In its on-going campaign to reveal the inner workings of the Sar-CoV-2 virus, the U.S. Department of Energy's (DOE) Argonne National Laboratory is leading efforts to couple artificial intelligence (AI) and cutting-edge simulation workflows to better understand biological observations and accelerate drug discovery. Argonne collaborated with academic and commercial research partners to achieve near real-time feedback between simulation and AI approaches to understand how two proteins in the SARS-CoV-2 viral genome, nsp10 and nsp16, interact to help the virus replicate and elude the host's immune system. The team achieved this milestone by coupling two distinct hardware platforms: Cerebras CS-1, a processor-packed silicon wafer deep learning accelerator; and ThetaGPU, an AI- and simulation-enabled extension of the Theta supercomputer, housed at the Argonne Leadership Computing Facility, a DOE Office of Science User Facility. To enable this capability, the team developed Stream-AI-MD, a novel application of the AI method called deep learning to drive adaptive molecular dynamics (MD) simulations in a streaming manner. Data from simulations is streamed from ThetaGPU onto the Cerebras CS-1 platform to simultaneously analyze how the two proteins interact.

Convolutional neural networks (CNNs) have recently achieved remarkable performance in positron emission tomography (PET) image reconstruction. In particular, CNN-based direct PET image reconstruction, which directly generates the reconstructed image from the sinogram, has potential applicability to PET image enhancements because it does not require image reconstruction algorithms, which often produce some artifacts. However, these deep learning-based, direct PET image reconstruction algorithms have the disadvantage that they require a large number of high-quality training datasets. In this study, we propose an unsupervised direct PET image reconstruction method that incorporates a deep image prior framework. Our proposed method incorporates a forward projection model with a loss function to achieve unsupervised direct PET image reconstruction from sinograms. To compare our proposed direct reconstruction method with the filtered back projection (FBP) and maximum likelihood expectation maximization (ML-EM) algorithms, we evaluated using Monte Carlo simulation data of brain [$^{18}$F]FDG PET scans. The results demonstrate that our proposed direct reconstruction quantitatively and qualitatively outperforms the FBP and ML-EM algorithms with respect to peak signal-to-noise ratio and structural similarity index.

Image super-resolution is important in many fields, such as surveillance and remote sensing. However, infrared (IR) images normally have low resolution since the optical equipment is relatively expensive. Recently, deep learning methods have dominated image super-resolution and achieved remarkable performance on visible images; however, IR images have received less attention. IR images have fewer patterns, and hence, it is difficult for deep neural networks (DNNs) to learn diverse features from IR images. In this paper, we present a framework that employs heterogeneous convolution and adversarial training, namely, heterogeneous kernel-based super-resolution Wasserstein GAN (HetSRW-GAN), for IR image super-resolution. The HetSRWGAN algorithm is a lightweight GAN architecture that applies a plug-and-play heterogeneous kernel-based residual block. Moreover, a novel loss function that employs image gradients is adopted, which can be applied to an arbitrary model. The proposed HetSRWGAN achieves consistently better performance in both qualitative and quantitative evaluations. According to the experimental results, the whole training process is more stable.

Transformers changed modern NLP in many ways. However, they can hardly exploit domain knowledge, and like other blackbox models, they lack interpretability. Unfortunately, structured knowledge injection, in the long run, risks to suffer from a knowledge acquisition bottleneck. We thus propose a memory enhancement of transformer models that makes use of unstructured domain knowledge expressed in plain natural language. An experimental evaluation conducted on two challenging NLP tasks demonstrates that our approach yields better performance and model interpretability than baseline transformer-based architectures.

Graph Neural Networks (GNNs) are currently a hot topic in artificial intelligence, with a huge amount of applications in many domains, ranging from bioinformatics to computer vision, from social network analysis to natural language processing [1]. First introduced in [2], and then far and wide extended with a large number of variants, GNNs can learn embedding representations of generic graphs, by exploiting aggregation functions based on propagation and pooling layers. These building blocks are frequently stacked into a deep network, and the resulting embeddings can be exploited in any high-level task. This kind of architecture has rapidly become the state-of-the-art, or at least a strong competitor, in many application domains dealing with structured data. Historically, in natural language processing (NLP) as well as in other domains, Tree Kernels (TKs) have long been one of the most widely employed technique to handle structured data in the form of trees [3]. A TK is basically a similarity function that captures the degree of similarity of two trees by looking at common fragments within their substructures.

Dry eye disease (DED) has a prevalence of between 5 and 50\%, depending on the diagnostic criteria used and population under study. However, it remains one of the most underdiagnosed and undertreated conditions in ophthalmology. Many tests used in the diagnosis of DED rely on an experienced observer for image interpretation, which may be considered subjective and result in variation in diagnosis. Since artificial intelligence (AI) systems are capable of advanced problem solving, use of such techniques could lead to more objective diagnosis. Although the term `AI' is commonly used, recent success in its applications to medicine is mainly due to advancements in the sub-field of machine learning, which has been used to automatically classify images and predict medical outcomes. Powerful machine learning techniques have been harnessed to understand nuances in patient data and medical images, aiming for consistent diagnosis and stratification of disease severity. This is the first literature review on the use of AI in DED. We provide a brief introduction to AI, report its current use in DED research and its potential for application in the clinic. Our review found that AI has been employed in a wide range of DED clinical tests and research applications, primarily for interpretation of interferometry, slit-lamp and meibography images. While initial results are promising, much work is still needed on model development, clinical testing and standardisation.

Semantic information provides intra-class consistency and inter-class discriminability beyond visual concepts, which has been employed in Few-Shot Learning (FSL) to achieve further gains. However, semantic information is only available for labeled samples but absent for unlabeled samples, in which the embeddings are rectified unilaterally by guiding the few labeled samples with semantics. Therefore, it is inevitable to bring a cross-modal bias between semantic-guided samples and nonsemantic-guided samples, which results in an information asymmetry problem. To address this problem, we propose a Modal-Alternating Propagation Network (MAP-Net) to supplement the absent semantic information of unlabeled samples, which builds information symmetry among all samples in both visual and semantic modalities. Specifically, the MAP-Net transfers the neighbor information by the graph propagation to generate the pseudo-semantics for unlabeled samples guided by the completed visual relationships and rectify the feature embeddings. In addition, due to the large discrepancy between visual and semantic modalities, we design a Relation Guidance (RG) strategy to guide the visual relation vectors via semantics so that the propagated information is more beneficial. Extensive experimental results on three semantic-labeled datasets, i.e., Caltech-UCSD-Birds 200-2011, SUN Attribute Database, and Oxford 102 Flower, have demonstrated that our proposed method achieves promising performance and outperforms the state-of-the-art approaches, which indicates the necessity of information symmetry.

The following defines intent, an arbitrary task and its solutions, and then argues that an agent which always constructs what is called an Intensional Solution would qualify as artificial general intelligence. We then explain how natural language may emerge and be acquired by such an agent, conferring the ability to model the intent of other individuals labouring under similar compulsions, because an abstract symbol system and the solution to a task are one and the same.

Target-oriented opinion words extraction (TOWE) (Fan et al., 2019b) is a new subtask of target-oriented sentiment analysis that aims to extract opinion words for a given aspect in text. Current state-of-the-art methods leverage position embeddings to capture the relative position of a word to the target. However, the performance of these methods depends on the ability to incorporate this information into word representations. In this paper, we explore a variety of text encoders based on pretrained word embeddings or language models that leverage part-of-speech and position embeddings, aiming to examine the actual contribution of each component in TOWE. We also adapt a graph convolutional network (GCN) to enhance word representations by incorporating syntactic information. Our experimental results demonstrate that BiLSTM-based models can effectively encode position information into word representations while using a GCN only achieves marginal gains. Interestingly, our simple methods outperform several state-of-the-art complex neural structures.

More predictable words are easier to process - they are read faster and elicit smaller neural signals associated with processing difficulty, most notably, the N400 component of the event-related brain potential. Thus, it has been argued that prediction of upcoming words is a key component of language comprehension, and that studying the amplitude of the N400 is a valuable way to investigate the predictions that we make. In this study, we investigate whether the linguistic predictions of computational language models or humans better reflect the way in which natural language stimuli modulate the amplitude of the N400. One important difference in the linguistic predictions of humans versus computational language models is that while language models base their predictions exclusively on the preceding linguistic context, humans may rely on other factors. We find that the predictions of three top-of-the-line contemporary language models - GPT-3, RoBERTa, and ALBERT - match the N400 more closely than human predictions. This suggests that the predictive processes underlying the N400 may be more sensitive to the surface-level statistics of language than previously thought.