Author name cluster

Flavia Vitale

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

3 papers

2 author rows

NeurIPS Conference 2025 Conference Paper

A Scalable, Causal, and Energy Efficient Framework for Neural Decoding with Spiking Neural Networks

Georgios Mentzelopoulos
Ioannis Asmanis
Konrad Kording
Eva L Dyer
Kostas Daniilidis
Flavia Vitale

Brain-computer interfaces (BCIs) promise to enable vital functions, such as speech and prosthetic control, for individuals with neuromotor impairments. Central to their success are neural decoders, models that map neural activity to intended behavior. Current learning-based decoding approaches fall into two classes: simple, causal models that lack generalization, or complex, non-causal models that generalize and scale offline but struggle in real-time settings. Both face a common challenge, their reliance on power-hungry artificial neural network backbones, which makes integration into real-world, resource-limited systems difficult. Spiking neural networks (SNNs) offer a promising alternative. Because they operate causally (i. e. only on present and past inputs) these models are suitable for real-time use, and their low energy demands make them ideal for battery-constrained environments. To this end, we introduce Spikachu: a scalable, causal, and energy-efficient neural decoding framework based on SNNs. Our approach processes binned spikes directly by projecting them into a shared latent space, where spiking modules, adapted to the timing of the input, extract relevant features; these latent representations are then integrated and decoded to generate behavioral predictions. We evaluate our approach on 113 recording sessions from 6 non-human primates, totaling 43 hours of recordings. Our method outperforms causal baselines when trained on single sessions using between 2. 26× and 418. 81× less energy. Furthermore, we demonstrate that scaling up training to multiple sessions and subjects improves performance and enables few-shot transfer to unseen sessions, subjects, and tasks. Overall, Spikachu introduces a scalable, online-compatible neural decoding framework based on SNNs, whose performance is competitive relative to state-of-the-art models while consuming orders of magnitude less energy.

PDF Details

NeurIPS Conference 2024 Conference Paper

Neural decoding from stereotactic EEG: accounting for electrode variability across subjects

Georgios Mentzelopoulos
Evangelos Chatzipantazis
Ashwin G. Ramayya
Michelle J. Hedlund
Vivek P. Buch
Kostas Daniilidis
Konrad P. Kording
Flavia Vitale

Deep learning based neural decoding from stereotactic electroencephalography (sEEG) would likely benefit from scaling up both dataset and model size. To achieve this, combining data across multiple subjects is crucial. However, in sEEG cohorts, each subject has a variable number of electrodes placed at distinct locations in their brain, solely based on clinical needs. Such heterogeneity in electrode number/placement poses a significant challenge for data integration, since there is no clear correspondence of the neural activity recorded at distinct sites between individuals. Here we introduce seegnificant: a training framework and architecture that can be used to decode behavior across subjects using sEEG data. We tokenize the neural activity within electrodes using convolutions and extract long-term temporal dependencies between tokens using self-attention in the time dimension. The 3D location of each electrode is then mixed with the tokens, followed by another self-attention in the electrode dimension to extract effective spatiotemporal neural representations. Subject-specific heads are then used for downstream decoding tasks. Using this approach, we construct a multi-subject model trained on the combined data from 21 subjects performing a behavioral task. We demonstrate that our model is able to decode the trial-wise response time of the subjects during the behavioral task solely from neural data. We also show that the neural representations learned by pretraining our model across individuals can be transferred in a few-shot manner to new subjects. This work introduces a scalable approach towards sEEG data integration for multi-subject model training, paving the way for cross-subject generalization for sEEG decoding.

PDF Details DOI

ICRA Conference 2010 Conference Paper

Low-temperature H2O2-powered actuators for biorobotics: Thermodynamic and kinetic analysis

Flavia Vitale
Dino Accoto
Luca Turchetti
Stefano Indini
Maria Cristina Annesini
Eugenio Guglielmelli

The need for novel, high performance actuators felt in several fields of robotics, such as assistive or rehabilitative robotics, is not fully satisfied by current actuation means. This fosters an intense research on novel energy transduction methods. In particular, propellant-based chemical actuators, able to directly convert chemical energy into mechanical energy, appear very promising, although their potential in robotics has not yet been deeply investigated. This work focuses on H 2 O 2, used as propellant for actuators. This chemical was first used in robotics, with excellent results, by Goldfarb and collaborators, in 2003. H 2 O 2 dissociation is strongly exothermic, which generates important design issues when the actuated machine operates in close proximity to the human body. In this paper it is shown that: 1) is possible to operate the decomposition process at acceptable temperature, by means of basic solutions of hydrogen peroxide; 2) for basic pH solutions, tin becomes an effective catalyst for H 2 O 2 dissociation. A kinetic model of H 2 O 2 dissociation in basic solutions is provided, that is in good agreement with experimental data. We show how the model can be used to gather the necessary information for the dimensioning of H 2 O 2 -based actuators.

Details