Quantitative predictive modelling approaches to understanding rheumatoid arthritis: A brief review. (arXiv:1911.09035v1 [q-bio.QM])

Rheumatoid arthritis is a chronic autoimmune disease that is a major public health challenge. The disease is characterised by inflammation of synovial joints and cartilage erosion, which leads to chronic pain, poor life quality and, in some cases, premature mortality. Understanding the biological mechanisms behind the progression of the disease, as well as developing new…

A CNN-RNN Framework for Crop Yield Prediction. (arXiv:1911.09045v1 [cs.LG])

Crop yield prediction is extremely challenging due to its dependence on multiple factors such as crop genotype, environmental factors, management practices, and their interactions. This paper presents a deep learning framework using convolutional neural networks (CNN) and recurrent neural networks (RNN) for crop yield prediction based on environmental data and management practices. The proposed CNN-RNN…

Exploring the Origins and Prevalence of Texture Bias in Convolutional Neural Networks. (arXiv:1911.09071v1 [cs.CV])

Recent work has indicated that, unlike humans, ImageNet-trained CNNs tend to classify images by texture rather than shape. How pervasive is this bias, and where does it come from? We find that, when trained on datasets of images with conflicting shape and texture, the inductive bias of CNNs often favors shape; in general, models learn…

Heterogeneous Deep Graph Infomax. (arXiv:1911.08538v1 [cs.LG])

Graph representation learning is to learn universal node representations that preserve both node attributes and structural information. The derived node representations can be used to serve various downstream tasks, such as node classification and node clustering. When a graph is heterogeneous, the problem becomes more challenging than the homogeneous graph node learning problem. Inspired by…

Deep Motion Blur Removal Using Noisy/Blurry Image Pairs. (arXiv:1911.08541v1 [cs.CV])

Removing spatially variant motion blur from a blurry image is a challenging problem as blur sources are complicated and difficult to model accurately. Recent progress in deep neural networks suggests that kernel free single image deblurring can be efficiently performed, but questions about deblurring performance persist. Thus, we propose to restore a sharp image by…

Learning to Control Latent Representations for Few-Shot Learning of Named Entities. (arXiv:1911.08542v1 [cs.AI])

Humans excel in continuously learning with small data without forgetting how to solve old problems. However, neural networks require large datasets to compute latent representations across different tasks while minimizing a loss function. For example, a natural language understanding (NLU) system will often deal with emerging entities during its deployment as interactions with users in…

Cross-Class Relevance Learning for Temporal Concept Localization. (arXiv:1911.08548v1 [cs.CV])

We present a novel Cross-Class Relevance Learning approach for the task of temporal concept localization. Most localization architectures rely on feature extraction layers followed by a classification layer which outputs class probabilities for each segment. However, in many real-world applications classes can exhibit complex relationships that are difficult to model with this architecture. In contrast,…

Prediction Focused Topic Models for Electronic Health Records. (arXiv:1911.08551v1 [cs.LG])

Electronic Health Record (EHR) data can be represented as discrete counts over a high dimensional set of possible procedures, diagnoses, and medications. Supervised topic models present an attractive option for incorporating EHR data as features into a prediction problem: given a patient’s record, we estimate a set of latent factors that are predictive of the…

Synthetic Controls with Imperfect Pre-Treatment Fit. (arXiv:1911.08521v1 [econ.EM])

We analyze the properties of the Synthetic Control (SC) and related estimators when the pre-treatment fit is imperfect. In this framework, we show that these estimators are generally biased if treatment assignment is correlated with unobserved confounders, even when the number of pre-treatment periods goes to infinity. Still, we also show that a modified version…