Deep learning architectures have achieved promising results in different areas (e.g., medicine, agriculture, and security). However, using those powerful techniques in many real applications becomes challenging due to the large labeled collections required during training. Several works have pursued solutions to overcome it by proposing strategies that can learn more for less, e.g., weakly and semi-supervised learning approaches. As these approaches do not usually address memorization and sensitivity to adversarial examples, this paper presents three deep metric learning approaches combined with Mixup for incomplete-supervision scenarios. We show that some state-of-the-art approaches in metric learning might not work well in such scenarios. Moreover, the proposed approaches outperform most of them in different datasets.

Thanks to Hollywood, the first thing people tend to think of when they hear "artificial intelligence" is a dystopian future where humanity is at war with its electronic overlords – Terminator, Ex Machina and I, Robot come to mind. "If you ask a random stranger what AI is, they're likely to talk about robots that take over the world," Peter van der Putten, Director AI Lab at Pegasystems, explained to The Mandarin. In his role, van der Putten determines how AI can drive change and impact business, arts and science, and more in a responsible, customer centric and ethical manner. "Responsible and trustworthy AI can be used to have a meaningful impact, improve the life of citizens, customers, and businesses," he said. With oversight, regulations, responsible data use and the right tools that enable business logic to be coded simply, AI can be fair and free from bias, making the future much brighter than Hollywood suggests.

New South Wales digital minister Victor Dominello has asked the state's information and privacy watchdogs to undertake a "scan of the AI and privacy landscape" in the wake of the robodebt royal commission launch. The move is a possible precursor to Australia's first Artificial Intelligence commissioner, a role the outgoing minister backed earlier this week. Mr Dominello told reporters on Monday a dedicated AI watchdog would be "good to see" as the next layer of independent oversight of government technologies and digital services. He said it likely won't arrive before he retires from politics early next year, but an AI commissioner is being explored and will be necessary to maintain public trust in government technology. "I want to make sure that there is oversight [and] there's checks and balances all the way because there will be failures," Mr Dominello said.

This COVID-19 pandemic is so dreadful that it leads to severe anxiety, phobias, and complicated feelings or emotions. Even after vaccination against Coronavirus has been initiated, people feelings have become more diverse and complex, and our goal is to understand and unravel their sentiments in this research using some Deep Learning techniques. Social media is currently the best way to express feelings and emotions, and with the help of it, specifically Twitter, one can have a better idea of what is trending and what is going on in people minds. Our motivation for this research is to understand the sentiment of people regarding the vaccination process, and their diverse thoughts regarding this. In this research, the timeline of the collected tweets was from December 21 to July 21, and contained tweets about the most common vaccines available recently from all across the world. The sentiments of people regarding vaccines of all sorts were assessed by using a Natural Language Processing (NLP) tool named Valence Aware Dictionary for sEntiment Reasoner (VADER). By initializing the sentiment polarities into 3 groups (positive, negative and neutral), the overall scenario was visualized here and our findings came out as 33.96% positive, 17.55% negative and 48.49% neutral responses. Recurrent Neural Network (RNN) oriented architecture such as Long Short-Term Memory (LSTM and Bi-LSTM) is used to assess the performance of the predictive models, with LSTM achieving an accuracy of 90.59% and Bi-LSTM achieving an accuracy of 90.83%. Other performance metrics such as Precision, Recall, F-1 score, and Confusion matrix were also shown to validate our models and findings more effectively. This study will help everyone understand public opinion on the COVID-19 vaccines and impact the aim of eradicating the Coronavirus from our beautiful world.

Towards developing effective and efficient brain-computer interface (BCI) systems, precise decoding of brain activity measured by electroencephalogram (EEG), is highly demanded. Traditional works classify EEG signals without considering the topological relationship among electrodes. However, neuroscience research has increasingly emphasized network patterns of brain dynamics. Thus, the Euclidean structure of electrodes might not adequately reflect the interaction between signals. To fill the gap, a novel deep learning framework based on the graph convolutional neural networks (GCNs) is presented to enhance the decoding performance of raw EEG signals during different types of motor imagery (MI) tasks while cooperating with the functional topological relationship of electrodes. Based on the absolute Pearson's matrix of overall signals, the graph Laplacian of EEG electrodes is built up. The GCNs-Net constructed by graph convolutional layers learns the generalized features. The followed pooling layers reduce dimensionality, and the fully-connected softmax layer derives the final prediction. The introduced approach has been shown to converge for both personalized and group-wise predictions. It has achieved the highest averaged accuracy, 93.06% and 88.57% (PhysioNet Dataset), 96.24% and 80.89% (High Gamma Dataset), at the subject and group level, respectively, compared with existing studies, which suggests adaptability and robustness to individual variability. Moreover, the performance is stably reproducible among repetitive experiments for cross-validation. The excellent performance of our method has shown that it is an important step towards better BCI approaches. To conclude, the GCNs-Net filters EEG signals based on the functional topological relationship, which manages to decode relevant features for brain motor imagery.

Abstract--We present a method for generating, predicting, and using Spatiotemporal Occupancy Grid Maps (SOGM), which embed future semantic information of real dynamic scenes. We present an auto-labeling process that creates SOGMs from noisy real navigation data. We use a 3D-2D feedforward architecture, trained to predict the future time steps of SOGMs, given 3D lidar frames as input. Our pipeline is entirely self-supervised, thus enabling lifelong learning for real robots. The network is composed of a 3D back-end that extracts rich features and enables the semantic segmentation of the lidar frames, and a 2D front-end that predicts the future information embedded in the SOGM representation, potentially capturing the complexities and uncertainties of real-world multi-agent, multi-future interactions. We also design a navigation system that uses these predicted SOGMs within planning, after they have been transformed into Spatiotemporal Risk Maps (SRMs). We verify our navigation system's abilities in simulation, validate it on a real robot, study SOGM predictions on real data in various circumstances, and Time is represented as a color, from red (now) to yellow (future). REDICTING the future has always fascinated humanity. In this paper, we provide a detailed curiosity for the unknown has never faded. But we tend to description of the collection of algorithms required for these forget that we already predict the future constantly in our daily various tasks, for a complete view of the overall approach, as lives, only it is for a short horizon. Walking in the street, illustrated in Figure 2. catching a falling object, or driving a car, all these actions Some of the algorithms we use have already been introduced require a certain level of anticipation. In the first one [1], we described can become quite good at predicting what might happen for how to automatically annotate 3D lidar points, and train a the next few seconds in many situations; what about robots? In the second one We study this question in the context of a concrete example: [2], our system learned to predict the future of dynamic a robot learning on its own to navigate among humans or scenes as SOGMs. Until now, we only evaluated results in dynamic objects in an indoor space. Our approach allows the a simulated environment.

Non-autoregressive (NAR) models can generate sentences with less computation than autoregressive models but sacrifice generation quality. Previous studies addressed this issue through iterative decoding. This study proposes using nearest neighbors as the initial state of an NAR decoder and editing them iteratively. We present a novel training strategy to learn the edit operations on neighbors to improve NAR text generation. Experimental results show that the proposed method (NeighborEdit) achieves higher translation quality (1.69 points higher than the vanilla Transformer) with fewer decoding iterations (one-eighteenth fewer iterations) on the JRC-Acquis En-De dataset, the common benchmark dataset for machine translation using nearest neighbors. We also confirm the effectiveness of the proposed method on a data-to-text task (WikiBio). In addition, the proposed method outperforms an NAR baseline on the WMT'14 En-De dataset. We also report analysis on neighbor examples used in the proposed method.

--Network alignment task, which aims to identify corresponding nodes in different networks, is of great significance for many subsequent applications. Without the need for labeled anchor links, unsupervised alignment methods have been attracting more and more attention. However, the topological consistency assumptions defined by existing methods are generally low-order and less accurate because only the edge-indiscriminative topological pattern is considered, which is especially risky in an unsupervised setting. T o reposition the focus of the alignment process from low-order to higher-order topological consistency, in this paper, we propose a fully unsupervised network alignment framework named HTC. The proposed higher-order topological consistency is formulated based on edge orbits, which is merged into the information aggregation process of a graph convolutional network so that the alignment consistencies are transformed into the similarity of node embeddings. Furthermore, the encoder is trained to be multi-orbit-aware and then be refined to identify more trusted anchor links. Node correspondence is comprehensively evaluated by integrating all different orders of consistency. In addition to sound theoretical analysis, the superiority of the proposed method is also empirically demonstrated through extensive experimental evaluation. On three pairs of real-world datasets and two pairs of synthetic datasets, our HTC consistently outperforms a wide variety of unsupervised and supervised methods with the least or comparable time consumption. It also exhibits robustness to structural noise as a result of our multi-orbit-aware training mechanism. Network alignment task, which aims to identify entity correspondence across different networks, is usually the very first step of many downstream analyzing tasks. For instance, recognizing the same user on different social networks can facilitate friend suggestion, item recommendation, personalized advertisement [1]-[5]. Similar scenarios also exist widely in other fields, such as protein network analysis [6], knowledge discovery [7], etc. Identifying corresponding nodes across different networks is an extremely hard task, even for humans. Manually labelling correspondence can be prohibitively challenging, expensive (in human efforts, time, and money costs), and tedious [8]. Due to such obstacles, in some cases, it may be impractical to get access to sufficient labels for training well-performed supervised or even semi-supervised models [4], [9]. By contrast, unsupervised models can be trained without the need for labeled data, which is more flexible and practical in real-world application scenarios. Thus, unsupervised alignment methods have been drawing a surge of interest recently [10]-[12].

Development of methods to detect fake news (FN) in low-resource languages has been impeded by a lack of training data. In this study, we solve the problem by using only training data from a high-resource language. Our FN-detection system permitted this strategy by applying adversarial learning that transfers the detection knowledge through languages. To assist the knowledge transfer, our system judges the reliability of articles by exploiting source information, which is a cross-lingual feature that represents the credibility of the speaker. In experiments, our system got 3.71% higher accuracy than a system that uses a machine-translated training dataset. In addition, our suggested cross-lingual feature exploitation for fake news detection improved accuracy by 3.03%.

In this paper we introduce the FooDI-ML dataset. This dataset contains over 1.5M unique images and over 9.5M store names, product names descriptions, and collection sections gathered from the Glovo application. The data made available corresponds to food, drinks and groceries products from 37 countries in Europe, the Middle East, Africa and Latin America. The dataset comprehends 33 languages, including 870K samples of languages of countries from Eastern Europe and Western Asia such as Ukrainian and Kazakh, which have been so far underrepresented in publicly available visio-linguistic datasets. The dataset also includes widely spoken languages such as Spanish and English. To assist further research, we include benchmarks over two tasks: text-image retrieval and conditional image generation.