目的：确定逼真，但是电磁图的计算上有效模型可用于预先列车，具有广泛的形态和特定于给定条件的形态和异常 - T波段（TWA）由于创伤后应激障碍，或重点 - 在稀有人的小型数据库上显着提高了性能。方法：使用先前经过验证的人工ECG模型，我们生成了180,000人的人工ECG，有或没有重要的TWA，具有不同的心率，呼吸率，TWA幅度和ECG形态。在70,000名患者中培训的DNN进行分类为25种不同的节奏，将输出层修改为二进制类（TWA或NO-TWA，或等效，PTSD或NO-PTSD），并对人工ECG进行转移学习。在最终转移学习步骤中，DNN在ECG的培训和交叉验证，从12个PTE和24个控件，用于使用三个数据库的所有组合。主要结果：通过进行转移学习步骤，使用预先培训的心律失常DNN，人工数据和真实的PTSD相关的心电图数据，发现了最佳性能的方法（AUROC = 0.77，精度= 0.72，F1-SCATE = 0.64） 。从训练中删除人工数据导致性能的最大下降。从培训中取出心律失常数据提供了适度但重要的，表现下降。最终模型在人工数据上显示出在性能下没有显着下降，表明没有过度拟合。意义：在医疗保健中，通常只有一小部分高质量数据和标签，或更大的数据库，质量较低（和较差的相关）标签。这里呈现的范式，涉及基于模型的性能提升，通过在大型现实人工数据库和部分相关的真实数据库上传输学习来提供解决方案。

A comprehensive pharmaceutical recommendation system was designed based on the patients and drugs features extracted from Drugs.com and Druglib.com. First, data from these databases were combined, and a dataset of patients and drug information was built. Secondly, the patients and drugs were clustered, and then the recommendation was performed using different ratings provided by patients, and importantly by the knowledge obtained from patients and drug specifications, and considering drug interactions. To the best of our knowledge, we are the first group to consider patients conditions and history in the proposed approach for selecting a specific medicine appropriate for that particular user. Our approach applies artificial intelligence (AI) models for the implementation. Sentiment analysis using natural language processing approaches is employed in pre-processing along with neural network-based methods and recommender system algorithms for modeling the system. In our work, patients conditions and drugs features are used for making two models based on matrix factorization. Then we used drug interaction to filter drugs with severe or mild interactions with other drugs. We developed a deep learning model for recommending drugs by using data from 2304 patients as a training set, and then we used data from 660 patients as our validation set. After that, we used knowledge from critical information about drugs and combined the outcome of the model into a knowledge-based system with the rules obtained from constraints on taking medicine.

Nowadays, the current neural network models of dialogue generation(chatbots) show great promise for generating answers for chatty agents. But they are short-sighted in that they predict utterances one at a time while disregarding their impact on future outcomes. Modelling a dialogue's future direction is critical for generating coherent, interesting dialogues, a need that has led traditional NLP dialogue models that rely on reinforcement learning. In this article, we explain how to combine these objectives by using deep reinforcement learning to predict future rewards in chatbot dialogue. The model simulates conversations between two virtual agents, with policy gradient methods used to reward sequences that exhibit three useful conversational characteristics: the flow of informality, coherence, and simplicity of response (related to forward-looking function). We assess our model based on its diversity, length, and complexity with regard to humans. In dialogue simulation, evaluations demonstrated that the proposed model generates more interactive responses and encourages a more sustained successful conversation. This work commemorates a preliminary step toward developing a neural conversational model based on the long-term success of dialogues.

Pruning refers to the elimination of trivial weights from neural networks. The sub-networks within an overparameterized model produced after pruning are often called Lottery tickets. This research aims to generate winning lottery tickets from a set of lottery tickets that can achieve similar accuracy to the original unpruned network. We introduce a novel winning ticket called Cyclic Overlapping Lottery Ticket (COLT) by data splitting and cyclic retraining of the pruned network from scratch. We apply a cyclic pruning algorithm that keeps only the overlapping weights of different pruned models trained on different data segments. Our results demonstrate that COLT can achieve similar accuracies (obtained by the unpruned model) while maintaining high sparsities. We show that the accuracy of COLT is on par with the winning tickets of Lottery Ticket Hypothesis (LTH) and, at times, is better. Moreover, COLTs can be generated using fewer iterations than tickets generated by the popular Iterative Magnitude Pruning (IMP) method. In addition, we also notice COLTs generated on large datasets can be transferred to small ones without compromising performance, demonstrating its generalizing capability. We conduct all our experiments on Cifar-10, Cifar-100 & TinyImageNet datasets and report superior performance than the state-of-the-art methods.

We address interactive panoptic annotation, where one segment all object and stuff regions in an image. We investigate two graph-based segmentation algorithms that both enforce connectivity of each region, with a notable class-aware Integer Linear Programming (ILP) formulation that ensures global optimum. Both algorithms can take RGB, or utilize the feature maps from any DCNN, whether trained on the target dataset or not, as input. We then propose an interactive, scribble-based annotation framework.

We introduce an information-maximization approach for the Generalized Category Discovery (GCD) problem. Specifically, we explore a parametric family of loss functions evaluating the mutual information between the features and the labels, and find automatically the one that maximizes the predictive performances. Furthermore, we introduce the Elbow Maximum Centroid-Shift (EMaCS) technique, which estimates the number of classes in the unlabeled set. We report comprehensive experiments, which show that our mutual information-based approach (MIB) is both versatile and highly competitive under various GCD scenarios. The gap between the proposed approach and the existing methods is significant, more so when dealing with fine-grained classification problems. Our code: \url{https://github.com/fchiaroni/Mutual-Information-Based-GCD}.

Recent studies have revealed that, beyond conventional accuracy, calibration should also be considered for training modern deep neural networks. To address miscalibration during learning, some methods have explored different penalty functions as part of the learning objective, alongside a standard classification loss, with a hyper-parameter controlling the relative contribution of each term. Nevertheless, these methods share two major drawbacks: 1) the scalar balancing weight is the same for all classes, hindering the ability to address different intrinsic difficulties or imbalance among classes; and 2) the balancing weight is usually fixed without an adaptive strategy, which may prevent from reaching the best compromise between accuracy and calibration, and requires hyper-parameter search for each application. We propose Class Adaptive Label Smoothing (CALS) for calibrating deep networks, which allows to learn class-wise multipliers during training, yielding a powerful alternative to common label smoothing penalties. Our method builds on a general Augmented Lagrangian approach, a well-established technique in constrained optimization, but we introduce several modifications to tailor it for large-scale, class-adaptive training. Comprehensive evaluation and multiple comparisons on a variety of benchmarks, including standard and long-tailed image classification, semantic segmentation, and text classification, demonstrate the superiority of the proposed method. The code is available at https://github.com/by-liu/CALS.

We tackle the problem of novel class discovery and localization (NCDL). In this setting, we assume a source dataset with supervision for only some object classes. Instances of other classes need to be discovered, classified, and localized automatically based on visual similarity without any human supervision. To tackle NCDL, we propose a two-stage object detection network Region-based NCDL (RNCDL) that uses a region proposal network to localize regions of interest (RoIs). We then train our network to learn to classify each RoI, either as one of the known classes, seen in the source dataset, or one of the novel classes, with a long-tail distribution constraint on the class assignments, reflecting the natural frequency of classes in the real world. By training our detection network with this objective in an end-to-end manner, it learns to classify all region proposals for a large variety of classes, including those not part of the labeled object class vocabulary. Our experiments conducted using COCO and LVIS datasets reveal that our method is significantly more effective than multi-stage pipelines that rely on traditional clustering algorithms. Furthermore, we demonstrate the generality of our approach by applying our method to a large-scale Visual Genome dataset, where our network successfully learns to detect various semantic classes without direct supervision.

在本说明中，我研究了制度和游戏理论假设，这些假设将阻止AI*表示的“超人级”弧形通用智能的出现。这些假设是（i）“心灵自由”，（ii）开源“访问” AI*，以及（iii）与AI*竞争的代表人类代理人的合理性。我证明，在这三个假设下，AI*不可能存在。该结果引起了公共政策的两个即时建议。首先，“克隆”以数字方式受到严格调节，并应禁止假设的脑部进入大脑。其次，如果不公开，应广泛进行AI*研究。

近年来，卷积神经网络（CNN）证明了它们在许多领域解决问题的能力，并且以前无法进行准确性。但是，这带有广泛的计算要求，这使得普通CPU无法提供所需的实时性能。同时，FPGA对加速CNN推断的兴趣激增。这是由于他们有能力创建具有不同级别的并行性的自定义设计。此外，与GPU相比，FPGA提供每瓦的性能更好。基于FPGA的CNN加速器的当前趋势是实现多个卷积层处理器（CLP），每个处理器都针对一层层量身定制。但是，CNN体系结构的日益增长的复杂性使得优化目标FPGA设备上可用的资源，以使最佳性能更具挑战性。在本文中，我们提出了CNN加速器和随附的自动设计方法，该方法采用元启发式学来分区可用的FPGA资源来设计多CLP加速器。具体而言，提出的设计工具采用模拟退火（SA）和禁忌搜索（TS）算法来查找所需的CLP数量及其各自的配置，以在给定的目标FPGA设备上实现最佳性能。在这里，重点是关键规格和硬件资源，包括数字信号处理器，阻止RAM和芯片内存储器带宽。提出了使用四个众所周知的基准CNN的实验结果和比较，表明所提出的加速框架既令人鼓舞又有前途。基于SA-/TS的多CLP比在加速Alexnet，Squeezenet 1.1，VGGNET和Googlenet架构上的最新单个/多CLP方法高1.31x-2.37倍高2.37倍。和VC709 FPGA板。