Scholarship 22/16075-9 - Aprendizado computacional, Aprendizagem profunda - BV FAPESP
Advanced search
Start date
Betweenand

Investigation of Explanation Methods for Deep Learning

Grant number: 22/16075-9
Support Opportunities:Scholarships in Brazil - Scientific Initiation
Start date until: December 01, 2022
End date until: November 30, 2023
Field of knowledge:Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
Principal Investigator:Solange Oliveira Rezende
Grantee:Ramon Moreira Machado
Host Institution: Instituto de Ciências Matemáticas e de Computação (ICMC). Universidade de São Paulo (USP). São Carlos , SP, Brazil
Associated research grant:19/17721-9 - The role of Chemistry in holobiont adaptation, AP.TEM

Abstract

Data mining has been successfully applied in several domains to extract knowledge from different media types. In the context of images, part of this process can be supported by deep learning methods, including convolutional neural networks. State-of-the-art in many visual recognition tasks, these methods can learn directly from unstructured data. However, they are generally perceived as black boxes, making their decision less understandable to humans and restricting their usage in certain applications. This project aims to investigate explanation methods derived from explainable artificial intelligence to help confirm, contest and/or build novel assumptions about the knowledge acquired by deep learning models for classifying small and large microorganism image sets. We will evaluate and validate the researched explanation methods with the support of clinical microbiologists, especially those seeking to discover original bioactive compounds with pharmacological potential.

News published in Agência FAPESP Newsletter about the scholarship:
More itemsLess items
Articles published in other media outlets ( ):
More itemsLess items
VEICULO: TITULO (DATA)
VEICULO: TITULO (DATA)

Please report errors in scientific publications list using this form.