"A new federated learning adaptation of AdaBoost"

AEMCO Congress, Oral presentation

Sevilla, Spain, September 2024

The rise of artificial intelligence has been accompanied by an explosion in the amount of data, leading to growing concerns about privacy and data management. Federated Learning allows training artificial intelligence models with distributed data, respecting privacy and accessing large volumes of information without exposing sensitive data. This conference talk introduces Federated Learning (FL), gives an example of a novel FL algorithm and highlights possible FL applications to Health and Social Sciences.

"Delayed Spiking Neural Networks for Neuromorphic Computing"

AIHUB's Connexion Summer School, Poster presentation

Valencia, Spain, July 2024

Spiking Neural Networks (SNNs) are emergent models that offer a biologically plausible alternative to Artificial Neural Networks (ANNs) by computing in terms of discrete spikes (a.k.a. events) instead of real-valued activations. Some advantages of SNNs include sparsity, efficiency, and their natural ability to process time-series. Previous research has demonstrated that incorporating learnable synaptic delays in SNNs enhances their ability to learn temporal features while reducing the required number of layers and parameters. This poster covers a study on the performance of SNNs using learnable synaptic delays when used to classify a neuromorphic spatio-temporal dataset.