There are many active research projects accessing and applying shared ADNI data. Use the search above to find specific research focuses on the active ADNI investigations. This information is requested annually as a requirement for data access.
| Principal Investigator | |
| Principal Investigator's Name: | Vahid Balazadeh Meresht |
| Institution: | University of Toronto |
| Department: | Computer Science |
| Country: | |
| Proposed Analysis: | We study a methodological usage of privileged information to model Alzheimer's progression. Privileged information is a part of data available during the training phase but not deployment. For example, the time-series progression data for each patient can be seen as privileged information since we only have access to the baselines and initial points of progression during deployment. Our methodological idea is to construct causal graphs relating the privileged information to the input-output data and construct simple predictive functions for each edge in the causal graph. This approach can be seen as an example of regularization in classic machine learning methods. |
| Additional Investigators | |
| Investigator's Name: | Jinyu Hou |
| Proposed Analysis: | We study a methodological usage of privileged information to model Alzheimer's progression. Privileged information is a part of data available during the training phase but not deployment. For example, the time-series progression data for each patient can be seen as privileged information since we only have access to the baselines and initial points of progression during deployment. Our methodological idea is to construct causal graphs relating the privileged information to the input-output data and construct simple predictive functions for each edge in the causal graph. This approach can be seen as an example of regularization in classic machine learning methods. |
