Textbook Question Answering is a complex task in the intersection of Machine Comprehension and Visual Question Answering that requires reasoning with multimodal information from text and diagrams. For the first time, this paper taps on the potential of transformer language models and bottom-up and top-down attention to tackle the language and visual understanding challenges this task entails. Rather than training a language-visual transformer from scratch we rely on pre-trained transformers, fine-tuning and ensembling. We add bottom-up and top-down attention to identify regions of interest corresponding to diagram constituents and their relationships, improving the selection of relevant visual information for each question and answer options. Our system ISAAQ reports unprecedented success in all TQA question types, with accuracies of 81.36%, 71.11% and 55.12% on true/false, text-only and diagram multiple choice questions. ISAAQ also demonstrates its broad applicability, obtaining state-of-the-art results in other demanding datasets.

The ageing population trend is correlated with an increased prevalence of acquired cognitive impairments such as dementia. Although there is no cure for dementia, a timely diagnosis helps in obtaining necessary support and appropriate medication. Researchers are working urgently to develop effective technological tools that can help doctors undertake early identification of cognitive disorder. In particular, screening for dementia in ageing Deaf signers of British Sign Language (BSL) poses additional challenges as the diagnostic process is bound up with conditions such as quality and availability of interpreters, as well as appropriate questionnaires and cognitive tests. On the other hand, deep learning based approaches for image and video analysis and understanding are promising, particularly the adoption of Convolutional Neural Network (CNN), which require large amounts of training data. In this paper, however, we demonstrate novelty in the following way: a) a multi-modal machine learning based automatic recognition toolkit for early stages of dementia among BSL users in that features from several parts of the body contributing to the sign envelope, e.g., hand-arm movements and facial expressions, are combined, b) universality in that it is possible to apply our technique to users of any sign language, since it is language independent, c) given the trade-off between complexity and accuracy of machine learning (ML) prediction models as well as the limited amount of training and testing data being available, we show that our approach is not over-fitted and has the potential to scale up.

Unhealthy behaviors, e.g., physical inactivity and unhealthful food choice, are the primary healthcare cost drivers in developed countries. Pervasive computational, sensing, and communication technology provided by smartphones and smartwatches have made it possible to support individuals in their everyday lives to develop healthier lifestyles. In this paper, we propose an exercise recommendation system that also predicts individual success rates . The system, consisting of two inter-connected recurrent neural networks (RNNs), uses the history of workouts to recommend the next workout activity for each individual. The system then predicts the probability of successful completion of the predicted activity by the individual. The prediction accuracy of this interconnected-RNN model is assessed on previously published data from a four-week mobile health experiment and is shown to improve upon previous predictions from a computational cognitive model.

Single image super-resolution is an effective way to enhance the spatial resolution of remote sensing image, which is crucial for many applications such as target detection and image classification. However, existing methods based on the neural network usually have small receptive fields and ignore the image detail. We propose a novel method named deep memory connected network (DMCN) based on a convolutional neural network to reconstruct high-quality super-resolution images. We build local and global memory connections to combine image detail with environmental information. To further reduce parameters and ease time-consuming, we propose downsampling units, shrinking the spatial size of feature maps. We test DMCN on three remote sensing datasets with different spatial resolution. Experimental results indicate that our method yields promising improvements in both accuracy and visual performance over the current state-of-the-art.

This paper presents a systematic review of benchmarks and approaches for explainability in Machine Reading Comprehension (MRC). We present how the representation and inference challenges evolved and the steps which were taken to tackle these challenges. We also present the evaluation methodologies to assess the performance of explainable systems. In addition, we identify persisting open research questions and highlight critical directions for future work.

White supremacists embrace a radical ideology that considers white people superior to people of other races. The critical influence of these groups is no longer limited to social media; they also have a significant effect on society in many ways by promoting racial hatred and violence. White supremacist hate speech is one of the most recently observed harmful content on social media.Traditional channels of reporting hate speech have proved inadequate due to the tremendous explosion of information, and therefore, it is necessary to find an automatic way to detect such speech in a timely manner. This research investigates the viability of automatically detecting white supremacist hate speech on Twitter by using deep learning and natural language processing techniques. Through our experiments, we used two approaches, the first approach is by using domain-specific embeddings which are extracted from white supremacist corpus in order to catch the meaning of this white supremacist slang with bidirectional Long Short-Term Memory (LSTM) deep learning model, this approach reached a 0.74890 F1-score. The second approach is by using the one of the most recent language model which is BERT, BERT model provides the state of the art of most NLP tasks. It reached to a 0.79605 F1-score. Both approaches are tested on a balanced dataset given that our experiments were based on textual data only. The dataset was combined from dataset created from Twitter and a Stormfront dataset compiled from that white supremacist forum.

Artificial Intelligence is providing astonishing results, with medicine being one of its favourite playgrounds. In a few decades, computers may be capable of formulating diagnoses and choosing the correct treatment, while robots may perform surgical operations, and conversational agents could interact with patients as virtual coaches. Machine Learning and, in particular, Deep Neural Networks are behind this revolution. In this scenario, important decisions will be controlled by standalone machines that have learned predictive models from provided data. Among the most challenging targets of interest in medicine are cancer diagnosis and therapies but, to start this revolution, software tools need to be adapted to cover the new requirements. In this sense, learning tools are becoming a commodity in Python and Matlab libraries, just to name two, but to exploit all their possibilities, it is essential to fully understand how models are interpreted and which models are more interpretable than others. In this survey, we analyse current machine learning models, frameworks, databases and other related tools as applied to medicine - specifically, to cancer research - and we discuss their interpretability, performance and the necessary input data. From the evidence available, ANN, LR and SVM have been observed to be the preferred models. Besides, CNNs, supported by the rapid development of GPUs and tensor-oriented programming libraries, are gaining in importance. However, the interpretability of results by doctors is rarely considered which is a factor that needs to be improved. We therefore consider this study to be a timely contribution to the issue.

The ability to continuously learn and adapt itself to new tasks, without losing grasp of already acquired knowledge is a hallmark of biological learning systems, which current deep learning systems fall short of. In this work, we present a novel methodology for continual learning called MERLIN: Meta-Consolidation for Continual Learning. We assume that weights of a neural network $\boldsymbol \psi$, for solving task $\boldsymbol t$, come from a meta-distribution $p(\boldsymbol{\psi|t})$. This meta-distribution is learned and consolidated incrementally. We operate in the challenging online continual learning setting, where a data point is seen by the model only once. Our experiments with continual learning benchmarks of MNIST, CIFAR-10, CIFAR-100 and Mini-ImageNet datasets show consistent improvement over five baselines, including a recent state-of-the-art, corroborating the promise of MERLIN.

Researchers at Texas A&M University have recently begun using artificial intelligence to forecast the growth of COVID-19 cases in communities across the country. The university is using a deep-learning model, a method of machine-learning that relies on large amounts of data, to process data related to population activities and mobility to help predict the spread of COVID-19 at a county level. Ali Mostafavi, the project's lead researcher, said this work could help lawmakers make informed policy decisions to protect residents and mitigate spread of the virus. "Significant opportunities exist using these big data and AI to contain the existing pandemic and also better prepare and mitigate the future pandemics," said Mostafavi, an associate professor of civil and environmental engineering. According to an announcement from the university last week, data fed into the model included the movement of people within communities, census data, social-distancing data, past case count growth and social demographics.

Tensors are the basic building blocks in PyTorch and put very simply, they are NumPy arrays but on GPU. In this part, I will list down some of the most used operations we can use while working with Tensors. This is by no means an exhaustive list of operations you can do with Tensors, but it is helpful to understand what tensors are before going towards the more exciting parts. We can create a PyTorch tensor in multiple ways. This includes converting to tensor from a NumPy array.