Methods of pattern recognition and machine learning are applied extensively in science, technology, and society. Hence, any advances in related theory may translate into large-scale impact. Here we explore how algorithmic information theory, especially algorithmic probability, may aid in a machine learning task. We study a multiclass supervised classification problem, namely learning the RNA molecule sequence-to-shape map, where the different possible shapes are taken to be the classes. The primary motivation for this work is a proof of concept example, where a concrete, well-motivated machine learning task can be aided by approximations to algorithmic probability. Our approach is based on directly estimating the class (i.e., shape) probabilities from shape complexities, and using the estimated probabilities as a prior in a Gaussian process learning problem. Naturally, with a large amount of training data, the prior has no significant influence on classification accuracy, but in the very small training data regime, we show that using the prior can substantially improve classification accuracy. To our knowledge, this work is one of the first to demonstrate how algorithmic probability can aid in a concrete, real-world, machine learning problem.

基本上有三种不确定性量化方法（UQ）：（a）强大的优化，（b）贝叶斯，（c）决策理论。尽管（a）坚固，但在准确性和数据同化方面是不利的。 （b）需要先验，通常是脆弱的，后验估计可能很慢。尽管（c）导致对最佳先验的识别，但其近似遭受了维度的诅咒，风险的概念是相对于数据分布的平均值。我们引入了第四种，它是（a），（b），（c）和假设检验之间的杂种。可以总结为在观察样本$ x $之后，（1）通过相对可能性定义了可能性区域，（2）在该区域玩Minmax游戏以定义最佳估计器及其风险。最终的方法具有几种理想的属性（a）测量数据后确定了最佳先验，并且风险概念是后部的，（b）确定最佳估计值，其风险可以降低到计算最小封闭的最小封闭式。利益图量下的可能性区域图像的球（这是快速的，不受维数的诅咒）。该方法的特征在于$ [0,1] $中的参数，该参数是在观察到的数据（相对可能性）的稀有度上被假定的下限。当该参数接近$ 1 $时，该方法会产生一个后分布，该分布集中在最大似然估计的情况下，并具有较低的置信度UQ估计值。当该参数接近$ 0 $时，该方法会产生最大风险后验分布，并具有很高的信心UQ估计值。除了导航准确性不确定性权衡外，该建议的方法还通过导航与数据同化相关的稳健性 - 准确性权衡解决了贝叶斯推断的脆弱性。

The integration of data and knowledge from several sources is known as data fusion. When data is available in a distributed fashion or when different sensors are used to infer a quantity of interest, data fusion becomes essential. In Bayesian settings, a priori information of the unknown quantities is available and, possibly, shared among the distributed estimators. When the local estimates are fused, such prior might be overused unless it is accounted for. This paper explores the effects of shared priors in Bayesian data fusion contexts, providing fusion rules and analysis to understand the performance of such fusion as a function of the number of collaborative agents and the uncertainty of the priors. Analytical results are corroborated through experiments in a variety of estimation and classification problems.

Continual Learning, also known as Lifelong or Incremental Learning, has recently gained renewed interest among the Artificial Intelligence research community. Recent research efforts have quickly led to the design of novel algorithms able to reduce the impact of the catastrophic forgetting phenomenon in deep neural networks. Due to this surge of interest in the field, many competitions have been held in recent years, as they are an excellent opportunity to stimulate research in promising directions. This paper summarizes the ideas, design choices, rules, and results of the challenge held at the 3rd Continual Learning in Computer Vision (CLVision) Workshop at CVPR 2022. The focus of this competition is the complex continual object detection task, which is still underexplored in literature compared to classification tasks. The challenge is based on the challenge version of the novel EgoObjects dataset, a large-scale egocentric object dataset explicitly designed to benchmark continual learning algorithms for egocentric category-/instance-level object understanding, which covers more than 1k unique main objects and 250+ categories in around 100k video frames.

The ability to sequentially learn multiple tasks without forgetting is a key skill of biological brains, whereas it represents a major challenge to the field of deep learning. To avoid catastrophic forgetting, various continual learning (CL) approaches have been devised. However, these usually require discrete task boundaries. This requirement seems biologically implausible and often limits the application of CL methods in the real world where tasks are not always well defined. Here, we take inspiration from neuroscience, where sparse, non-overlapping neuronal representations have been suggested to prevent catastrophic forgetting. As in the brain, we argue that these sparse representations should be chosen on the basis of feed forward (stimulus-specific) as well as top-down (context-specific) information. To implement such selective sparsity, we use a bio-plausible form of hierarchical credit assignment known as Deep Feedback Control (DFC) and combine it with a winner-take-all sparsity mechanism. In addition to sparsity, we introduce lateral recurrent connections within each layer to further protect previously learned representations. We evaluate the new sparse-recurrent version of DFC on the split-MNIST computer vision benchmark and show that only the combination of sparsity and intra-layer recurrent connections improves CL performance with respect to standard backpropagation. Our method achieves similar performance to well-known CL methods, such as Elastic Weight Consolidation and Synaptic Intelligence, without requiring information about task boundaries. Overall, we showcase the idea of adopting computational principles from the brain to derive new, task-free learning algorithms for CL.

神经网络的一种众所周知的故障模式对应于高置信度错误的预测，尤其是对于训练分布有所不同的数据。这种不安全的行为限制了其适用性。为此，我们表明可以通过在其内部表示中添加约束来定义提供准确置信度的模型。也就是说，我们将类标签编码为固定的唯一二进制向量或类代码，并使用这些标签来在整个模型中强制执行依赖类的激活模式。结果预测因子被称为总激活分类器（TAC），而TAC用作基础分类器的附加组件，以指示预测的可靠性。给定数据实例，TAC切片中间表示分为不相交集，并将此类切片减少到标量中，从而产生激活曲线。在培训期间，将激活轮廓推向分配给给定培训实例的代码。在测试时，可以预测与最匹配示例激活曲线的代码相对应的类。从经验上讲，我们观察到激活模式及其相应代码之间的相似之处导致一种廉价的无监督方法来诱导歧视性置信度得分。也就是说，我们表明TAC至少与从现有模型中提取的最新置信度得分一样好，同时严格改善了模型在拒绝设置上的价值。还观察到TAC在多种类型的架构和数据模式上都很好地工作。

Tokamak设备创建的核融合能力是作为可持续能源来源的最有希望的方法之一。 Tokamak的一个主要挑战研究领域是预测由执行器线圈和内部Tokamak等离子体的相互作用确定的最后一个封闭的磁通表面（LCF）。这项工作需要高维，高频，高保真，实时工具，这使多种执行器线圈的输入与内部Tokamak等离子体状态相互作用，这使得更加复杂。在这项工作中，我们提出了一种新的机器学习模型，用于从实验性高级超导Tokamak（EAST）重建LCF，该模型从East的实验数据中自动学习。该体系结构可以检查控制策略设计，并将其与Tokamak控制系统集成在一起，以进行实时磁预测。在实时建模测试中，我们的方法在整个放电过程的LCFS重建中达到了99％以上的平均相似性。在离线磁重建中，我们的方法达到了93％以上的平均相似性。

已知应用于任务序列的标准梯度下降算法可在深层神经网络中产生灾难性遗忘。当对序列中的新任务进行培训时，该模型会在当前任务上更新其参数，从而忘记过去的知识。本文探讨了我们在有限环境中扩展任务数量的方案。这些方案由与重复数据的长期任务组成。我们表明，在这种情况下，随机梯度下降可以学习，进步并融合到根据现有文献需要持续学习算法的解决方案。换句话说，我们表明该模型在没有特定的记忆机制的情况下执行知识保留和积累。我们提出了一个新的实验框架，即Scole（缩放量表），以研究在潜在无限序列中的知识保留和算法的积累。为了探索此设置，我们对1,000个任务的序列进行了大量实验，以更好地了解这种新的设置家庭。我们还提出了对香草随机梯度下降的轻微修改，以促进这种情况下的持续学习。 SCOLE框架代表了对实用训练环境的良好模拟，并允许长序列研究收敛行为。我们的实验表明，在短方案上以前的结果不能总是推断为更长的场景。

该报告说明了基于音频和视频数据的最成功的AAL应用程序和功能的艺术状态，即（i）生命式和自我监控，（ii）对生命体征的远程监控，（iii）情绪状态识别，（（iv）食物摄入量监测，活动和行为认识，（v）活动和个人帮助，（vi）手势识别，（vii）秋季检测和预防，（viii）移动性评估和脆弱的识别以及（IX）认知和运动康复。对于这些应用程序方案，该报告说明了科学进步，可用产品和研究项目的状态。开放的挑战也被突出显示。

尽管在构建强大的神经网络方面具有明显的计算优势，但使用单步方法的对抗训练（AT）是不稳定的，因为它遭受了灾难性的过度拟合（CO）：网络在对抗性训练的第一阶段获得了非平凡的鲁棒性，但突然达到了一个阶段在几次迭代中，他们很快失去了所有鲁棒性。尽管有些作品成功地预防了CO，但导致这种显着失败模式的不同机制仍然很少理解。但是，在这项工作中，我们发现数据结构与AT动力学之间的相互作用在CO中起着基本作用。特别是，通过对自然图像的典型数据集进行主动干预，我们建立了一个因果关系。在方法上单步中的数据和CO的发作。这种新的观点提供了对导致CO的机制的重要见解，并为更好地理解强大模型构建的一般动态铺平了道路。可以在https://github.com/gortizji/co_features上找到复制本文实验的代码。