The preservation, monitoring, and control of water resources has been a major challenge in recent decades. Water resources must be constantly monitored to know the contamination levels of water. To meet this objective, this paper proposes a water monitoring system using autonomous surface vehicles, equipped with water quality sensors, based on a multimodal particle swarm optimization, and the federated learning technique, with Gaussian process as a surrogate model, the AquaFeL-PSO algorithm. The proposed monitoring system has two phases, the exploration phase and the exploitation phase. In the exploration phase, the vehicles examine the surface of the water resource, and with the data acquired by the water quality sensors, a first water quality model is estimated in the central server. In the exploitation phase, the area is divided into action zones using the model estimated in the exploration phase for a better exploitation of the contamination zones. To obtain the final water quality model of the water resource, the models obtained in both phases are combined. The results demonstrate the efficiency of the proposed path planner in obtaining water quality models of the pollution zones, with a 14$\%$ improvement over the other path planners compared, and the entire water resource, obtaining a 400$\%$ better model, as well as in detecting pollution peaks, the improvement in this case study is 4,000$\%$. It was also proven that the results obtained by applying the federated learning technique are very similar to the results of a centralized system.

We study the problem of combining neural networks with symbolic reasoning. Recently introduced frameworks for Probabilistic Neurosymbolic Learning (PNL), such as DeepProbLog, perform exponential-time exact inference, limiting the scalability of PNL solutions. We introduce Approximate Neurosymbolic Inference (A-NeSI): a new framework for PNL that uses neural networks for scalable approximate inference. A-NeSI 1) performs approximate inference in polynomial time without changing the semantics of probabilistic logics; 2) is trained using data generated by the background knowledge; 3) can generate symbolic explanations of predictions; and 4) can guarantee the satisfaction of logical constraints at test time, which is vital in safety-critical applications. Our experiments show that A-NeSI is the first end-to-end method to scale the Multi-digit MNISTAdd benchmark to sums of 15 MNIST digits, up from 4 in competing systems. Finally, our experiments show that A-NeSI achieves explainability and safety without a penalty in performance.

For improving short-length codes, we demonstrate that classic decoders can also be used with real-valued, neural encoders, i.e., deep-learning based codeword sequence generators. Here, the classical decoder can be a valuable tool to gain insights into these neural codes and shed light on weaknesses. Specifically, the turbo-autoencoder is a recently developed channel coding scheme where both encoder and decoder are replaced by neural networks. We first show that the limited receptive field of convolutional neural network (CNN)-based codes enables the application of the BCJR algorithm to optimally decode them with feasible computational complexity. These maximum a posteriori (MAP) component decoders then are used to form classical (iterative) turbo decoders for parallel or serially concatenated CNN encoders, offering a close-to-maximum likelihood (ML) decoding of the learned codes. To the best of our knowledge, this is the first time that a classical decoding algorithm is applied to a non-trivial, real-valued neural code. Furthermore, as the BCJR algorithm is fully differentiable, it is possible to train, or fine-tune, the neural encoder in an end-to-end fashion.

We describe PromptBoosting, a query-efficient procedure for building a text classifier from a neural language model (LM) without access to the LM's parameters, gradients, or hidden representations. This form of "black-box" classifier training has become increasingly important as the cost of training and inference in large-scale LMs grows. But existing black-box LM classifier learning approaches are themselves computationally inefficient, typically specializing LMs to the target task by searching in a large space of (discrete or continuous) prompts using zeroth-order optimization methods. Instead of directly optimizing in prompt space, PromptBoosting obtains a small pool of prompts via a gradient-free approach and then constructs a large pool of weak learners by pairing these prompts with different elements of the LM's output distribution. These weak learners are then ensembled using the AdaBoost algorithm. The entire learning process requires only a small number of forward passes and no backward pass. Experiments show that PromptBoosting achieves state-of-the-art performance in multiple black-box few-shot classification tasks, and matches or outperforms full fine-tuning in both few-shot and standard learning paradigms, while training 10x faster than existing black-box methods.

Federated Learning (FL) has emerged as a promising distributed learning paradigm with an added advantage of data privacy. With the growing interest in having collaboration among data owners, FL has gained significant attention of organizations. The idea of FL is to enable collaborating participants train machine learning (ML) models on decentralized data without breaching privacy. In simpler words, federated learning is the approach of ``bringing the model to the data, instead of bringing the data to the mode''. Federated learning, when applied to data which is partitioned vertically across participants, is able to build a complete ML model by combining local models trained only using the data with distinct features at the local sites. This architecture of FL is referred to as vertical federated learning (VFL), which differs from the conventional FL on horizontally partitioned data. As VFL is different from conventional FL, it comes with its own issues and challenges. In this paper, we present a structured literature review discussing the state-of-the-art approaches in VFL. Additionally, the literature review highlights the existing solutions to challenges in VFL and provides potential research directions in this domain.

该注释有三个目的：（i）我们提供了一个独立的说明，表明在可能的（PAC）模型中，连接性查询无法有效地学习，从而明确注意这一概念阶级缺乏这一概念的事实，多项式大小的拟合属性，在许多计算学习理论文献中被默认假设的属性；（ii）我们建立了强大的负PAC可学习性结果，该结果适用于许多限制类别的连接性查询（CQ），包括针对广泛的“无循环”概念的无孔CQ；（iii）我们证明CQ可以通过会员查询有效地学习PAC。

查找最佳消息量化是低复杂性信念传播（BP）解码的关键要求。为此，我们提出了一个浮点替代模型，该模型模仿量化效果，作为均匀噪声的添加，其幅度是可训练的变量。我们验证替代模型与定点实现的行为非常匹配，并提出了手工制作的损失功能，以实现复杂性和误差率性能之间的权衡。然后，采用一种基于深度学习的方法来优化消息位。此外，我们表明参数共享既可以确保实现友好的解决方案，又比独立参数导致更快的培训收敛。我们为5G低密度均衡检查（LDPC）代码提供模拟结果，并在浮点分解的0.2 dB内报告误差率性能，平均消息量化位低于3.1位。此外，我们表明，学到的位宽也将其推广到其他代码速率和渠道。

本文介绍了用于自动赛车的多层运动计划和控制架构，能够避免静态障碍，进行主动超越并达到75 $ m/s $以上的速度。使用的脱机全局轨迹生成和在线模型预测控制器高度基于车辆的优化和动态模型，在该模型中，在基本的Pacejka Magic公式的扩展版本中，轮胎和弯曲效果表示。使用多体汽车运动库鉴定并验证了所提出的单轨模型，这些模型允许正确模拟车辆动力学，在丢失实际实验数据时尤其有用。调整了控制器的基本正规化项和约束，以降低输入的变化速率，同时确保可接受的速度和路径跟踪。运动计划策略由一个基于Fren \'ET框架的计划者组成，该计划者考虑了Kalman过滤器产生的对手的预测。策划者选择了无碰撞路径和速度轮廓要在3秒钟的视野中跟踪，以实现不同的目标，例如跟随和超车。该提议的解决方案已应用于达拉拉AV-21赛车，并在椭圆形赛道上进行了测试，可实现高达25 $ m/s^{2} $的横向加速度。

第一次采用了深入的增强学习方法来解决动态多核心纤维弹性光学网络（MCF-eons）中的路由，调制，频谱和核心分配（RMSCA）问题。为此，设计和实施了一个与OpenAI的健身房兼容的新环境，以模仿MCF -eons的运行。新的环境通过考虑网络状态和与物理层相关的方面来处理代理操作（选择路线，核心和频谱插槽）。后者包括可用的调制格式及其覆盖范围以及与MCF相关的障碍的核心间串扰（XT）。如果信号的产生质量是可以接受的，则环境将分配代理选择的资源。处理代理的操作后，环境被配置为为代理提供有关新网络状态的数值奖励和信息。通过仿真将四个不同药物的阻塞性能与MCF-eons中使用的3个基线启发式方法进行了比较。 NSFNET和COST239网络拓扑获得的结果表明，表现最佳的代理平均而言，在阻止最佳性基线启发式方法方面，最多可降低四倍的降低。

This paper introduces the novel CNN-based encoder Twin Embedding Network (TEN), for the jigsaw puzzle problem (JPP), which represents a puzzle piece with respect to its boundary in a latent embedding space. Combining this latent representation with a simple distance measure, we demonstrate improved accuracy levels of our newly proposed pairwise compatibility measure (CM), compared to that of various classical methods, for degraded puzzles with eroded tile boundaries. We focus on this problem instance for our case study, as it serves as an appropriate testbed for real-world scenarios. Specifically, we demonstrated an improvement of up to 8.5% and 16.8% in reconstruction accuracy, for so-called Type-1 and Type-2 problem variants, respectively. Furthermore, we also demonstrated that TEN is faster by a few orders of magnitude, on average, than a typical deep neural network (NN) model, i.e., it is as fast as the classical methods. In this regard, the paper makes a significant first attempt at bridging the gap between the relatively low accuracy (of classical methods and the intensive computational complexity (of NN models), for practical, real-world puzzle-like problems.