可重复性是科学的基石，因为发现的复制是它们成为知识的过程。人们普遍认为，许多科学领域正在经历可重复性危机。这导致了各种准则的出版物，以提高研究可重复性。该教学章节旨在作为医学成像机器学习领域的研究人员的可重复性介绍。我们首先区分不同类型的可重复性。对于每个人，我们旨在定义它，描述实现它的要求并讨论其效用。本章以讨论可重复性的好处的讨论以及对这种概念的非态度方法及其在研究实践中的实施的认罪。

脉络膜丛（CP）是产生大部分脑脊液（CSF）的大脑的心室的结构。几个淘汰的课后和体内研究已经指出了它们在多发性硬化症（MS）中的炎症过程中的作用。因此，来自MRI的CP的自动分割具有高价值，用于研究其在大型患者的大队列中的特征。据我们所知，CP分段唯一可自由的工具是FreeSurfer，但其对该特定结构的准确性很差。在本文中，我们建议自动从非对比度增强的T1加权MRI自动分段。为此，我们介绍了一种基于轴向多层截图（MLP）的组件的“Axial-MLP”的新模型。这是最近的作品启发，表明，变压器的自我注意层可以用MLPS取代。系统地与标准的3D U-Net，NNU-Net，FreeSurfer和Fastsurefer系统地进行系统地进行系统地进行系统地进行。对于我们的实验，我们利用141个受试者的数据集（44个对照和97名MS患者）。我们展示所有测试的深度学习（DL）方法优于FreeSurfer（DIC为0.7的骰子，对于FreeSurfer的DL 0.33）。 Axial-MLP与U-Net竞争竞争，即使它略有略低于准确。我们纸张的结论是两倍：1）学习的深度学习方法可能是研究CP在MS患者的大型队列中的有用工具; 2）〜Axial-MLP是用于这种任务的卷积神经网络的潜在可行的替代方案，尽管它可以从进一步的改进中受益。

This report summarizes the work carried out by the authors during the Twelfth Montreal Industrial Problem Solving Workshop, held at Universit\'e de Montr\'eal in August 2022. The team tackled a problem submitted by CBC/Radio-Canada on the theme of Automatic Text Simplification (ATS).

Wearable sensors for measuring head kinematics can be noisy due to imperfect interfaces with the body. Mouthguards are used to measure head kinematics during impacts in traumatic brain injury (TBI) studies, but deviations from reference kinematics can still occur due to potential looseness. In this study, deep learning is used to compensate for the imperfect interface and improve measurement accuracy. A set of one-dimensional convolutional neural network (1D-CNN) models was developed to denoise mouthguard kinematics measurements along three spatial axes of linear acceleration and angular velocity. The denoised kinematics had significantly reduced errors compared to reference kinematics, and reduced errors in brain injury criteria and tissue strain and strain rate calculated via finite element modeling. The 1D-CNN models were also tested on an on-field dataset of college football impacts and a post-mortem human subject dataset, with similar denoising effects observed. The models can be used to improve detection of head impacts and TBI risk evaluation, and potentially extended to other sensors measuring kinematics.

The number of international benchmarking competitions is steadily increasing in various fields of machine learning (ML) research and practice. So far, however, little is known about the common practice as well as bottlenecks faced by the community in tackling the research questions posed. To shed light on the status quo of algorithm development in the specific field of biomedical imaging analysis, we designed an international survey that was issued to all participants of challenges conducted in conjunction with the IEEE ISBI 2021 and MICCAI 2021 conferences (80 competitions in total). The survey covered participants' expertise and working environments, their chosen strategies, as well as algorithm characteristics. A median of 72% challenge participants took part in the survey. According to our results, knowledge exchange was the primary incentive (70%) for participation, while the reception of prize money played only a minor role (16%). While a median of 80 working hours was spent on method development, a large portion of participants stated that they did not have enough time for method development (32%). 25% perceived the infrastructure to be a bottleneck. Overall, 94% of all solutions were deep learning-based. Of these, 84% were based on standard architectures. 43% of the respondents reported that the data samples (e.g., images) were too large to be processed at once. This was most commonly addressed by patch-based training (69%), downsampling (37%), and solving 3D analysis tasks as a series of 2D tasks. K-fold cross-validation on the training set was performed by only 37% of the participants and only 50% of the participants performed ensembling based on multiple identical models (61%) or heterogeneous models (39%). 48% of the respondents applied postprocessing steps.

Scene understanding is a major challenge of today's computer vision. Center to this task is image segmentation, since scenes are often provided as a set of pictures. Nowadays, many such datasets also provide 3D geometry information given as a 3D point cloud acquired by a laser scanner or a depth camera. To exploit this geometric information, many current approaches rely on both a 2D loss and 3D loss, requiring not only 2D per pixel labels but also 3D per point labels. However obtaining a 3D groundtruth is challenging, time-consuming and error-prone. In this paper, we show that image segmentation can benefit from 3D geometric information without requiring any 3D groundtruth, by training the geometric feature extraction with a 2D segmentation loss in an end-to-end fashion. Our method starts by extracting a map of 3D features directly from the point cloud by using a lightweight and simple 3D encoder neural network. The 3D feature map is then used as an additional input to a classical image segmentation network. During training, the 3D features extraction is optimized for the segmentation task by back-propagation through the entire pipeline. Our method exhibits state-of-the-art performance with much lighter input dataset requirements, since no 3D groundtruth is required.

An eco-system of agents each having their own policy with some, but limited, generalizability has proven to be a reliable approach to increase generalization across procedurally generated environments. In such an approach, new agents are regularly added to the eco-system when encountering a new environment that is outside of the scope of the eco-system. The speed of adaptation and general effectiveness of the eco-system approach highly depends on the initialization of new agents. In this paper we propose different techniques for such initialization and study their impact. We then rework the ecosystem setup to use forked agents which brings better results than the initial eco-system approach with a drastically reduced number of training cycles.

We construct a universally Bayes consistent learning rule that satisfies differential privacy (DP). We first handle the setting of binary classification and then extend our rule to the more general setting of density estimation (with respect to the total variation metric). The existence of a universally consistent DP learner reveals a stark difference with the distribution-free PAC model. Indeed, in the latter DP learning is extremely limited: even one-dimensional linear classifiers are not privately learnable in this stringent model. Our result thus demonstrates that by allowing the learning rate to depend on the target distribution, one can circumvent the above-mentioned impossibility result and in fact, learn \emph{arbitrary} distributions by a single DP algorithm. As an application, we prove that any VC class can be privately learned in a semi-supervised setting with a near-optimal \emph{labeled} sample complexity of $\tilde{O}(d/\varepsilon)$ labeled examples (and with an unlabeled sample complexity that can depend on the target distribution).

There is a growing interest in the use of reduced-precision arithmetic, exacerbated by the recent interest in artificial intelligence, especially with deep learning. Most architectures already provide reduced-precision capabilities (e.g., 8-bit integer, 16-bit floating point). In the context of FPGAs, any number format and bit-width can even be considered.In computer arithmetic, the representation of real numbers is a major issue. Fixed-point (FxP) and floating-point (FlP) are the main options to represent reals, both with their advantages and drawbacks. This chapter presents both FxP and FlP number representations, and draws a fair a comparison between their cost, performance and energy, as well as their impact on accuracy during computations.It is shown that the choice between FxP and FlP is not obvious and strongly depends on the application considered. In some cases, low-precision floating-point arithmetic can be the most effective and provides some benefits over the classical fixed-point choice for energy-constrained applications.

With the growth of residential rooftop PV adoption in recent decades, the problem of 1 effective layout design has become increasingly important in recent years. Although a number 2 of automated methods have been introduced, these tend to rely on simplifying assumptions and 3 heuristics to improve computational tractability. We demonstrate a fully automated layout design 4 pipeline that attempts to solve a more general formulation with greater geometric flexibility that 5 accounts for shading losses. Our approach generates rooftop areas from satellite imagery and uses 6 MINLP optimization to select panel positions, azimuth angles and tilt angles on an individual basis 7 rather than imposing any predefined layouts. Our results demonstrate that although several common 8 heuristics are often effective, they may not be universally suitable due to complications resulting 9 from geometric restrictions and shading losses. Finally, we evaluate a few specific heuristics from the 10 literature and propose a potential new rule of thumb that may help improve rooftop solar energy 11 potential when shading effects are considered.