Nous utilisons des témoins pour analyser le trafic et l’utilisation de notre site web, afin de personnaliser votre expérience. Vous pouvez désactiver ces technologies à tout moment, mais cela peut restreindre certaines fonctionnalités du site. Consultez notre Politique de protection de la vie privée pour en savoir plus.
Paramètre des cookies
Vous pouvez activer et désactiver les types de cookies que vous souhaitez accepter. Cependant certains choix que vous ferez pourraient affecter les services proposés sur nos sites (ex : suggestions, annonces personnalisées, etc.).
Cookies essentiels
Ces cookies sont nécessaires au fonctionnement du site et ne peuvent être désactivés. (Toujours actif)
Cookies analyse
Acceptez-vous l'utilisation de cookies pour mesurer l'audience de nos sites ?
Multimedia Player
Acceptez-vous l'utilisation de cookies pour afficher et vous permettre de regarder les contenus vidéo hébergés par nos partenaires (YouTube, etc.) ?
Publications
Deep Learning Unlocks the True Potential of Organ Donation after Circulatory Death with Accurate Prediction of Time-to-Death
Increasing the number of organ donations after circulatory death (DCD) has been identified as one of the most important ways of addressing t… (voir plus)he ongoing organ shortage. While recent technological advances in organ transplantation have increased their success rate, a substantial challenge in increasing the number of DCD donations resides in the uncertainty regarding the timing of cardiac death after terminal extubation, impacting the risk of prolonged ischemic organ injury, and negatively affecting post-transplant outcomes. In this study, we trained and externally validated an ODE-RNN model, which combines recurrent neural network with neural ordinary equations and excels in processing irregularly-sampled time series data. The model is designed to predict time-to-death following terminal extubation in the intensive care unit (ICU) using the last 24 hours of clinical observations. Our model was trained on a cohort of 3,238 patients from Yale New Haven Hospital, and validated on an external cohort of 1,908 patients from six hospitals across Connecticut. The model achieved accuracies of 95.3 {+/-} 1.0% and 95.4 {+/-} 0.7% for predicting whether death would occur in the first 30 and 60 minutes, respectively, with a calibration error of 0.024 {+/-} 0.009. Heart rate, respiratory rate, mean arterial blood pressure (MAP), oxygen saturation (SpO2), and Glasgow Coma Scale (GCS) scores were identified as the most important predictors. Surpassing existing clinical scores, our model sets the stage for reduced organ acquisition costs and improved post-transplant outcomes.
Machine unlearning aims to solve the problem of removing the influence of selected training examples from a learned model. Despite the incre… (voir plus)asing attention to this problem, it remains an open research question how to evaluate unlearning in large language models (LLMs), and what are the critical properties of the data to be unlearned that affect the quality and efficiency of unlearning. This work formalizes a metric to evaluate unlearning quality in generative models, and uses it to assess the trade-offs between unlearning quality and performance. We demonstrate that unlearning out-of-distribution examples requires more unlearning steps but overall presents a better trade-off overall. For in-distribution examples, however, we observe a rapid decay in performance as unlearning progresses. We further evaluate how example's memorization and difficulty affect unlearning under a classical gradient ascent-based approach.
Latent diffusion models (LDMs) power state-of-the-art high-resolution generative image models. LDMs learn the data distribution in the laten… (voir plus)t space of an autoencoder (AE) and produce images by mapping the generated latents into RGB image space using the AE decoder. While this approach allows for efficient model training and sampling, it induces a disconnect between the training of the diffusion model and the decoder, resulting in a loss of detail in the generated images. To remediate this disconnect, we propose to leverage the internal features of the decoder to define a latent perceptual loss (LPL). This loss encourages the models to create sharper and more realistic images. Our loss can be seamlessly integrated with common autoencoders used in latent diffusion models, and can be applied to different generative modeling paradigms such as DDPM with epsilon and velocity prediction, as well as flow matching. Extensive experiments with models trained on three datasets at 256 and 512 resolution show improved quantitative -- with boosts between 6% and 20% in FID -- and qualitative results when using our perceptual loss.
Neural networks are traditionally trained under the assumption that data come from a stationary distribution. However, settings which violat… (voir plus)e this assumption are becoming more popular; examples include supervised learning under distributional shifts, reinforcement learning, continual learning and non-stationary contextual bandits. In this work we introduce a novel learning approach that automatically models and adapts to non-stationarity, via an Ornstein-Uhlenbeck process with an adaptive drift parameter. The adaptive drift tends to draw the parameters towards the initialisation distribution, so the approach can be understood as a form of soft parameter reset. We show empirically that our approach performs well in non-stationary supervised and off-policy reinforcement learning settings.
Abstract Spinal cord disease is important in most people with multiple sclerosis, but assessment remains less emphasized in patient care, ba… (voir plus)sic and clinical research and therapeutic trials. The North American Imaging in Multiple Sclerosis Spinal Cord Interest Group was formed to determine and present the contemporary landscape of multiple sclerosis spinal cord evaluation, further existing and advanced spinal cord imaging techniques, and foster collaborative work. Important themes arose: (i) multiple sclerosis spinal cord lesions (differential diagnosis, association with clinical course); (ii) spinal cord radiological–pathological associations; (iii) ‘critical’ spinal cord lesions; (iv) multiple sclerosis topographical model; (v) spinal cord atrophy; and (vi) automated and special imaging techniques. Distinguishing multiple sclerosis from other myelopathic aetiology is increasingly refined by imaging and serological studies. Post-mortem spinal cord findings and MRI pathological correlative studies demonstrate MRI’s high sensitivity in detecting microstructural demyelination and axonal loss. Spinal leptomeninges include immune inflammatory infiltrates, some in B-cell lymphoid-like structures. ‘Critical’ demyelinating lesions along spinal cord corticospinal tracts are anatomically consistent with and may be disproportionately associated with motor progression. Multiple sclerosis topographical model implicates the spinal cord as an area where threshold impairment associates with multiple sclerosis disability. Progressive spinal cord atrophy and ‘silent’ multiple sclerosis progression may be emerging as an important multiple sclerosis prognostic biomarker. Manual atrophy assessment is complicated by rater bias, while automation (e.g. Spinal Cord Toolbox), and artificial intelligence may reduce this. Collaborative research by the North American Imaging in Multiple Sclerosis and similar groups with experts combining distinct strengths is key to advancing assessment and treatment of people with multiple sclerosis spinal cord disease.
Text-to-SQL enables users to interact with databases through natural language, simplifying access to structured data. Although highly capabl… (voir plus)e large language models (LLMs) achieve strong accuracy for complex queries, they incur unnecessary latency and dollar cost for simpler ones. In this paper, we introduce the first LLM routing approach for Text-to-SQL, which dynamically selects the most cost-effective LLM capable of generating accurate SQL for each query. We present two routing strategies (score- and classification-based) that achieve accuracy comparable to the most capable LLM while reducing costs. We design the routers for ease of training and efficient inference. In our experiments, we highlight a practical and explainable accuracy-cost trade-off on the BIRD dataset.
Large-scale training of latent diffusion models (LDMs) has enabled unprecedented quality in image generation. However, the key components of… (voir plus) the best performing LDM training recipes are oftentimes not available to the research community, preventing apple-to-apple comparisons and hindering the validation of progress in the field. In this work, we perform an in-depth study of LDM training recipes focusing on the performance of models and their training efficiency. To ensure apple-to-apple comparisons, we re-implement five previously published models with their corresponding recipes. Through our study, we explore the effects of (i)~the mechanisms used to condition the generative model on semantic information (e.g., text prompt) and control metadata (e.g., crop size, random flip flag, etc.) on the model performance, and (ii)~the transfer of the representations learned on smaller and lower-resolution datasets to larger ones on the training efficiency and model performance. We then propose a novel conditioning mechanism that disentangles semantic and control metadata conditionings and sets a new state-of-the-art in class-conditional generation on the ImageNet-1k dataset -- with FID improvements of 7% on 256 and 8% on 512 resolutions -- as well as text-to-image generation on the CC12M dataset -- with FID improvements of 8% on 256 and 23% on 512 resolution.
High-level synthesis (HLS) produces hardware au-tomatically by scheduling and assigning resources based on an input control/data-flow graph.… (voir plus) One particular aspect of HLS for the digital signal processing (DSP) architecture is the het-erogeneous assignment problem (HAP) which maps operations into different types of functional units available in the electronic design automation tools to build efficient implementations. An optimal solution to this assignment problem can be found by formulating the problem as integer linear programming (ILP) and using a solver. However, given the slow nature of this process, heuristics tend to be used instead leading to sub-optimal designs. This paper revisits the classical ILP formulation of the HAP with time constraints for the DSP architecture by identifying redundant constraints. This paper proves theoretically, and demonstrates experimentally, that removing these constraints does not affect the obtained solution. This technique achieves speedups of more than 100 × in terms of runtime and reductions of more than 50 × in terms of memory usage of the solver. Also, this work proposes an updated heuristic that keeps reducing the latency of a path instead of finding a new critical path after giving a new node assignment. Runtime reductions (more than another 10×) due to reduced numbers of critical path searches are observed while returning similar results.
2024-11-04
IEEE Workshop on Signal Processing Systems (publié)
High-level synthesis (HLS) produces hardware au-tomatically by scheduling and assigning resources based on an input control/data-flow graph.… (voir plus) One particular aspect of HLS for the digital signal processing (DSP) architecture is the het-erogeneous assignment problem (HAP) which maps operations into different types of functional units available in the electronic design automation tools to build efficient implementations. An optimal solution to this assignment problem can be found by formulating the problem as integer linear programming (ILP) and using a solver. However, given the slow nature of this process, heuristics tend to be used instead leading to sub-optimal designs. This paper revisits the classical ILP formulation of the HAP with time constraints for the DSP architecture by identifying redundant constraints. This paper proves theoretically, and demonstrates experimentally, that removing these constraints does not affect the obtained solution. This technique achieves speedups of more than 100 × in terms of runtime and reductions of more than 50 × in terms of memory usage of the solver. Also, this work proposes an updated heuristic that keeps reducing the latency of a path instead of finding a new critical path after giving a new node assignment. Runtime reductions (more than another 10×) due to reduced numbers of critical path searches are observed while returning similar results.
2024-11-04
IEEE Workshop on Signal Processing Systems (publié)
High-level synthesis (HLS) produces hardware au-tomatically by scheduling and assigning resources based on an input control/data-flow graph.… (voir plus) One particular aspect of HLS for the digital signal processing (DSP) architecture is the het-erogeneous assignment problem (HAP) which maps operations into different types of functional units available in the electronic design automation tools to build efficient implementations. An optimal solution to this assignment problem can be found by formulating the problem as integer linear programming (ILP) and using a solver. However, given the slow nature of this process, heuristics tend to be used instead leading to sub-optimal designs. This paper revisits the classical ILP formulation of the HAP with time constraints for the DSP architecture by identifying redundant constraints. This paper proves theoretically, and demonstrates experimentally, that removing these constraints does not affect the obtained solution. This technique achieves speedups of more than 100 × in terms of runtime and reductions of more than 50 × in terms of memory usage of the solver. Also, this work proposes an updated heuristic that keeps reducing the latency of a path instead of finding a new critical path after giving a new node assignment. Runtime reductions (more than another 10×) due to reduced numbers of critical path searches are observed while returning similar results.
2024-11-04
IEEE Workshop on Signal Processing Systems (publié)
