Publications

The Butterfly Effect: Tiny Perturbations Cause Neural Network Training to Diverge
Neural network training begins with a chaotic phase in which the network is sensitive to small perturbations, such as those caused by stocha… (see more)stic gradient descent (SGD). This sensitivity can cause identically initialized networks to diverge both in parameter space and functional similarity. However, the exact degree to which networks are sensitive to perturbation, and the sensitivity of networks as they transition out of the chaotic phase, is unclear. To address this uncertainty, we apply a controlled perturbation at a single point in training time and measure its effect on otherwise identical training trajectories. We find that both the
TutteNet: Injective 3D Deformations by Composition of 2D Mesh Deformations
Bo Sun
Thibault Groueix
Chen Song
Qixing Huang
Using neural biomarkers to personalize dosing of vagus nerve stimulation
Antonin Berthon
Lorenz Wernisch
Myrta Stoukidi
Michael Thornton
Pascal Fortier-Poisson
Max Pinkney
Susannah Lee
Elvijs Sarkans
Luca Annecchino
Ben Appleton
Philip Garsed
Bret Patterson
Samuel Gonshaw
Matjaž Jakopec
Sudhakaran Shunmugam
Tristan Edwards
Aleksi Tukiainen
Joel Jennings … (see 3 more)
Emil Hewage
Oliver Armitage
Vagus nerve stimulation (VNS) is an established therapy for treating a variety of chronic diseases, such as epilepsy, depression, obesity, a… (see more)nd for stroke rehabilitation. However, lack of precision and side-effects have hindered its efficacy and extension to new conditions. To achieve a better understanding of the relationship between VNS parameters and neural and physiological responses to enable the design of personalized dosing procedures to improve precision and efficacy of VNS therapies. We used biomarkers from recorded evoked neural activity and short-term physiological responses (throat muscle, cardiac and respiratory activity) to understand the response to a wide range of VNS parameters in anaesthetised pigs. Using signal processing, Gaussian processes (GP) and parametric regression models we analyse the relationship between VNS parameters and neural and physiological responses. Firstly, we observe inter-subject variability for both neural and physiological responses. Secondly, we illustrate how considering multiple stimulation parameters in VNS dosing can improve the efficacy and precision of VNS therapies. Thirdly, we describe the relationship between different VNS parameters and the evoked neural activity and show how spatially selective electrodes can be used to improve fibre recruitment. Fourthly, we provide a detailed exploration of the relationship between the activations of neural fibre types and different physiological effects, and show that recordings of evoked neural activity are powerful biomarkers for predicting the short-term physiological effects of VNS. Finally, based on these results, we discuss how recordings of evoked neural activity can help design VNS dosing procedures that optimize short-term physiological effects safely and efficiently. Understanding of evoked neural activity during VNS provide powerful biomarkers that could improve the precision, safety and efficacy of VNS therapies.
Variable Star Light Curves in Koopman Space
Nicolas Mekhaël
Mario Pasquato
GAIA CARENINI
Vittorio F. Braga
PIERO TREVISAN
Giuseppe Bono
The past as an imaginative resource. Hybridity, pattern and adaptation in Alexandru I. Alexandrescu’s historical novel
A.R. Olteanu
Using machine learning to predict student science achievement based on science curriculum type in TIMSS 2019
Yajie Song
A Hybrid CNN-Transformer Approach for Continuous Fine Finger Motion Decoding from sEMG Signals
Zihan Weng
Xiabing Zhang
Yufeng Mou
Chanlin Yi
Fali Li
Peng Xu
This work presents a novel approach that synergistically integrates convolutional neural networks (CNNs) and Transformer models for decoding… (see more) continuous fine finger motions from surface electromyography (sEMG) signals. This integration capitalizes on CNNs’ proficiency in extracting rich temporal and spatial features from multichannel sEMG data and the Transformer’s superior capability in recognizing complex patterns and long-range dependencies. A significant advancement in this field is the use of a custom-developed Epidermal Electrode Array Sleeve (EEAS) for capturing high-fidelity sEMG signals, enabling more accurate and reliable signal acquisition than traditional methods. The decoded joint angles could be used in seamless and intuitive human-machine interaction in various applications, such as virtual reality, augmented reality, robotic control, and prosthetic control. Evaluations demonstrate the superior performance of the proposed CNN-Transformer hybrid architecture in decoding continuous fine finger motions, outperforming individual CNN and Transformer models. The synergistic integration of CNNs and Transformers presents a powerful framework for sEMG decoding, offering exciting opportunities for naturalistic and intuitive human-machine interaction applications. Its robustness and efficiency make it an ideal choice for real-world applications, promising to enhance the interface between humans and machines significantly. The implications of this research extend to advancing the understanding of human neuromuscular signals and their application in computing interfaces.
MiNT: Multi-Network Training for Transfer Learning on Temporal Graphs
Tran Gia Bao Ngo
Kiarash Shamsi
Poupak Azad
Baris Coskunuzer
Cuneyt Gurcan Akcora
Tracing the Ransomware Bloodline: Investigation and Detection of Drifting Virlock Variants
Salwa Razaulla
Claude Fachkha
Amjad Gawanmeh
Christine Markarian
Benjamin C. M. Fung
Chadi Assi
Malware, especially ransomware, has dramatically increased in volume and sophistication in recent years. The growing complexity and destruct… (see more)ive potential of ransomware demand effective countermeasures. Despite tremendous efforts by the security community to document these threats, reliance on manual analysis makes it challenging to discern unique malware variants from polymorphic variants. Moreover, the easy accessibility of source code of prominent ransomware families in public domains has led to the rise of numerous variants, complicating manual detection and hindering the identification of phylogenetic relationships. This paper introduces a novel approach that narrows the focus to analyze one such prominent ransomware family, Virlock. Using binary code similarity, we systematically reconstruct the lineage of Virlock, tracing its relationships, evolution, and variants. Employing this technique on a dataset of over 1000 Virlock samples submitted to VirusTotal and VirusShare, our analysis unveils intricate relationships within the Virlock ransomware family, offering valuable insights into the tangled relationships of this ransomware.
Are we making progress in unlearning? Findings from the first NeurIPS unlearning competition
Eleni Triantafillou
Peter Kairouz
Fabian Pedregosa
Jamie Hayes
Meghdad Kurmanji
Kairan Zhao
Julio C. S. Jacques Junior
Jun Wan
Lisheng Sun-Hosoya
Sergio Escalera
Peter Triantafillou
Isabelle Guyon
We present the findings of the first NeurIPS competition on unlearning, which sought to stimulate the development of novel algorithms and in… (see more)itiate discussions on formal and robust evaluation methodologies. The competition was highly successful: nearly 1,200 teams from across the world participated, and a wealth of novel, imaginative solutions with different characteristics were contributed. In this paper, we analyze top solutions and delve into discussions on benchmarking unlearning, which itself is a research problem. The evaluation methodology we developed for the competition measures forgetting quality according to a formal notion of unlearning, while incorporating model utility for a holistic evaluation. We analyze the effectiveness of different instantiations of this evaluation framework vis-a-vis the associated compute cost, and discuss implications for standardizing evaluation. We find that the ranking of leading methods remains stable under several variations of this framework, pointing to avenues for reducing the cost of evaluation. Overall, our findings indicate progress in unlearning, with top-performing competition entries surpassing existing algorithms under our evaluation framework. We analyze trade-offs made by different algorithms and strengths or weaknesses in terms of generalizability to new datasets, paving the way for advancing both benchmarking and algorithm development in this important area.
Exploring validation metrics for offline model-based optimisation
In offline model-based optimisation (MBO) we are interested in using machine learning to de-sign candidates that maximise some measure of d… (see more)esirability through an expensive but real-world scoring process. Offline MBO tries to approximate this expensive scoring function and use that to evaluate generated designs, however evaluation is non-exact because one approximation is being evaluated with another. Instead, we ask ourselves: if we did have the real world scoring function at hand, what cheap-to-compute validation metrics would correlate best with this? Since the real-world scoring function is available for simulated MBO datasets, insights obtained from this can be transferred over to real-world offline MBO tasks where the real-world scoring function is expensive to compute. To address this, we propose a conceptual evaluation framework that is amenable to measuring extrapolation, and apply this to conditional denoising diffusion models. Empirically, we find that two validation metrics – agreement and Frechet distance – correlate quite well with the ground truth. When there is high variability in conditional generation, feedback is required in the form of an approximated version of the real-world scoring function. Furthermore, we find that generating high-scoring samples may require heavily weighting the generative model in favour of sample quality, potentially at the cost of sample diversity.
GIST: Generated Inputs Sets Transferability in Deep Learning
Florian Tambon
Giuliano Antoniol