Robustness

Three-year salaried doctoral appointment studying the expressivity, robustness and verification of neural models of automata. The project connects systems theory, statistics, optimization and formal methods, examining recurrent networks, attention mechanisms and state-space models. Work includes theoretical analysis, experimental algorithms and scientific publication. The advertised gross monthly salary is €2,300. The advert lists an October 2026 target start alongside a November application deadline; applicants should confirm start-date flexibility.

…It also considers interpretability, robustness and responsible deployment. The programme combines keynotes, research presentations and a discussion of the gap between architectural ideas and real-world systems. Workshop W05 runs from 08:30 to 12:00 local time. Paper submissions closed on 20 August and camera-rea

…This creates robustness problems for axiomatic reconstructions based on generalized probabilistic theories. The talk introduces an operational alternative that treats a state as an observer's knowledge, aiming to compare possible physical theories while avoiding instability under small changes of the theory.

…relationship between memory and mood, robustness and fragility, modelling, standardisation and iterative changes in how researchers frame the problems they study.

Neural dynamics represent the hard-to-interpret substrate of circuit computations. Advances in large-scale recordings have highlighted the sheer spatiotemporal complexity of circuit dynamics within and across circuits, portraying in detail the difficulty of interpreting such dynamics and relating it to computation. Indeed, even in extremely simplified experimental conditions, one observes high-dimensional temporal dynamics in the relevant circuits. This complexity can be potentially addressed by the notion that not all changes in population activity have equal meaning, i.e., a small change in

Memories are thought to be stored in synapses and retrieved through the reactivation of neural ensembles. However, neural representations exhibit significant dynamics even in stable environments, a phenomenon called representational drift. Theoretical studies suggest that multiple neural representations can correspond to a memory, with post-learning exploration of these representation solutions driving drift. However, the functional implications of drift-explored representations versus those initially learned remain poorly understood. Here we show that drift uncovers robust, sparsely engaged r

The ability to maintain a stable state in the presence of perturbations, known as robustness, is a defining feature of living systems. Most animals demonstrate adaptability by adjusting their position when confronted with external stimuli, a crucial skill for survival. How the brain dynamically regulates behavior in response to a changing environment remains a fundamental question in neuroscience. We investigated it using Danionella cerebrum, the smallest known vertebrate amenable to brain-wide functional imaging at cellular resolution across all developmental stages. We developed a 2D virtual

Since the introduction of the term explainable artificial intelligence, many contrasting definitions and methods have been proposed. A key issue is that most of the extant explanations are not sufficiently clear either to practitioners or to users. While some researchers use interpretation algorithms as post-hoc explanations (Samek et al., 2021; Ribeiro, 2016), others argue that we should use models which are interpretable in the first place (Rudin, 2019). Although the latter is important, developers are not always willing to sacrifice accuracy by choosing a less complex interpretable model. H

Neural systems are remarkably robust against various perturbations, a phenomenon that still requires a clear explanation. Here, we graphically illustrate how neural networks can become robust. We study spiking networks that generate low-dimensional representations, and we show that the neurons’ subthreshold voltages are confined to a convex region in a lower-dimensional voltage subspace, which we call a ‘bounding box.’ Any changes in network parameters (such as number of neurons, dimensionality of inputs, firing thresholds, synaptic weights, or transmission delays) can all be understood as def

…(and neuroscience) results robustness and re-usability.

…raising the question of what controls robustness, one of the essential functions of an oscillator. We computationally generate an atlas of oscillators and found that, while core topologies are critical for oscillations, local structures substantially modulate the degree of robustness. Strikingly, two local structures, incoherent and coherent inputs, can modify a core topology to promote and attenuate its robustness, additively. The findings underscore the importance of local modificat