Titulo Estágio
Spiking Neural Networks Learning and Inference for Biased, Imbalanced and Dynamic Data
Áreas de especialidade
Sistemas Inteligentes
Local do Estágio
DEI
Enquadramento
Deep Neural Networks (DNNs) have exhibited remarkable capabilities in various applications, showcasing their power as models. However, it is important to acknowledge that DNNs also impose significant demands in terms of data, energy, and computational resources. These requirements can limit their applicability in critical domains such as public policy, security/safety systems, health diagnosis, and fraud detection, where the availability of such resources is crucial.
Conversely, Spiking Neural Networks (SNNs) bear a closer resemblance to biological neurons, displaying characteristics such as sparsity and energy efficiency. While these advantages make SNNs appealing, training them remains a challenging task primarily due to the intricate dynamics and the non-differentiability of spike operations.
This internship aims to investigate and implement learning mechanisms in spiking neural models, specifically focusing on biased, imbalanced, and dynamic data with application in the context of financial applications. The internship is part of the NextGenAI - Center for responsible AI - Project, which is dedicated to finding solutions in the field of artificial intelligence for the market establishment of responsible and sustainable AI products.
Objetivo
In this internship the student should study, propose, implement, and test methods for explainability and trustworthiness in spiking neural networks
To achieve this goal, the following objectives will be pursued:
- Study the state of the art
- Study the available frameworks for model development
- Define case studies for Biased, Imbalanced and Dynamic Data
- Define, implement, and fine tune a spiking neural network architecture
- Propose and deploy test setup
Plano de Trabalhos - Semestre 1
- Literature review
- Identification and study of learning and inference in SNNs
- Identification and study of available tools
- Analyse and define case studies
- Define the proposed approach for learning with dynamic data
- Write intermediate report
Plano de Trabalhos - Semestre 2
- Implement the proposed solution and fine tune models
- Test and evaluate performance
- Write the final thesis report
- Write a scientific article
Condições
The internship will be held at the Laboratory of Artificial Neural Networks (LARN-CISUC).
The selected student should possess a strong motivation to conduct research in the fields of artificial intelligence, machine learning, and data science.
A potential research grant of 930€/month will be available under the research program of the NextGenAI - Centre For Responsible AI project, supported by the National Recovery and Resilience Plan (PRR). The grant will be dependent of the student's performance during the 1s semester internship.
Orientador
Prof Bernardete RIbeiro / Prof Catarina Silva
bribeiro@dei.uc.pt 📩