Or is it just another hyped innovation? It comes with no surprise how AI today becomes a catchall term that is said out loud in the job market. The US and China are in nip and tuck in the AI race for supremacy. Although China aims to be the technology leader by 2030, the economy is still at a struggle phase with a slowdown and trade war with the US. Emerging trends in artificial intelligence (AI) significantly points toward having a geopolitical disruption in the foreseeable future.

An end-to-end solution for handwritten numeral string recognition is proposed, in which the numeral string is considered as composed of objects automatically detected and recognized by a YoLo-based model. The main contribution of this paper is to avoid heuristic-based methods for string preprocessing and segmentation, the need for task-oriented classifiers, and also the use of specific constraints related to the string length. A robust experimental protocol based on several numeral string datasets, including one composed of historical documents, has shown that the proposed method is a feasible end-to-end solution for numeral string recognition. Besides, it reduces the complexity of the string recognition task considerably since it drops out classical steps, in special preprocessing, segmentation, and a set of classifiers devoted to strings with a specific length.

In this paper, we proposed two modified neural network architectures based on SFANet and SegNet respectively for accurate and efficient crowd counting. Inspired by SFANet, the first model is attached with two novel multi-scale-aware modules, called ASSP and CAN. This model is called M-SFANet. The encoder of M-SFANet is enhanced with ASSP containing parallel atrous convolution with different sampling rates and hence able to extract multi-scale features of the target object and incorporate larger context. To further deal with scale variation throughout an input image, we leverage contextual module called CAN which adaptively encodes the scales of the contextual information. The combination yields an effective model for counting in both dense and sparse crowd scenes. Based on the SFANet's decoder structure, M-SFANet's decoder has dual paths, for density map generation and attention map generation. The second model is called M-SegNet. For M-SegNet, we simply change bilinear upsampling used in SFANet to max unpooling originally from SegNet and propose the faster model while providing competitive counting performance. Designed for high-speed surveillance applications, M-SegNet has no additional multi-scale-aware module in order to not increase the complexity. Both models are encoder-decoder based architectures and end-to-end trainable. We also conduct extensive experiments on four crowd counting datasets and one vehicle counting dataset to show that these modifications yield algorithms that could outperform some state-of-the-art crowd counting methods.

Amazon's voice assistant, Alexa, can now help users who are worried about having been infected with novel coronavirus. According to the company, users can now query any device equipped with Alexa with phrases like'Alexa, what do I do if I think I have coronavirus?' and the assistant will begin to quiz them about their symptoms. The assistant will then provide users with information pulled from the Centers for Disease Control and Prevention in an effort to provide sound advice on what to do. Amazon's line of Alexa-enabled devices like the Echo (pictured) can now provide users guidance on what to do if they think they may have novel coronavirus As a part of the update, users can now also ask Alexa to'sing along' while they wash their hands to help them time the task for 20 seconds - the recommended amount of time for proper sanitation. That feature is currently available in Australia, Brazil, Canada, France, India, the UK, and the US and mirrors a similar feature rolled out by Google on its home assistants. The feature most closely mirrors one rolled out by Apple this week which updated its own voice assistant, Siri, to help provide users with guidance on coronavirus.

Internet of Things (IoT) devices have been the primary force behind the biggest distributed denial of service (DDoS) botnet attacks for some time. It's a threat that has never really diminished, as numerous IoT device manufacturers continue to ship products that cannot be properly secured. A10 Networks, a leading application delivery controller manufacturer, has been keeping tabs on DDoS attacks around the globe for several years now. The company's quarterly State of DDoS Weapons Report provides a very useful snapshot of the current activity and threat level. The recently-published report for the fourth quarter of 2019 is noteworthy in identifying some new trends that are amplifying DDoS attacks, including a common vulnerability in the WD-Discovery protocol that is being widely exploited and the use of autonomous number systems (ANS) to track attacks back to their source.

Machine learning techniques always aim to reduce the generalized prediction error. In order to reduce it, ensemble methods present a good approach combining several models that results in a greater forecasting capacity. The Random Machines already have been demonstrated as strong technique, i.e: high predictive power, to classification tasks, in this article we propose an procedure to use the bagged-weighted support vector model to regression problems. Simulation studies were realized over artificial datasets, and over real data benchmarks. The results exhibited a good performance of Regression Random Machines through lower generalization error without needing to choose the best kernel function during tuning process.

Vector representations of graphs and relational structures, whether hand-crafted feature vectors or learned representations, enable us to apply standard data analysis and machine learning techniques to the structures. A wide range of methods for generating such embeddings have been studied in the machine learning and knowledge representation literature. However, vector embeddings have received relatively little attention from a theoretical point of view. Starting with a survey of embedding techniques that have been used in practice, in this paper we propose two theoretical approaches that we see as central for understanding the foundations of vector embeddings. We draw connections between the various approaches and suggest directions for future research.

In this paper, we propose a method of distributed stochastic gradient descent (SGD), with low communication load and computational complexity, and still fast convergence. To reduce the communication load, at each iteration of the algorithm, the worker nodes calculate and communicate some scalers, that are the directional derivatives of the sample functions in some \emph{pre-shared directions}. However, to maintain accuracy, after every specific number of iterations, they communicate the vectors of stochastic gradients. To reduce the computational complexity in each iteration, the worker nodes approximate the directional derivatives with zeroth-order stochastic gradient estimation, by performing just two function evaluations rather than computing a first-order gradient vector. The proposed method highly improves the convergence rate of the zeroth-order methods, guaranteeing order-wise faster convergence. Moreover, compared to the famous communication-efficient methods of model averaging (that perform local model updates and periodic communication of the gradients to synchronize the local models), we prove that for the general class of non-convex stochastic problems and with reasonable choice of parameters, the proposed method guarantees the same orders of communication load and convergence rate, while having order-wise less computational complexity. Experimental results on various learning problems in neural networks applications demonstrate the effectiveness of the proposed approach compared to various state-of-the-art distributed SGD methods.

In multicriteria decision aiding (MCDA), the Choquet integral has been used as an aggregation operator to deal with the case of interacting decision criteria. While the application of the Choquet integral for ranking problems have been receiving most of the attention, this paper rather focuses on multicriteria sorting problems (MCSP). In the Choquet integral context, a practical problem that arises is related to the elicitation of parameters known as the Choquet capacities. We address the problem of Choquet capacity identification for MCSP by applying the Stochastic Acceptability Multicriteri Analysis (SMAA), proposing the SMAA-S-Choquet method. The proposed method is also able to model uncertain data that may be present in both decision matrix and limiting profiles, the latter a parameter associated with the sorting problematic. We also introduce two new descriptive measures in order to conduct reverse analysis regarding the capacities: the Scenario Acceptability Index and the Scenario Central Capacity vector.

Multi-label classification consists in classifying an instance into two or more classes simultaneously. It is a very challenging task present in many real-world applications, such as classification of biology, image, video, audio, and text. Recently, the interest in interpretable classification models has grown, partially as a consequence of regulations such as the General Data Protection Regulation. In this context, we propose a multi-objective evolutionary algorithm that generates multiple rule-based multi-label classification models, allowing users to choose among models that offer different compromises between predictive power and interpretability. An important contribution of this work is that different from most algorithms, which usually generate models based on lists (ordered collections) of rules, our algorithm generates models based on sets (unordered collections) of rules, increasing interpretability. Also, by employing a conflict avoidance algorithm during the rule-creation, every rule within a given model is guaranteed to be consistent with every other rule in the same model. Thus, no conflict resolution strategy is required, evolving simpler models. We conducted experiments on synthetic and real-world datasets and compared our results with state-of-the-art algorithms in terms of predictive performance (F-Score) and interpretability (model size), and demonstrate that our best models had comparable F-Score and smaller model sizes.