Multilingual models have demonstrated impressive cross-lingual transfer performance. However, test sets like XNLI are monolingual at the example level. In multilingual communities, it is common for polyglots to code-mix when conversing with each other. Inspired by this phenomenon, we present two strong black-box adversarial attacks (one word-level, one phrase-level) for multilingual models that push their ability to handle code-mixed sentences to the limit. The former uses bilingual dictionaries to propose perturbations and translations of the clean example for sense disambiguation. The latter directly aligns the clean example with its translations before extracting phrases as perturbations. Our phrase-level attack has a success rate of 89.75% against XLM-R-large, bringing its average accuracy of 79.85 down to 8.18 on XNLI. Finally, we propose an efficient adversarial training scheme that trains in the same number of steps as the original model and show that it improves model accuracy.

The pandemic, chronic disease, rising costs, an ageing population, limited resources, health worker shortages, and a data explosion are converging to accelerate digital health globally. WHO has launched a major transformative agenda on digital health, "The use and scale up of digital health solutions can revolutionize how people worldwide achieve higher standards of health, and access services to promote and protect their health and well-being." At a granular level, technology offers improved efficiency; better treatment choice; more efficient diagnosis; faster drug development; better prediction of disease outbreaks, medical consultations with patients where there is no doctor and improved medical training. Consumers can access information they need to proactively manage their own health and wellness. AI can identify specific demographics or geographies where population health issues exist, then targeting and precisely implementing education and prevention programs.

Mobile health (mHealth) apps such as menstrual trackers provide a rich source of self-tracked health observations that can be leveraged for health-relevant research. However, such data streams have questionable reliability since they hinge on user adherence to the app. Therefore, it is crucial for researchers to separate true behavior from self-tracking artifacts. By taking a machine learning approach to modeling self-tracked cycle lengths, we can both make more informed predictions and learn the underlying structure of the observed data. In this work, we propose and evaluate a hierarchical, generative model for predicting next cycle length based on previously-tracked cycle lengths that accounts explicitly for the possibility of users skipping tracking their period. Our model offers several advantages: 1) accounting explicitly for self-tracking artifacts yields better prediction accuracy as likelihood of skipping increases; 2) because it is a generative model, predictions can be updated online as a given cycle evolves, and we can gain interpretable insight into how these predictions change over time; and 3) its hierarchical nature enables modeling of an individual's cycle length history while incorporating population-level information. Our experiments using mHealth cycle length data encompassing over 186,000 menstruators with over 2 million natural menstrual cycles show that our method yields state-of-the-art performance against neural network-based and summary statistic-based baselines, while providing insights on disentangling menstrual patterns from self-tracking artifacts. This work can benefit users, mHealth app developers, and researchers in better understanding cycle patterns and user adherence.

How to improve generative modeling by better exploiting spatial regularities and coherence in images? We introduce a novel neural network for building image generators (decoders) and apply it to variational autoencoders (VAEs). In our spatial dependency networks (SDNs), feature maps at each level of a deep neural net are computed in a spatially coherent way, using a sequential gating-based mechanism that distributes contextual information across 2-D space. We show that augmenting the decoder of a hierarchical VAE by spatial dependency layers considerably improves density estimation over baseline convolutional architectures and the state-of-the-art among the models within the same class. Furthermore, we demonstrate that SDN can be applied to large images by synthesizing samples of high quality and coherence. In a vanilla VAE setting, we find that a powerful SDN decoder also improves learning disentangled representations, indicating that neural architectures play an important role in this task. Our results suggest favoring spatial dependency over convolutional layers in various VAE settings. The accompanying source code is given at https://github.com/djordjemila/sdn.

Language is inherent and compulsory for human communication. Whether expressed in a written or spoken way, it ensures understanding between people of the same and different regions. With the growing awareness and effort to include more low-resourced languages in NLP research, African languages have recently been a major subject of research in machine translation, and other text-based areas of NLP. However, there is still very little comparable research in speech recognition for African languages. Interestingly, some of the unique properties of African languages affecting NLP, like their diacritical and tonal complexities, have a major root in their speech, suggesting that careful speech interpretation could provide more intuition on how to deal with the linguistic complexities of African languages for text-based NLP. OkwuGb\'e is a step towards building speech recognition systems for African low-resourced languages. Using Fon and Igbo as our case study, we conduct a comprehensive linguistic analysis of each language and describe the creation of end-to-end, deep neural network-based speech recognition models for both languages. We present a state-of-art ASR model for Fon, as well as benchmark ASR model results for Igbo. Our linguistic analyses (for Fon and Igbo) provide valuable insights and guidance into the creation of speech recognition models for other African low-resourced languages, as well as guide future NLP research for Fon and Igbo. The Fon and Igbo models source code have been made publicly available.

ZEISS Germany, Nikon Instruments, Ariadne.ai, Mindpeak, Aiforia, Celly.AI Corporation, SVision LLC, Scopio Lab, AlexaPath, MicroscopeIT, Nanotronics, AiScope, Thermo Fisher, Ash Vision, Sigtuple, GoMicro, MantiScope, Cognex, Paige.AI, Motic, and Pleora Technologies among others are the players in the artificial intelligence microscopy market.Brooklyn, New York, March 10, 2021 (GLOBE NEWSWIRE) -- According to a new market research report published by Global Market Estimates, the Artificial Intelligence Microscopy Market will grow with a CAGR value of 7.2 percent from 2021 to 2026. The market for AI in microscopy will increase with the rising prevalence of infectious disease, cancer, and other disorders that require routine blood morphology analysis. Moreover, with the rising need for advanced live-cell imaging, cloud sharing, and efficient lab workflow, clubbed with the rising research activities in the field of drug testing and toxicology, the market will grow rapidly from 2020 to 2021. Browse 151 Market Data Tables and 111 Figures spread through 181 Pages and in-depth TOC on “Global Artificial Intelligence Microscopy Market - Forecast to 2026" https://www.globalmarketestimates.com/market-report/global-artificial-intelligence-microscopy-market-2824 Key Market Insights Optical or light microscopy is estimated to be the largest segment as per market share or market revenue generation from 2021 to 2026Cancer disease diagnosis and prevention is the major driving factor for this segment to grow rapidlyThe market for independent & private laboratories will be dominant from 2021 to 2026ZEISS Germany, Nikon Instruments, Ariadne.ai, Mindpeak, Aiforia, Celly.AI Corporation, SVision LLC, Scopio Lab, AlexaPath, MicroscopeIT, Nanotronics, AiScope, Thermo Fisher, Ash Vision, Sigtuple, GoMicro, MantiScope, Cognex, Paige.AI, Motic, and Pleora Technologies among others are the players in the artificial intelligence microscopy market Browse the Report @ https://www.globalmarketestimates.com/market-report/global-artificial-intelligence-microscopy-market-2824 Imaging Modalities Outlook (Revenue, USD Billion, 2019-2026) Optical MicroscopyElectron MicroscopyScanning Probe Microscopy Application Outlook (Revenue, USD Billion, 2019-2026) Clinical PathologyNeuron MorphologyCell BiologyPharmacology & ToxicologyOncologyOthers Product Type Outlook (Revenue, USD Billion, 2019-2026) AI-Enabled Cloud SoftwareAI-Enabled Microscopes End-User Outlook (Revenue, USD Billion, 2019-2026) Hospital LaboratoriesIndependent & Private LaboratoriesAcademic Research LabsPharmaceutical & Biotechnology LaboratoriesContract Research Organizations Regional Outlook (Revenue, USD Billion, 2019-2026) North America The U.S.CanadaMexico Europe GermanyUKFranceSpainItalyRest of Europe Asia Pacific ChinaIndiaJapanSouth KoreaAustraliaRest of APAC Central & South America BrazilArgentinaRest of CSA Middle East & Africa Saudi ArabiaUAERest of MEA Website: Global Market Estimates CONTACT: Contact: Yash Jain Email address: yash.jain@globalmarketestimates.com Phone Number: +16026667238

Hate speech on social media is a growing concern, and automated methods have so far been sub-par at reliably detecting it. A major challenge lies in the potentially evasive nature of hate speech due to the ambiguity and fast evolution of natural language. To tackle this, we introduce a vectorisation based on a crowd-sourced and continuously updated dictionary of hate words and propose fusing this approach with standard word embedding in order to improve the classification performance of a CNN model. To train and test our model we use a merge of two established datasets (110,748 tweets in total). By adding the dictionary-enhanced input, we are able to increase the CNN model's predictive power and increase the F1 macro score by seven percentage points.

As transparency becomes key for robotics and AI, it will be necessary to evaluate the methods through which transparency is provided, including automatically generated natural language (NL) explanations. Here, we explore parallels between the generation of such explanations and the much-studied field of evaluation of Natural Language Generation (NLG). Specifically, we investigate which of the NLG evaluation measures map well to explanations. We present the ExBAN corpus: a crowd-sourced corpus of NL explanations for Bayesian Networks. We run correlations comparing human subjective ratings with NLG automatic measures. We find that embedding-based automatic NLG evaluation methods, such as BERTScore and BLEURT, have a higher correlation with human ratings, compared to word-overlap metrics, such as BLEU and ROUGE. This work has implications for Explainable AI and transparent robotic and autonomous systems.

Generally, when learners are now studying the knowledge of the reinforcement learning algorithm at the beginning, the algorithm we first came up in learner's mind is the Q-learning algorithm, which is a classical reinforcement learning algorithm based on value iteration. In the state-to-action mapping process, an algorithm based on value iteration allows the system to explore in accordance with the policy guidelines, and update the state value at each step of the exploration. Then, in value-based iteration, we have several problems that cannot prevent that. For example, when the value of each state is updated, it is necessary to estimate the probability of all actions. Unlike the discrete action of walking a maze, some cases such as robot control and automatic driving since the massive state information brought by continuous actions makes the calculation process almost impossible by tabular computation. At this time, Policy Gradient, a reinforcement learning algorithm based on iteration policy, came into being. The policy gradient no longer calculates the reward, but directly calculates the probability of taking an action in a certain state, and directly selects the action through the probability.

Digital twins are meant to bridge the gap between real-world physical systems and virtual representations. Both stand-alone and descriptive digital twins incorporate 3D geometric models, which are the physical representations of objects in the digital replica. Digital twin applications are required to rapidly update internal parameters with the evolution of their physical counterpart. Due to an essential need for having high-quality geometric models for accurate physical representations, the storage and bandwidth requirements for storing 3D model information can quickly exceed the available storage and bandwidth capacity. In this work, we demonstrate a novel approach to geometric change detection in the context of a digital twin. We address the issue through a combined solution of Dynamic Mode Decomposition (DMD) for motion detection, YOLOv5 for object detection, and 3D machine learning for pose estimation. DMD is applied for background subtraction, enabling detection of moving foreground objects in real-time. The video frames containing detected motion are extracted and used as input to the change detection network. The object detection algorithm YOLOv5 is applied to extract the bounding boxes of detected objects in the video frames. Furthermore, the rotational pose of each object is estimated in a 3D pose estimation network. A series of convolutional neural networks conducts feature extraction from images and 3D model shapes. Then, the network outputs the estimated Euler angles of the camera orientation with respect to the object in the input image. By only storing data associated with a detected change in pose, we minimize necessary storage and bandwidth requirements while still being able to recreate the 3D scene on demand.