Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
mrtools:classificationtoolsnew [2014/10/24 15:36]
tsliu
mrtools:classificationtoolsnew [2014/10/24 15:42] (current)
tsliu
Line 38: Line 38:
   - Classification (on orientation) results are largley consistent with the results mentioned above (when collapsing across contrast).   - Classification (on orientation) results are largley consistent with the results mentioned above (when collapsing across contrast).
   - There is not much difference in classification accuracy between low and high contrast. One might expect high contrast to be classified better, but not quite the case here (there might be some minor improvements but subtle).   - There is not much difference in classification accuracy between low and high contrast. One might expect high contrast to be classified better, but not quite the case here (there might be some minor improvements but subtle).
-  - For classification,​ two decon method were tried to get instances: 1-gamma fit and 2-gamma fit. 1-gamma ​outperforms ​2-gamma for block design, but the two are similar ​for event-related design. ​+  - For classification,​ two decon method were tried to get instances: 1-gamma fit and 2-gamma fit. 1-gamma ​seems to give better accuracy than 2-gamma, especially ​for block design ​(less so for event-related design), even though 2-gamma seems to fit the HRF better (judging from the figure shown by fitTimecourse)
  
 ===== Further things to consider ===== ===== Further things to consider =====