Publications

Language Models Can Reduce Asymmetry in Information Markets
Nasim Rahaman
Martin Weiss
Manuel Wuthrich
Yoshua Bengio
Erran L. Li
Christopher Pal
Bernhard Schölkopf
2024-03-20
ArXiv (prépublication)
doi.org
arxiv.org
Multi-resolution continuous normalizing flows.
Vikram Voleti
Chris Finlay
Adam Oberman
Christopher Pal
Recent work has shown that Neural Ordinary Differential Equations (ODEs) can serve as generative models of images using the perspective of C… (voir plus)ontinuous Normalizing Flows (CNFs). Such models offer exact likelihood calculation, and invertible generation/density estimation. In this work we introduce a Multi-Resolution variant of such models (MRCNF), by characterizing the conditional distribution over the additional information required to generate a fine image that is consistent with the coarse image. We introduce a transformation between resolutions that allows for no change in the log likelihood. We show that this approach yields comparable likelihood values for various image datasets, with improved performance at higher resolutions, with fewer parameters, using only one GPU. Further, we examine the out-of-distribution properties of MRCNFs, and find that they are similar to those of other likelihood-based generative models.
2024-03-20
Annals of Mathematics and Artificial Intelligence (inconnu)
doi.org
openreview.net
Assistive sensory-motor perturbations influence learned neural representations
Pavithra Rajeswaran
Alexandre Payeur
Guillaume Lajoie
Amy L. Orsborn
Task errors are used to learn and refine motor skills. We investigated how task assistance influences learned neural representations using B… (voir plus)rain-Computer Interfaces (BCIs), which map neural activity into movement via a decoder. We analyzed motor cortex activity as monkeys practiced BCI with a decoder that adapted to improve or maintain performance over days. Over time, task-relevant information became concentrated in fewer neurons, unlike with fixed decoders. At the population level, task information also became largely confined to a few neural modes that accounted for an unexpectedly small fraction of the population variance. A neural network model suggests the adaptive decoders directly contribute to forming these more compact neural representations. Our findings show that assistive decoders manipulate error information used for long-term learning computations like credit assignment, which informs our understanding of motor learning and has implications for designing real-world BCIs.
2024-03-19
bioRxiv (prépublication)
doi.org
Dual quantum spin Hall insulator by density-tuned correlations in TaIrTe4.
Jian Tang
Thomas Siyuan Ding
Hongyu Chen
Anyuan Gao
Tiema Qian
Zumeng Huang
Zhe Sun
Xin Han
Alex Strasser
Jiangxu Li
Michael Geiwitz
Mohamed Shehabeldin
Vsevolod Belosevich
Zihan Wang
Yiping Wang
Kenji Watanabe
Takashi Taniguchi
David C. Bell
Ziqiang Wang
Liang Fu … (voir 8 de plus)
Yang Zhang
Xiaofeng Qian
Kenneth S. Burch
Youguo Shi
Ni Ni
Guoqing Chang
Su-Yang Xu
Qiong Ma
2024-03-19
Nature (publié)
doi.org
arxiv.org
Two-stage Multiple-Model Compression Approach for Sampled Electrical Signals
Corentin Presvôts
Michel Kieffer
Thibault Prevost
Patrick Panciatici
Zuxing Li
Pablo Piantanida
This paper presents a two-stage Multiple-Model Compression (MMC) approach for sampled electrical waveforms. To limit latency, the processing… (voir plus) is window-based, with a window length commensurate to the electrical period. For each window, the first stage compares several parametric models to get a coarse representation of the samples. The second stage then compares different residual compression techniques to minimize the norm of the reconstruction error. The allocation of the rate budget among the two stages is optimized. The proposed MMC approach provides better signal-to-noise ratios than state-of-the-art solutions on periodic and transient waveforms.
2024-03-18
Data Compression Conference (publié)
doi.org
Reinforcement learning for freight booking control problems
Justin Dumouchelle
Emma Frejinger
Andrea Lodi
2024-03-15
Journal of Revenue and Pricing Management (publié)
doi.org
arxiv.org
Normalizing Spinal Cord Compression Morphometric Measures: Application in Degenerative Cervical Myelopathy
Sandrine Bédard
Jan Valosek
Maryam Seif
Armin Curt
Simon Schadings
M.Sc
Nikolai Pfender
Patrick Freund
Markus Hupp
Julien Cohen-Adad
The study introduced an automatic method for computation of normalized MSCC measures of cord compression from MRI scans, which is an importa… (voir plus)nt step towards better informed therapeutic decisions in DCM patients. The method is open-source and available in the Spinal Cord Toolbox v6.0.
2024-03-14
medRxiv (prépublication)
doi.org
Safety Cases: How to Justify the Safety of Advanced AI Systems
Joshua Clymer
Nick Gabrieli
David M. Krueger
T. Larsen
As AI systems become more advanced, companies and regulators will make difficult decisions about whether it is safe to train and deploy them… (voir plus). To prepare for these decisions, we investigate how developers could make a 'safety case,' which is a structured rationale that AI systems are unlikely to cause a catastrophe. We propose a framework for organizing a safety case and discuss four categories of arguments to justify safety: total inability to cause a catastrophe, sufficiently strong control measures, trustworthiness despite capability to cause harm, and -- if AI systems become much more powerful -- deference to credible AI advisors. We evaluate concrete examples of arguments in each category and outline how arguments could be combined to justify that AI systems are safe to deploy.
2024-03-14
ArXiv (prépublication)
doi.org
arxiv.org
Aleatoric and epistemic uncertainty extraction of patient-specific deep learning-based dose predictions in LDR prostate brachytherapy
Francisco Berumen
Samuel Ouellet
S. Enger
Luc Beaulieu
2024-03-13
Physics in Medicine and Biology (publié)
doi.org
Analyzing Data Augmentation for Medical Images: A Case Study in Ultrasound Images
Adam Tupper
Christian Gagné
Data augmentation is one of the most effective techniques to improve the generalization performance of deep neural networks. Yet, despite of… (voir plus)ten facing limited data availability in medical image analysis, it is frequently underutilized. This appears to be due to a gap in our collective understanding of the efficacy of different augmentation techniques across medical imaging tasks and modalities. One domain where this is especially true is breast ultrasound images. This work addresses this issue by analyzing the effectiveness of different augmentation techniques for the classification of breast lesions in ultrasound images. We assess the generalizability of our findings across several datasets, demonstrate that certain augmentations are far more effective than others, and show that their usage leads to significant performance gains.
2024-03-13
ArXiv (prépublication)
doi.org
arxiv.org
Bayesian Spectral Graph Denoising with Smoothness Prior
Samuel Leone
Xingzhi Sun
Michael Perlmutter
Smita Krishnaswamy
Here we consider the problem of denoising features associated to complex data, modeled as signals on a graph, via a smoothness prior. This i… (voir plus)s motivated in part by settings such as single-cell RNA where the data is very high-dimensional, but its structure can be captured via an affinity graph. This allows us to utilize ideas from graph signal processing. In particular, we present algorithms for the cases where the signal is perturbed by Gaussian noise, dropout, and uniformly distributed noise. The signals are assumed to follow a prior distribution defined in the frequency domain which favors signals which are smooth across the edges of the graph. By pairing this prior distribution with our three models of noise generation, we propose Maximum A Posteriori (M.A.P.) estimates of the true signal in the presence of noisy data and provide algorithms for computing the M.A.P. Finally, we demonstrate the algorithms’ ability to effectively restore signals from white noise on image data and from severe dropout in single-cell RNA sequence data.
2024-03-12
Annual Conference on Information Sciences and Systems (publié)
doi.org
arxiv.org
Online Bayesian optimization of vagus nerve stimulation
Lorenz Wernisch
Tristan Edwards
Antonin Berthon
Olivier Tessier-Larivière
Elvijs Sarkans
Myrta Stoukidi
Pascal Fortier-Poisson
Max Pinkney
Michael Thornton
Catherine Hanley
Susannah Lee
Joel Jennings
Ben Appleton
Phillip Garsed
Bret Patterson
Will Buttinger
Samuel Gonshaw
Matjaž Jakopec
Sudhakaran Shunmugam
Jorin Mamen … (voir 4 de plus)
Aleksi Tukiainen
Guillaume Lajoie
Oliver Armitage
Emil Hewage
Objective. In bioelectronic medicine, neuromodulation therapies induce neural signals to the brain or organs, modifying their function. Stim… (voir plus)ulation devices capable of triggering exogenous neural signals using electrical waveforms require a complex and multi-dimensional parameter space to control such waveforms. Determining the best combination of parameters (waveform optimization or dosing) for treating a particular patient’s illness is therefore challenging. Comprehensive parameter searching for an optimal stimulation effect is often infeasible in a clinical setting due to the size of the parameter space. Restricting this space, however, may lead to suboptimal therapeutic results, reduced responder rates, and adverse effects. Approach. As an alternative to a full parameter search, we present a flexible machine learning, data acquisition, and processing framework for optimizing neural stimulation parameters, requiring as few steps as possible using Bayesian optimization. This optimization builds a model of the neural and physiological responses to stimulations, enabling it to optimize stimulation parameters and provide estimates of the accuracy of the response model. The vagus nerve (VN) innervates, among other thoracic and visceral organs, the heart, thus controlling heart rate (HR), making it an ideal candidate for demonstrating the effectiveness of our approach. Main results. The efficacy of our optimization approach was first evaluated on simulated neural responses, then applied to VN stimulation intraoperatively in porcine subjects. Optimization converged quickly on parameters achieving target HRs and optimizing neural B-fiber activations despite high intersubject variability. Significance. An optimized stimulation waveform was achieved in real time with far fewer stimulations than required by alternative optimization strategies, thus minimizing exposure to side effects. Uncertainty estimates helped avoiding stimulations outside a safe range. Our approach shows that a complex set of neural stimulation parameters can be optimized in real-time for a patient to achieve a personalized precision dosing.
2024-03-12
Journal of Neural Engineering (publié)
doi.org