We use cookies to analyze the browsing and usage of our website and to personalize your experience. You can disable these technologies at any time, but this may limit certain functionalities of the site. Read our Privacy Policy for more information.
Setting cookies
You can enable and disable the types of cookies you wish to accept. However certain choices you make could affect the services offered on our sites (e.g. suggestions, personalised ads, etc.).
Essential cookies
These cookies are necessary for the operation of the site and cannot be deactivated. (Still active)
Analytics cookies
Do you accept the use of cookies to measure the audience of our sites?
Multimedia Player
Do you accept the use of cookies to display and allow you to watch the video content hosted by our partners (YouTube, etc.)?
Publications
DIBS: Diversity inducing Information Bottleneck in Model Ensembles
Can meta-learning discover generic ways of processing time series (TS) from a diverse dataset so as to greatly improve generalization on new… (see more) TS coming from different datasets? This work provides positive evidence to this using a broad meta-learning framework which we show subsumes many existing meta-learning algorithms. Our theoretical analysis suggests that residual connections act as a meta-learning adaptation mechanism, generating a subset of task-specific parameters based on a given TS input, thus gradually expanding the expressive power of the architecture on-the-fly. The same mechanism is shown via linearization analysis to have the interpretation of a sequential update of the final linear layer. Our empirical results on a wide range of data emphasize the importance of the identified meta-learning mechanisms for successful zero-shot univariate forecasting, suggesting that it is viable to train a neural network on a source TS dataset and deploy it on a different target TS dataset without retraining, resulting in performance that is at least as good as that of state-of-practice univariate forecasting models.
2021-05-18
Proceedings of the AAAI Conference on Artificial Intelligence (published)
Branch and Bound (B&B) is the exact tree search method typically used to solve Mixed-Integer Linear Programming problems (MILPs). Learning b… (see more)ranching policies for MILP has become an active research area, with most works proposing to imitate the strong branching rule and specialize it to distinct classes of problems. We aim instead at learning a policy that generalizes across heterogeneous MILPs: our main hypothesis is that parameterizing the state of the B&B search tree can aid this type of generalization. We propose a novel imitation learning framework, and introduce new input features and architectures to represent branching. Experiments on MILP benchmark instances clearly show the advantages of incorporating an explicit parameterization of the state of the search tree to modulate the branching decisions, in terms of both higher accuracy and smaller B&B trees. The resulting policies significantly outperform the current state-of-the-art method for "learning to branch" by effectively allowing generalization to generic unseen instances.
2021-05-18
Proceedings of the AAAI Conference on Artificial Intelligence (published)
Visual saliency has emerged as a major visualization tool for interpreting deep reinforcement learning (RL) agents. However, much of the exi… (see more)sting research uses it as an analyzing tool rather than an inductive bias for policy learning. In this work, we use visual attention as an inductive bias for RL agents. We propose a novel self-supervised attention learning approach which can 1. learn to select regions of interest without explicit annotations, and 2. act as a plug for existing deep RL methods to improve the learning performance. We empirically show that the self-supervised attention-aware deep RL methods outperform the baselines in the context of both the rate of convergence and performance. Furthermore, the proposed self-supervised attention is not tied with specific policies, nor restricted to a specific scene. We posit that the proposed approach is a general self-supervised attention module for multi-task learning and transfer learning, and empirically validate the generalization ability of the proposed method. Finally, we show that our method learns meaningful object keypoints highlighting improvements both qualitatively and quantitatively.
2021-05-18
AAAI Conference on Artificial Intelligence (published)
The search for appropriate treatments of cerebral palsy (CP) would be facilitated if researchers could non-invasively monitor anatomical cha… (see more)nges in the spinal cord. The study by Trevarrow et al. aims to validate the relevance of magnetization transfer ratio and diffusion tensor imaging, both magnetic resonance imaging (MRI) techniques, to quantify microstructural abnormalities in the spinal cord of adult patients with CP. The authors used a semi-automated atlas-based analysis pipeline based on Spinal Cord Toolbox software to compute cord and gray matter atrophy and to quantify MRI metrics in specific spinal tracts. In line with their hypothesis, Trevarrow et al. observed differences in cord and gray matter size between participants with CP and typically developing peers. Interestingly, they also demonstrated an association between these morphometric biomarkers and clinical scores of hand dexterity. Magnetization transfer ratio was also reduced in the corticospinal tract of patients with CP. The study by Trevarrow et al. is a remarkable tour de force in that it is extremely difficult to image patients with CP as they are prone to motion (spasticity). In particular, gradient-echo sequences, used for magnetization transfer imaging, are particularly sensitive to motion, as can be seen on Figure 1b of the article. Echo planar imaging sequences, used for diffusion imaging, are sensitive to magnetic field inhomogeneities, which are prevalent in the spine region. The authors used an MRI acquisition protocol similar to a recently proposed standardized quantitative spinal cord MRI protocol (https://spine-generic.rtfd.io/), which likely helped them to obtain satisfactory images despite the many aforementioned challenges. From an image analysis standpoint, one limitation associated with atlas-based analysis (acknowledged by the authors) is that the registration to the template only relies on the spinal cord contour, not its internal structure. In other words, the white matter atlas is adjusted to the participant’s spinal cord contour, and the internal structure of the cord is quasi-linearly scaled (based on a B-spline regularized deformation). This quasi-linearity assumption might not hold true if, for example, the gray/white matter ratio differs between the participant and the template, and/ or the spatial location of the white matter tracts differs between the participant and the atlas, and/or specific tracts (e.g. corticospinal) degenerate. All these effects would cause a mismatch between the warped atlas’ and the participant’s white matter tracts. Unfortunately, there is no solution to this problem (yet). There are ways, however, to mitigate it. For example, using imaging sequences that are sensitive to some internal structures of the spinal cord, such as gray matter, or even some white matter tracts. These internal structures could then be accounted for during registration. However, these advanced contrast techniques are themselves noisy and sensitive to participant motion. In conclusion, the study by Trevarrow et al. is a remarkable technical achievement and a concrete first step towards the inclusion of microstructure MRI to the assessment of spinal cord integrity in patients with CP. Limitations, mostly related to data acquisition, could be tackled with the development of better solutions for gradient echo sequences in participants that are prone to motion. Navigator and/or advanced shimming approaches will hopefully mitigate these issues, making spinal cord quantitative MRI more amenable to clinical routine.
2021-05-15
Developmental Medicine & Child Neurology (published)
Jumana Sara Tobias Carsten Michael Daniel Claudia Yvette Bhismadev Chris Ineke Daisy Flavio Jessica Vincent Pilar David Lindsay Hannah Joerg Rosemary J. Xavier Liogier David J. René Andre Maarten Nico Bethany Laurence Bob Gahan Antonio M. Barbara Amber N. V. Jessica Roberto Antonia San José Emily Roberto Heike Jack Steve C. R. Caroline Marcel P. Ahmad
Background: The initial injury burden from incident TBI is significantly amplified by recurrent TBI (rTBI). Unfortunately, research assessin… (see more)g the accuracy to conduct rTBI surveillance is not available. Accurate surveillance information on recurrent injuries is needed to justify the allocation of resources to rTBI prevention and to conduct high quality epidemiological research on interventions that mitigate this injury burden. This study evaluates the accuracy of administrative health data (AHD) surveillance case definitions for rTBI and estimates the 1-year rTBI incidence adjusted for measurement error. Methods: A 25% random sample of AHD for Montreal residents from 2000 to 2014 was used in this study. Four widely used TBI surveillance case definitions, based on the International Classification of Disease and on radiological exams of the head, were applied to ascertain suspected rTBI cases. Bayesian latent class models were used to estimate the accuracy of each case definition and the 1-year rTBI measurement-error-adjusted incidence without relying on a gold standard rTBI definition that does not exist, across children (18 years), adults (18-64 years), and elderly (> =65 years). Results: The adjusted 1-year rTBI incidence was 4.48 (95% CrI 3.42, 6.20) per 100 person-years across all age groups, as opposed to a crude estimate of 8.03 (95% CrI 7.86, 8.21) per 100 person-years. Patients with higher severity index TBI had a significantly higher incidence of rTBI compared to patients with lower severity index TBI. The case definition that identified patients undergoing a radiological examination of the head in the context of any traumatic injury was the most sensitive across children [0.46 (95% CrI 0.33, 0.61)], adults [0.79 (95% CrI 0.64, 0.94)], and elderly [0.87 (95% CrI 0.78, 0.95)]. The most specific case definition was the discharge abstract database in children [0.99 (95% CrI 0.99, 1.00)], and emergency room visits claims in adults/elderly [0.99 (95% CrI 0.99, 0.99)]. Median time to rTBI was the shortest in adults (75 days) and the longest in children (120 days). Conclusion: Conducting accurate surveillance and valid epidemiological research for rTBI using AHD is feasible when measurement error is accounted for.
