×
  • Select the area you would like to search.
  • ACTIVE INVESTIGATIONS Search for current projects using the investigator's name, institution, or keywords.
  • EXPERTS KNOWLEDGE BASE Enter keywords to search a list of questions and answers received and processed by the ADNI team.
  • ADNI PDFS Search any ADNI publication pdf by author, keyword, or PMID. Use an asterisk only to view all pdfs.
Principal Investigator  
Principal Investigator's Name: Mariano Ntrougkas
Institution: CEnter for Research & Technology Hellas
Department: Information Technologies Institute
Country:
Proposed Analysis: I am developing a trainable attention mechanism for explaining the decisions made by multiclass classifier neural networks. This method requires training the attention mechanism on the dataset in which the initial network was trained on. I would like to apply this method on Alzheimer's disease classifier networks to examine its effectiveness for a domain in which explainable AI is important i.e. the medical field. In my domain research, I have concluded that this dataset is vitally important for any research on Alzheimer's disease, and I will not be able to evaluate the effectiveness of the explainability method without it.
Additional Investigators