stochastic Point Location Problem in a Dynamic Environment with Weak Estimation." Proceedings of the International Conference on Research in Adaptive and Convergent Systems. ACM, 2017.