深度学习一直是近来最具破坏性的技术进步之一。深度学习模型的高性能以高度计算，存储和功率要求为代价。感知到加速和压缩这些模型以提高设备性能的直接需求，我们引入了Deeplite Neutrino，以便对模型的生产优化和Deeplite运行时进行介绍，以在基于ARM的平台上部署超低位量化模型。我们为ARMV7和ARMV8架构实施低级量化内核，可在32位和64位基于ARM的设备上进行部署。通过使用矢量化，并行化和平铺的有效实现，与具有XNNPACK后端的TensorFlow Lite相比，我们在分类和检测模型上分别实现了高达2倍和2.2倍的速度。与ONNX运行时相比，我们还获得了高达5倍和3.2倍的显着加速，分别用于分类和检测模型。

在本文中，我们研究了DNN培训中量化的影响。我们假设重量量化是正则化的一种形式，正则化的量与量化水平（精度）相关。我们通过提供分析研究和经验结果来证实我们的假设。通过将重量量化为重量噪声的一种形式，我们探讨了该噪声在训练时如何通过网络传播。然后，我们表明该噪声的大小与量化水平相关。为了确认我们的分析研究，我们在本文中进行了广泛的实验列表，其中我们表明，在各种数据集中，在各种视觉任务和模型中可以看到量化的正则化效果。基于我们的研究，我们建议8位量化在不同的视觉任务和模型中提供了一种可靠的正则化形式。

神经网络（NNS）对研究和行业进行了很大的影响。然而，随着NNS的准确性增加，它之后的大小是扩展，所需的计算操作数量和能量消耗。资源消费的增加导致NNS减少的采用率和现实世界部署不切实际。因此，需要压缩NNS以使它们可用于更广泛的受众，同时降低其运行时成本。在这项工作中，我们从因果推理的角度来处理这一挑战，我们提出了一个评分机制，以促进NNS的结构灌注。该方法基于在最大熵扰动下测量互信息，顺序地通过NN传播。我们展示了两种数据集和各种NNS尺寸的方法的表现，我们表明我们的方法在挑战条件下实现了竞争性能。

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.