Electronic Health Records (EHRs) provide vital contextual information to radiologists and other physicians when making a diagnosis. Unfortunately, because a given patient's record may contain hundreds of notes and reports, identifying relevant information within these in the short time typically allotted to a case is very difficult. We propose and evaluate models that extract relevant text snippets from patient records to provide a rough case summary intended to aid physicians considering one or more diagnoses. This is hard because direct supervision (i.e., physician annotations of snippets relevant to specific diagnoses in medical records) is prohibitively expensive to collect at scale. We propose a distantly supervised strategy in which we use groups of International Classification of Diseases (ICD) codes observed in 'future' records as noisy proxies for 'downstream' diagnoses. Using this we train a transformer-based neural model to perform extractive summarization conditioned on potential diagnoses. This model defines an attention mechanism that is conditioned on potential diagnoses (queries) provided by the diagnosing physician. We train (via distant supervision) and evaluate variants of this model on EHR data from a local hospital and MIMIC-III (the latter to facilitate reproducibility). Evaluations performed by radiologists demonstrate that these distantly supervised models yield better extractive summaries than do unsupervised approaches. Such models may aid diagnosis by identifying sentences in past patient reports that are clinically relevant to a potential diagnoses.

Graph Convolution Networks (GCN) are widely used in learning graph representations due to their effectiveness and efficiency. However, they suffer from the notorious over-smoothing problem, in which the learned representations of densely connected nodes converge to alike vectors when many (>3) graph convolutional layers are stacked. In this paper, we argue that there-normalization trick used in GCN leads to overly homogeneous information propagation, which is the source of over-smoothing. To address this problem, we propose Graph Highway Networks(GHNet) which utilize gating units to automatically balance the trade-off between homogeneity and heterogeneity in the GCN learning process. The gating units serve as direct highways to maintain heterogeneous information from the node itself after feature propagation. This design enables GHNet to achieve much larger receptive fields per node without over-smoothing and thus access to more of the graph connectivity information. Experimental results on benchmark datasets demonstrate the superior performance of GHNet over GCN and related models.

Deep learning algorithms can be seen as compositions of functions acting on learned representations encoded as tensor-structured data. However, in most applications those representations are monolithic, with for instance one single vector encoding an entire image or sentence. In this paper, we build upon the recent successes of Graph Neural Networks (GNNs) to explore the use of graph-structured representations for learning spatial configurations. Motivated by the ability of humans to distinguish arrangements of shapes, we introduce two novel geometrical reasoning tasks, for which we provide the datasets. We introduce novel GNN layers and architectures to solve the tasks and show that graph-structured representations are necessary for good performance.

The challenge of speeding up deep learning models during the deployment phase has been a large, expensive bottleneck in the modern tech industry. In this paper, we examine the use of both regularization and pruning for reduced computational complexity and more efficient inference in Deep Neural Networks (DNNs). In particular, we apply mixup and cutout regularizations and soft filter pruning to the ResNet architecture, focusing on minimizing floating-point operations (FLOPs). Furthermore, by using regularization in conjunction with network pruning, we show that such a combination makes a substantial improvement over each of the two techniques individually.

When DeepMind, the artificial intelligence company owned by Google parent Alphabet Inc., released its predictions about some of the building blocks of the virus that causes Covid-19 in early March, it gave medical researchers a small but potentially important clue that could help them develop a vaccine and treatments for the respiratory illness. The company's deep learning system, AlphaFold, which predicts the shapes of proteins when no similar structures are available, is just one example of the powerful role AI is playing in the fight against the novel coronavirus. The innovations that DeepMind and others are rapidly rolling out could be complicated by AI laws to be unveiled by the European Union this year. Even as the coronavirus upends business, economic, and legislative plans the world over, the EU is pushing ahead with its AI policy proposal, which would make it a global leader in regulating the sector. The European Commission, the bloc's executive body, released its plan in February, calling for public feedback by the end of May.

Throughout history, epidemics and chronic diseases have claimed the lives of many people and caused major crises that have taken a long time to overcome. The 2019 novel coronavirus (COVID-19) pandemic appeared in Wuhan, China in December 2019 and has become a serious public health problem worldwide. It is an acute resolved disease, but it can also be deadly, with a 2% case fatality rate. The early and automatic diagnosis of Covid-19 may be beneficial for timely referral of the patient to quarantine, and monitoring of the spread of the disease. Some tests requiring significant time to produce results (days), and a projected up to 30% false positive rate, other timely approaches to diagnosis are worthy of investigation.

Machine learning and in particular deep learning revolutionize the world as we know it today. We have seen tremendous advances in speech and image recognition, followed by the application of deep learning to many other domains. In many of those domains, deep learning is now the state of the art or is even going beyond it. A clear trend is that networks are growing more and more complex and more and more computationally demanding. Today, we are building ever-increasing networks that are built on top of previous generations of network topologies.

Every week, Invector Labs publishes a newsletter that covers the most recent developments in AI research and technology. You can find this week's issue below. You can sign up for it below. Games are often seen as a great benchmark to evaluate the ability of artificial intelligence(AI) algorithms to generalize knowledge. From the different data environments that we can create, games come the closest to resemble real world environments.

Artificial Intelligence (AI) represents a drastic change in the technological evolution. At the moment, this technology is used in every field of science. We have seen the use of AI in various arenas such as autonomous vehicles, face recognition and robotics, among others. Similarly, it is also embedded in the medical field in areas such as disease prediction using representational images, i.e. prediction of breast cancer using CNN (Convolutional Neural Networks) in a deep learning model. But currently, we are moving a step forward into the future in order to find the risk of premature death in individuals with underlying chronic diseases.

The ability to learn in dynamic, nonstationary environments without forgetting previous knowledge, also known as Continual Learning (CL), is a key enabler for scalable and trustworthy deployments of adaptive solutions. While the importance of continual learning is largely acknowledged in machine vision and reinforcement learning problems, this is mostly under-documented for sequence processing tasks. This work proposes a Recurrent Neural Network (RNN) model for CL that is able to deal with concept drift in input distribution without forgetting previously acquired knowledge. We also implement and test a popular CL approach, Elastic Weight Consolidation (EWC), on top of two different types of RNNs. Finally, we compare the performances of our enhanced architecture against EWC and RNNs on a set of standard CL benchmarks, adapted to the sequential data processing scenario. Results show the superior performance of our architecture and highlight the need for special solutions designed to address CL in RNNs.