Project work 3 (1-st dl 2nd February at 10:00)
The goal of this week’s project work is to do classification analysis on the fMRI dataset.
(1) Divide the data to testing & training (e.g., odd vs even runs; see lecture slides for other options)
(2) Use, for example, pattern-correlation classifier
- calculate within and between category correlations, (matlab function: ‘corr.m’)
- compare the correlation values within and between categories
(3) Apply the classifier to data from different ROIs (see project work 2)
(4) Can you replicate the results by Haxby et al 2001? See Lecture 3 and/or https://www.ncbi.nlm.nih.gov/pubmed/11577229.
(4) What can you conclude about the object representations based on the results?
Return the first version of your project work by Tuesday, February 2, at 10:00. Even if you have had trouble with the analysis, do return something that we can then discuss during the Tuesday's Q&A session. You will get 5 points for returning your preliminary results and actively contributing during the Q&A session.