Inner product-based convolution has been a central component of convolutional neural networks (CNNs) and the key to learning visual representations. Inspired by the observation that CNN-learned features are naturally decoupled with the norm of features corresponding to the intra-class variation and the angle corresponding to the semantic difference, we propose a generic decoupled learning framework which models the intra-class variation and semantic difference independently. Specifically, we first reparametrize the inner product to a decoupled form and then generalize it to the decoupled convolution operator which serves as the building block of our decoupled networks. We present several effective instances of the decoupled convolution operator. Each decoupled operator is well motivated and has an intuitive geometric interpretation. Based on these decoupled operators, we further propose to directly learn the operator from data. Extensive experiments show that such decoupled reparameterization renders significant performance gain with easier convergence and stronger robustness.

Medication dosing in a critical care environment is a complex task that involves close monitoring of relevant physiologic and laboratory biomarkers and corresponding sequential adjustment of the prescribed dose. Misdosing of medications with narrow therapeutic windows (such as intravenous [IV] heparin) can result in preventable adverse events, decrease quality of care and increase cost. Therefore, a robust recommendation system can help clinicians by providing individualized dosing suggestions or corrections to existing protocols. We present a clinician-in-the-loop framework for adjusting IV heparin dose using deep reinforcement learning (RL). Our main objectives were to learn a new IV heparin dosing policy based on the multi-dimensional features of patients, and evaluate the effectiveness of the learned policy in the presence of other confounding factors that may contribute to heparin-related side effects. The data used in the experiments included 2598 intensive care patients from the publicly available MIMIC database and 2310 patients from the Emory University clinical data warehouse. Experimental results suggested that the distance from RL policy had a statistically significant association with anticoagulant complications (p < 0.05), after adjusting for the effects of confounding factors.

No abstract

Detoxification enzymes play significant roles in the interactions between insects and host plants, wherein detoxification-related genes make great contributions. As herbivorous pests, aphids reproduce rapidly due to parthenogenesis. They are good biological materials for studying the mechanisms that allow insect adaptation to host plants. Insect detoxification gene families are associated with insect adaptation to host plants. The Aphidinae is the largest subfamily in the Aphididae with at least 2483 species in 256 genera in 2 tribes: the Macrosiphini (with 3/4 of the species) and the Aphidini. Most aphid pests on crops and ornamental plants are Aphidinae. Members of the Aphidinae occur in nearly every region of the world. The body shape and colour vary significantly. To research the role that detoxification gene families played in the process of aphid adaptation to host evolution, we analyzed the phylogeny and evolution of these detoxification gene families in Aphidinae. In general, the P450/GST/CCE gene families contract, whereas the ABC/UGT families are conserved in Aphidinae species compared to these families in other herbivorous insects. Genus-specific expansions of P450 CYP4, and GST Delta have occurred in the genus Acyrthosiphon. In addition, the evolutionary rates of five detoxification gene families in the evolution process of Aphidinae are different. The comparison of five detoxification gene families among nine Aphidinae species and the estimated relative evolutionary rates provided herein support an understanding of the interaction between and the co-evolution of Aphidinae and plants.