The nature of statistical learning theory
The nature of statistical learning theory
Learning to Decode Cognitive States from Brain Images
Machine Learning
| Hi-index | 0.00 |
Functional magnetic resonance imaging (fMRI) has provided an invaluable method of investing real time neuron activities. Statistical tools have been developed to recognise the mental state from a batch of fMRI observations over a period. However, an interesting question is whether it is possible to estimate the real time mental states at each moment during the fMRI observation. In this paper, we address this problem by building a probabilistic model of the brain activity. We model the tempo-spatial relations among the hidden high-level mental states and observable low-level neuron activities. We verify our model by experiments on practical fMRI data. The model also implies interesting clues on the task-responsible regions in the brain.