Titulo Estágio
Exploring Spiking Neural Networks towards more energy-efficient machine learning solutions
Áreas de especialidade
Sistemas Inteligentes
Sistemas Inteligentes
Local do Estágio
Laboratory of Artificial Neural Networks (LARN-CISUC)
Enquadramento
Recent years have been highly prolific in Artificial Intelligence (AI) and Machine Learning (ML) advancements culminating in increasingly powerful and complex solutions. However, despite their clear advantages, most of these solutions end up as closed systems that hardly explain how their results were generated. This may reduce the trust in such systems, limiting their adoption and full potential, especially when integrated into sensitive decision-making processes. The project NextGenAI – Centre for Responsible AI aims to find solutions in ‘responsible artificial intelligence’. By developing strategies based on three fundamental pillars – explainability, transparency and sustainability – the objective is to evaluate and address the potential risks of current AI and ML technologies, such as, for example, bias, model opacity and lack of interpretability, high data and energy consumption, and black box design. The participation of CISUC includes the development of algorithms allowing the creation of transparent, fair, reliable and energy-efficient models necessary for the market establishment of responsible and sustainable AI products.
Objetivo
Artificial Neural Networks (ANNs) are widely known for their success and ubiquity in a vast number of domains. However, such solutions are also highly demanding in terms of data, energy, and computational resources. By closely mimicking the real mechanisms of biological neurons, Spiking Neural Networks (SNNs) promise to increase energy and computational efficiency, especially if implemented in neuromorphic hardware. In the context of NextGenAI, the objective of this internship is twofold: first, to conduct a thorough literature review on SNNs, as well as to explore the currently available libraries/frameworks implementing such models; second, through an empirical setting, study and compare the energy-saving gains of SNNs versus traditional ANNs. This comparison will utilize the Bank Account Fraud (BAF) datasets suite, publicly provided and maintained by Feedzai, and established benchmark data sets such as MNIST. The internship should provide the candidate with an increased awareness of energy-efficient and sustainable issues to modern AI solutions.
Plano de Trabalhos - Semestre 1
1. State of the art review
2. Review and ranking of libraries and frameworks delivering implementations of SNNs.
3. Draft an experimental setting (methodology, models, tools, data sets (BAF suite, well-known benchmarks, etc.), performance metrics, etc.) for supporting the future empirical study comparing SNNs against traditional ANNs, focusing on energy-efficiency outcomes. It should also consider the use of neuromorphic hardware.
4. Writing of the intermediate internship report.
Plano de Trabalhos - Semestre 2
5. Review and execute the final experimental setting.
6. Explore, analyse, and discuss the results from an energy-saving and sustainable point of view, and analyse the real-world gains of deploying SNNs to neuromorphic hardware.
7. Preparation of a paper for a conference or journal (to be determined).
8. Writing and submission of the thesis.
Condições
The internship will take place at the Laboratory of Artificial Neural Networks (LARN-CISUC) with regular meetings with the supervision team. The candidate should be strongly motivated to conduct research in the areas of artificial intelligence, machine learning and data science. Experience in Python and ANN is essential, as well as in related machine learning algorithms and software/programming tools. Besides the laboratory itself, the selected candidate will be integrated within the research team currently working on the ongoing project NextGenAI – Centre For Responsible AI, supported by the National Recovery and Resilience Plan (PRR) and the Next Generation EU Funds.
Observações
A research grant opportunity, supported by the abovementioned project, may become available during the internship.
Orientador
Francisco José Nibau Antunes
fnibau@dei.uc.pt 📩