This study investigates the use of Riemannian geometry to detect and monitor physiological states such as mental workload (MWL) from an EEG dataset collected in an aeronautical context. The analysis, based on EEG data recorded from 14 participants performing a Simon’s task after inducing MWL by the Multi Attribute Task Battery-II (MATB), aimed to differentiate low and high workload conditions while tracking MWL effect over time. Using covariance matrices and a Minimum Distance to Mean classifier, Temporal Generalization Method (TGM) was used to assess stable decoding performance, indicating a consistent neural signature of MWL throughout the trials. Results demonstrate spatial effects of mental workload irrespective of the investigated time domain: spatial information is distributed evenly across all explored timescale.

Abstract

This thesis investigates visual search through the lens of the dual visual pathways found in biological systems : the ventral (“what”) pathway, involved in object recognition, and the dorsal (“where”) pathway, responsible for spatial localisation and saccadic planning. Drawing from both neuroscience and computer vision, we propose a computational framework that integrates deep convolutional neural networks (DCNNs) within a biologically inspired architecture grounded in foveal retinotopy. As a proof of concept, prior work has demonstrated that incorporating saccadic planning improves digit categorisation performance in a controlled environment. Building upon this foundation, the primary objective of this thesis is to extend the computational framework to natural images in more ecologically valid settings. Our contributions are as follows : (1) We introduce a novel framework for training and evaluating DCNNs using semantically grounded, task-specific labels ; (2) We bridge the gap between artificial models and biological substrates by emphasizing the role of foveal retinotopy in robust object categorisation and precise localisation ; (3) We disentangle the interplay between categorisation and localisation by proposing a novel “localisation-frame” dataset, aimed at guiding the design of a biologically plausible dorsal stream model ; and (4) We present an initial model of the dorsal pathway, leveraging the new dataset to develop interpretable and efficient active vision systems—where interpretability is achieved through modular and spatially structured representations, and efficiency is reflected in reduced computational cost during inference with saccade planning. Overall, this thesis extends the dual-stream computational paradigm for visual search, contributes tools for explainable active vision, and offers a platform to explore hypotheses about functional specialisation in the human visual cortex.

The visual systems of animals work in diverse and constantly changing environments where organism survival requires effective senses. To study the hierarchical brain networks that perform visual information processing, vision scientists require suitable tools, and Motion Clouds (MCs)—a dense mixture of drifting Gabor textons—serve as a versatile solution. Here, we present an open toolbox intended for the bespoke use of MC functions and objects within modeling or experimental psychophysics contexts, including easy integration within Psychtoolbox or PsychoPy environments. The toolbox includes output visualization via a Graphic User Interface. Visualizations of parameter changes in real time give users an intuitive feel for adjustments to texture features like orientation, spatiotemporal frequencies, bandwidth, and speed. Vector calculus tools serve the frame-by-frame autoregressive generation of fully controlled stimuli, and use of the GPU allows this to be done in real time for typical stimulus array sizes. We give illustrative examples of experimental use to highlight the potential with both simple and composite stimuli. The toolbox is developed for, and by, researchers interested in psychophysics, visual neurophysiology, and mathematical and computational models. We argue the case that in all these fields, MCs can bridge the gap between well- parameterized synthetic stimuli like dots or gratings and more complex and less controlled natural videos.

Accurate time-series forecasting is essential across a multitude of scientific and industrial domains, yet deep learning models often struggle with challenges such as capturing long-term dependencies and adapting to drift in data distributions over time. We introduce Future-Guided Learning, an approach that enhances time-series event forecasting through a dynamic feedback mechanism inspired by predictive coding. Our approach involves two models: a detection model that analyzes future data to identify critical events and a forecasting model that predicts these events based on present data. When discrepancies arise between the forecasting and detection models, the forecasting model undergoes more substantial updates, effectively minimizing surprise and adapting to shifts in the data distribution by aligning its predictions with actual future outcomes. This feedback loop, drawing upon principles of predictive coding, enables the forecasting model to dynamically adjust its parameters, improving accuracy by focusing on features that remain relevant despite changes in the underlying data. We validate our method on a variety of tasks such as seizure prediction in biomedical signal analysis and forecasting in dynamical systems, achieving a 40% increase in the area under the receiver operating characteristic curve (AUC-ROC) and a 10% reduction in mean absolute error (MAE), respectively. By incorporating a predictive feedback mechanism that adapts to data distribution drift, Future-Guided Learning offers a promising avenue for advancing time-series forecasting with deep learning.

Temporal sequences are an important feature of neural information processing in biology. Neurons can fire a spike with millisecond precision, and, at the network level, repetitions of spatiotemporal spike patterns are observed in neurobiological data. However, methods for detecting precise temporal patterns in neural activity suffer from high computational complexity and poor robustness to noise, and quantitative detection of these repetitive patterns remains an open problem. Here, we propose a new method to extract spike patterns embedded in raster plots using a 1D convolutional autoencoder with the Earth Mover’s Distance (EMD) as a loss function. Importantly, the properties of the EMD make the method suitable for spike-based distributions, easy to compute, and robust to noise. Through gradient descent, the autoencoder is trained to minimize the EMD between the input and its reconstruction. We then expect the weight matrices to learn the repeating spike patterns present in the data. We validate our method on synthetically generated raster plots and compare its performance with an autoencoder trained using the Mean Squared Error (MSE) as a loss function. We show that the method using the EMD performs better at detecting the occurrence of the spike patterns, while the method using the MSE is better at capturing the underlying distributions used to generate the spikes. Finally, we propose to train the autoencoder iteratively by sequentially combining the EMD and the MSE losses. This sequential approach outperforms the widely used seqNMF method in terms of robustness to various types of noise, speed and stability. Overall, our method provides a novel approach to reliably extract repetitive temporal spike sequences, and can be readily generalized to other sequence detection applications.

This study investigates the use of Riemannian geometry to classify mental workload from an EEG dataset collected in an aeronautical context. The analysis, based on EEG data recorded from 16 participants performing a Simon task, aimed to differentiate low and high workload conditions. Using covariance matrices and a Minimum Distance to Mean (MDM) classifier, the results demonstrate spatial effects of mental workload irrespective of the investigated spectral domain. This demonstrates that spatial information is distributed evenly across all explored frequency bands.