Biomedical research papers use significantly different language and jargon when compared to typical English text, which reduces the utility of pre-trained NLP models in this domain. Meanwhile Medline, a database of biomedical abstracts, introduces nearly a million new documents per-year. Applications that could benefit from understanding this wealth of publicly available information, such as scientific writing assistants, chat-bots, or descriptive hypothesis generation systems, require new domain-centered approaches. A conditional language model, one that learns the probability of words given some a priori criteria, is a fundamental building block in many such applications. We propose a transformer-based conditional language model with a shallow encoder "condition" stack, and a deep "language model" stack of multi-headed attention blocks. The condition stack encodes metadata used to alter the output probability distribution of the language model stack. We sample this distribution in order to generate biomedical abstracts given only a proposed title, an intended publication year, and a set of keywords. Using typical natural language generation metrics, we demonstrate that this proposed approach is more capable of producing non-trivial relevant entities within the abstract body than the 1.5B parameter GPT-2 language model.

Graph convolutional networks (GCNs) are a widely used method for graph representation learning. We investigate the power of GCNs, as a function of their number of layers, to distinguish between different random graph models on the basis of the embeddings of their sample graphs. In particular, the graph models that we consider arise from graphons, which are the most general possible parameterizations of infinite exchangeable graph models and which are the central objects of study in the theory of dense graph limits. We exhibit an infinite class of graphons that are well-separated in terms of cut distance and are indistinguishable by a GCN with nonlinear activation functions coming from a certain broad class if its depth is at least logarithmic in the size of the sample graph. These results theoretically match empirical observations of several prior works. Finally, we show a converse result that for pairs of graphons satisfying a degree profile separation property, a very simple GCN architecture suffices for distinguishability. To prove our results, we exploit a connection to random walks on graphs.

This paper proposes a novel deep learning architecture for semantic segmentation. The proposed Global and Selective Attention Network (GSANet) features Atrous Spatial Pyramid Pooling (ASPP) with a novel sparsemax global attention and a novel selective attention that deploys a condensation and diffusion mechanism to aggregate the multi-scale contextual information from the extracted deep features. A selective attention decoder is also proposed to process the GSA-ASPP outputs for optimizing the softmax volume. We are the first to benchmark the performance of semantic segmentation networks with the low-complexity feature extraction network (FXN) MobileNetEdge, that is optimized for low latency on edge devices. We show that GSANet can result in more accurate segmentation with MobileNetEdge, as well as with strong FXNs, such as Xception. GSANet improves the state-of-art semantic segmentation accuracy on both the ADE20k and the Cityscapes datasets.

Medical images differ from natural images in significantly higher resolutions and smaller regions of interest. Because of these differences, neural network architectures that work well for natural images might not be applicable to medical image analysis. In this work, we extend the globally-aware multiple instance classifier, a framework we proposed to address these unique properties of medical images. This model first uses a low-capacity, yet memory-efficient, network on the whole image to identify the most informative regions. It then applies another higher-capacity network to collect details from chosen regions. Finally, it employs a fusion module that aggregates global and local information to make a final prediction. While existing methods often require lesion segmentation during training, our model is trained with only image-level labels and can generate pixel-level saliency maps indicating possible malignant findings. We apply the model to screening mammography interpretation: predicting the presence or absence of benign and malignant lesions. On the NYU Breast Cancer Screening Dataset, consisting of more than one million images, our model achieves an AUC of 0.93 in classifying breasts with malignant findings, outperforming ResNet-34 and Faster R-CNN. Compared to ResNet-34, our model is 4.1x faster for inference while using 78.4% less GPU memory. Furthermore, we demonstrate, in a reader study, that our model surpasses radiologist-level AUC by a margin of 0.11. The proposed model is available online: https://github.com/nyukat/GMIC.

With the rapid development of manufacturing industry, machine fault diagnosis has become increasingly significant to ensure safe equipment operation and production. Consequently, multifarious approaches have been explored and developed in the past years, of which intelligent algorithms develop particularly rapidly. Convolutional neural network, as a typical representative of intelligent diagnostic models, has been extensively studied and applied in recent five years, and a large amount of literature has been published in academic journals and conference proceedings. However, there has not been a systematic review to cover these studies and make a prospect for the further research. To fill in this gap, this work attempts to review and summarize the development of the Convolutional Network based Fault Diagnosis (CNFD) approaches comprehensively. Generally, a typical CNFD framework is composed of the following steps, namely, data collection, model construction, and feature learning and decision making, thus this paper is organized by following this stream. Firstly, data collection process is described, in which several popular datasets are introduced. Then, the fundamental theory from the basic convolutional neural network to its variants is elaborated. After that, the applications of CNFD are reviewed in terms of three mainstream directions, i.e. classification, prediction and transfer diagnosis. Finally, conclusions and prospects are presented to point out the characteristics of current development, facing challenges and future trends. Last but not least, it is expected that this work would provide convenience and inspire further exploration for researchers in this field.

Inspired by the recent advances in deep learning (DL), this work presents a deep neural network aided decoding algorithm for binary linear codes. Based on the concept of deep unfolding, we design a decoding network by unfolding the alternating direction method of multipliers (ADMM)-penalized decoder. In addition, we propose two improved versions of the proposed network. The first one transforms the penalty parameter into a set of iteration-dependent ones, and the second one adopts a specially designed penalty function, which is based on a piecewise linear function with adjustable slopes. Numerical results show that the resulting DL-aided decoders outperform the original ADMM-penalized decoder for various low density parity check (LDPC) codes with similar computational complexity.

Graph generation is an extremely important task, as graphs are found throughout different areas of science and engineering. In this work, we focus on the modern equivalent of the Erdos-Renyi random graph model: the graph variational autoencoder (GVAE). This model assumes edges and nodes are independent in order to generate entire graphs at a time using a multi-layer perceptron decoder. As a result of these assumptions, GVAE has difficulty matching the training distribution and relies on an expensive graph matching procedure. We improve this class of models by building a message passing neural network into GVAE's encoder and decoder. We demonstrate our model on the specific task of generating small organic molecules

The current methodology in tackling Acoustic Scene Classification (ASC) task can be described in two steps, preprocessing of the audio waveform into log-mel spectrogram and then using it as the input representation for Convolutional Neural Network (CNN). This paradigm shift occurs after DCASE 2016 where this framework model achieves the state-of-the-art result in ASC tasks on the (ESC-50) dataset and achieved an accuracy of 64.5%, which constitute to 20.5% improvement over the baseline model, and DCASE 2016 dataset with an accuracy of 90.0% (development) and 86.2% (evaluation), which constitute a 6.4% and 9% improvements with respect to the baseline system. In this paper, we explored the use of harmonic and percussive source separation (HPSS) to split the audio into harmonic audio and percussive audio, which has received popularity in the field of music information retrieval (MIR). Although works have been done in using HPSS as input representation for CNN model in ASC task, this paper further investigate the possibility on leveraging the separated harmonic component and percussive component by curating 2 CNNs which tries to understand harmonic audio and percussive audio in their natural form, one specialized in extracting deep features in time biased domain and another specialized in extracting deep features in frequency biased domain, respectively. The deep features extracted from these 2 CNNs will then be combined using bilinear pooling. Hence, presenting a two-stream time and frequency CNN architecture approach in classifying acoustic scene. The model is being evaluated on DCASE 2019 sub task 1a dataset and scored an average of 65% on development dataset, Kaggle Leadership Private and Public board.

For multi-valued functions---such as when the conditional distribution on targets given the inputs is multi-modal---standard regression approaches are not always desirable because they provide the conditional mean. Modal regression aims to instead find the conditional mode, but is restricted to nonparametric approaches. Such methods can be difficult to scale, and cannot benefit from parametric function approximation, like neural networks, which can learn complex relationships between inputs and targets. In this work, we propose a parametric modal regression algorithm, by using the implicit function theorem to develop an objective for learning a joint parameterized function over inputs and targets. We empirically demonstrate on several synthetic problems that our method (i) can learn multi-valued functions and produce the conditional modes, (ii) scales well to high-dimensional inputs and (iii) is even more effective for certain uni-modal problems, particularly for high frequency data where the joint function over inputs and targets can better capture the complex relationship between them. We then demonstrate that our method is practically useful in a real-world modal regression problem. We conclude by showing that our method provides small improvements on two regression datasets that have asymmetric distributions over the targets.

Large-scale distributed training of deep neural networks results in models with worse generalization performance as a result of the increase in the effective mini-batch size. Previous approaches attempt to address this problem by varying the learning rate and batch size over epochs and layers, or ad hoc modifications of batch normalization. We propose Scalable and Practical Natural Gradient Descent (SP-NGD), a principled approach for training models that allows them to attain similar generalization performance to models trained with first-order optimization methods, but with accelerated convergence. Furthermore, SP-NGD scales to large mini-batch sizes with a negligible computational overhead as compared to first-order methods. We evaluated SP-NGD on a benchmark task where highly optimized first-order methods are available as references: training a ResNet-50 model for image classification on ImageNet. We demonstrate convergence to a top-1 validation accuracy of 75.4% in 5.5 minutes using a mini-batch size of 32,768 with 1,024 GPUs, as well as an accuracy of 74.9% with an extremely large mini-batch size of 131,072 in 873 steps of SP-NGD.