The One Million Bit Question – Memory
I am interested in the interception of brain research and neural AI models. Above all, Spiking Neural Networks (SNNs) seem like the most biologically interpretable AI models, which makes me curious what we can achieve with this new paradigm and what insights it will allow in the brain. SNNs show promising performance on classic AI tasks and they fill a bunch of neuromorphic hardware solutions with life, such as Intel’s Loihi 2 chip.
I am currently performing a literature review on and around the general topic of computational models of the brain and neuromorphic hardware (NMH).
Also, as a private external collaborator I joined the Barcelona Artificial Intelligence in Medicine Lab, Faculty of Mathematics and Computer Science, University of Barcelona. There we strive to enhance the AI-powered automatic analysis of mammography data.
During my Master’s thesis at The University of Edinburgh I applied Convolutional Neural Networks (CNNs) to the classification of Zebrafish swim bout movements. Using recent AI explainability techniques, I visualized the features learnt by the CNN which allowed me to correct misleading artefacts in the underlying data.