Paper Group ANR 478
The Mathematics of Changing one’s Mind, via Jeffrey’s or via Pearl’s update rule. Multi-Label Robust Factorization Autoencoder and its Application in Predicting Drug-Drug Interactions. SentRNA: Improving computational RNA design by incorporating a prior of human design strategies. Near Human-Level Performance in Grammatical Error Correction with Hy …
The Mathematics of Changing one’s Mind, via Jeffrey’s or via Pearl’s update rule
| Title | The Mathematics of Changing one’s Mind, via Jeffrey’s or via Pearl’s update rule |
| Authors | Bart Jacobs |
| Abstract | Evidence in probabilistic reasoning may be ‘hard’ or ‘soft’, that is, it may be of yes/no form, or it may involve a strength of belief, in the unit interval [0, 1]. Reasoning with soft, [0, 1]-valued evidence is important in many situations but may lead to different, confusing interpretations. This paper intends to bring more mathematical and conceptual clarity to the field by shifting the existing focus from specification of soft evidence to accomodation of soft evidence. There are two main approaches, known as Jeffrey’s rule and Pearl’s method; they give different outcomes on soft evidence. This paper argues that they can be understood as correction and as improvement. It describes these two approaches as different ways of updating with soft evidence, highlighting their differences, similarities and applications. This account is based on a novel channel-based approach to Bayesian probability. Proper understanding of these two update mechanisms is highly relevant for inference, decision tools and probabilistic programming languages. |
| Tasks | Probabilistic Programming |
| Published | 2018-07-15 |
| URL | https://arxiv.org/abs/1807.05609v3 |
| https://arxiv.org/pdf/1807.05609v3.pdf | |
| PWC | https://paperswithcode.com/paper/a-mathematical-account-of-soft-evidence-and |
| Repo | |
| Framework | |
Multi-Label Robust Factorization Autoencoder and its Application in Predicting Drug-Drug Interactions
| Title | Multi-Label Robust Factorization Autoencoder and its Application in Predicting Drug-Drug Interactions |
| Authors | Xu Chu, Yang Lin, Jingyue Gao, Jiangtao Wang, Yasha Wang, Leye Wang |
| Abstract | Drug-drug interactions (DDIs) are a major cause of preventable hospitalizations and deaths. Predicting the occurrence of DDIs helps drug safety professionals allocate investigative resources and take appropriate regulatory action promptly. Traditional DDI prediction methods predict DDIs based on the similarity between drugs. Recently, researchers revealed that predictive performance can be improved by better modeling the interactions between drug pairs with bilinear forms. However, the shallow models leveraging bilinear forms suffer from limitations on capturing complicated nonlinear interactions between drug pairs. To this end, we propose Multi-Label Robust Factorization Autoencoder (abbreviated to MuLFA) for DDI prediction, which learns a representation of interactions between drug pairs and has the capability of characterizing complicated nonlinear interactions more precisely. Moreover, a novel loss called CuXCov is designed to effectively learn the parameters of MuLFA. Furthermore, the decoder is able to generate high-risk chemical structures of drug pairs for specific DDIs, assisting pharmacists to better understand the relationship between drug chemistry and DDI. Experimental results on real-world datasets demonstrate that MuLFA consistently outperforms state-of-the-art methods; particularly, it increases 21:3% predictive performance compared to the best baseline for top 50 frequent DDIs.We also illustrate various case studies to demonstrate the efficacy of the chemical structures generated by MuLFA in DDI diagnosis. |
| Tasks | |
| Published | 2018-11-01 |
| URL | http://arxiv.org/abs/1811.00208v1 |
| http://arxiv.org/pdf/1811.00208v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-label-robust-factorization-autoencoder |
| Repo | |
| Framework | |
SentRNA: Improving computational RNA design by incorporating a prior of human design strategies
| Title | SentRNA: Improving computational RNA design by incorporating a prior of human design strategies |
| Authors | Jade Shi, Rhiju Das, Vijay S. Pande |
| Abstract | Solving the RNA inverse folding problem is a critical prerequisite to RNA design, an emerging field in bioengineering with a broad range of applications from reaction catalysis to cancer therapy. Although significant progress has been made in developing machine-based inverse RNA folding algorithms, current approaches still have difficulty designing sequences for large or complex targets. On the other hand, human players of the online RNA design game EteRNA have consistently shown superior performance in this regard, being able to readily design sequences for targets that are challenging for machine algorithms. Here we present a novel approach to the RNA design problem, SentRNA, a design agent consisting of a fully-connected neural network trained end-to-end using human-designed RNA sequences. We show that through this approach, SentRNA can solve complex targets previously unsolvable by any machine-based approach and achieve state-of-the-art performance on two separate challenging test sets. Our results demonstrate that incorporating human design strategies into a design algorithm can significantly boost machine performance and suggests a new paradigm for machine-based RNA design. |
| Tasks | |
| Published | 2018-03-08 |
| URL | http://arxiv.org/abs/1803.03146v2 |
| http://arxiv.org/pdf/1803.03146v2.pdf | |
| PWC | https://paperswithcode.com/paper/sentrna-improving-computational-rna-design-by |
| Repo | |
| Framework | |
Near Human-Level Performance in Grammatical Error Correction with Hybrid Machine Translation
| Title | Near Human-Level Performance in Grammatical Error Correction with Hybrid Machine Translation |
| Authors | Roman Grundkiewicz, Marcin Junczys-Dowmunt |
| Abstract | We combine two of the most popular approaches to automated Grammatical Error Correction (GEC): GEC based on Statistical Machine Translation (SMT) and GEC based on Neural Machine Translation (NMT). The hybrid system achieves new state-of-the-art results on the CoNLL-2014 and JFLEG benchmarks. This GEC system preserves the accuracy of SMT output and, at the same time, generates more fluent sentences as it typical for NMT. Our analysis shows that the created systems are closer to reaching human-level performance than any other GEC system reported so far. |
| Tasks | Grammatical Error Correction, Machine Translation |
| Published | 2018-04-16 |
| URL | http://arxiv.org/abs/1804.05945v1 |
| http://arxiv.org/pdf/1804.05945v1.pdf | |
| PWC | https://paperswithcode.com/paper/near-human-level-performance-in-grammatical |
| Repo | |
| Framework | |
Performance of Image Registration Tools on High-Resolution 3D Brain Images
| Title | Performance of Image Registration Tools on High-Resolution 3D Brain Images |
| Authors | Abdullah Nazib, James Galloway, Clinton Fookes, Dimitri Perrin |
| Abstract | Recent progress in tissue clearing has allowed for the imaging of entire organs at single-cell resolution. These methods produce very large 3D images (several gigabytes for a whole mouse brain). A necessary step in analysing these images is registration across samples. Existing methods of registration were developed for lower resolution image modalities (e.g. MRI) and it is unclear whether their performance and accuracy is satisfactory at this larger scale. In this study, we used data from different mouse brains cleared with the CUBIC protocol to evaluate five freely available image registration tools. We used several performance metrics to assess accuracy, and completion time as a measure of efficiency. The results of this evaluation suggest that the ANTS registration tool provides the best registration accuracy while Elastix has the highest computational efficiency among the methods with an acceptable accuracy. The results also highlight the need to develop new registration methods optimised for these high-resolution 3D images. |
| Tasks | Image Registration |
| Published | 2018-07-13 |
| URL | http://arxiv.org/abs/1807.04917v1 |
| http://arxiv.org/pdf/1807.04917v1.pdf | |
| PWC | https://paperswithcode.com/paper/performance-of-image-registration-tools-on |
| Repo | |
| Framework | |
Recurrent Stacking of Layers for Compact Neural Machine Translation Models
| Title | Recurrent Stacking of Layers for Compact Neural Machine Translation Models |
| Authors | Raj Dabre, Atsushi Fujita |
| Abstract | In neural machine translation (NMT), the most common practice is to stack a number of recurrent or feed-forward layers in the encoder and the decoder. As a result, the addition of each new layer improves the translation quality significantly. However, this also leads to a significant increase in the number of parameters. In this paper, we propose to share parameters across all the layers thereby leading to a recurrently stacked NMT model. We empirically show that the translation quality of a model that recurrently stacks a single layer 6 times is comparable to the translation quality of a model that stacks 6 separate layers. We also show that using pseudo-parallel corpora by back-translation leads to further significant improvements in translation quality. |
| Tasks | Machine Translation |
| Published | 2018-07-14 |
| URL | http://arxiv.org/abs/1807.05353v2 |
| http://arxiv.org/pdf/1807.05353v2.pdf | |
| PWC | https://paperswithcode.com/paper/recurrent-stacking-of-layers-for-compact |
| Repo | |
| Framework | |
Superimposition-guided Facial Reconstruction from Skull
| Title | Superimposition-guided Facial Reconstruction from Skull |
| Authors | Celong Liu, Xin Li |
| Abstract | We develop a new algorithm to perform facial reconstruction from a given skull. This technique has forensic application in helping the identification of skeletal remains when other information is unavailable. Unlike most existing strategies that directly reconstruct the face from the skull, we utilize a database of portrait photos to create many face candidates, then perform a superimposition to get a well matched face, and then revise it according to the superimposition. To support this pipeline, we build an effective autoencoder for image-based facial reconstruction, and a generative model for constrained face inpainting. Our experiments have demonstrated that the proposed pipeline is stable and accurate. |
| Tasks | Facial Inpainting |
| Published | 2018-09-28 |
| URL | http://arxiv.org/abs/1810.00107v1 |
| http://arxiv.org/pdf/1810.00107v1.pdf | |
| PWC | https://paperswithcode.com/paper/superimposition-guided-facial-reconstruction |
| Repo | |
| Framework | |
RSDNet: Learning to Predict Remaining Surgery Duration from Laparoscopic Videos Without Manual Annotations
| Title | RSDNet: Learning to Predict Remaining Surgery Duration from Laparoscopic Videos Without Manual Annotations |
| Authors | Andru Putra Twinanda, Gaurav Yengera, Didier Mutter, Jacques Marescaux, Nicolas Padoy |
| Abstract | Accurate surgery duration estimation is necessary for optimal OR planning, which plays an important role in patient comfort and safety as well as resource optimization. It is, however, challenging to preoperatively predict surgery duration since it varies significantly depending on the patient condition, surgeon skills, and intraoperative situation. In this paper, we propose a deep learning pipeline, referred to as RSDNet, which automatically estimates the remaining surgery duration (RSD) intraoperatively by using only visual information from laparoscopic videos. Previous state-of-the-art approaches for RSD prediction are dependent on manual annotation, whose generation requires expensive expert knowledge and is time-consuming, especially considering the numerous types of surgeries performed in a hospital and the large number of laparoscopic videos available. A crucial feature of RSDNet is that it does not depend on any manual annotation during training, making it easily scalable to many kinds of surgeries. The generalizability of our approach is demonstrated by testing the pipeline on two large datasets containing different types of surgeries: 120 cholecystectomy and 170 gastric bypass videos. The experimental results also show that the proposed network significantly outperforms a traditional method of estimating RSD without utilizing manual annotation. Further, this work provides a deeper insight into the deep learning network through visualization and interpretation of the features that are automatically learned. |
| Tasks | |
| Published | 2018-02-09 |
| URL | http://arxiv.org/abs/1802.03243v2 |
| http://arxiv.org/pdf/1802.03243v2.pdf | |
| PWC | https://paperswithcode.com/paper/rsdnet-learning-to-predict-remaining-surgery |
| Repo | |
| Framework | |
Fast and Efficient Information Transmission with Burst Spikes in Deep Spiking Neural Networks
| Title | Fast and Efficient Information Transmission with Burst Spikes in Deep Spiking Neural Networks |
| Authors | Seongsik Park, Seijoon Kim, Hyeokjun Choe, Sungroh Yoon |
| Abstract | The spiking neural networks (SNNs) are considered as one of the most promising artificial neural networks due to their energy efficient computing capability. Recently, conversion of a trained deep neural network to an SNN has improved the accuracy of deep SNNs. However, most of the previous studies have not achieved satisfactory results in terms of inference speed and energy efficiency. In this paper, we propose a fast and energy-efficient information transmission method with burst spikes and hybrid neural coding scheme in deep SNNs. Our experimental results showed the proposed methods can improve inference energy efficiency and shorten the latency. |
| Tasks | Image Classification |
| Published | 2018-09-10 |
| URL | http://arxiv.org/abs/1809.03142v2 |
| http://arxiv.org/pdf/1809.03142v2.pdf | |
| PWC | https://paperswithcode.com/paper/fast-and-efficient-information-transmission |
| Repo | |
| Framework | |
Actor-Expert: A Framework for using Q-learning in Continuous Action Spaces
| Title | Actor-Expert: A Framework for using Q-learning in Continuous Action Spaces |
| Authors | Sungsu Lim, Ajin Joseph, Lei Le, Yangchen Pan, Martha White |
| Abstract | Q-learning can be difficult to use in continuous action spaces, because an optimization has to be solved to find the maximal action for the action-values. A common strategy has been to restrict the functional form of the action-values to be concave in the actions, to simplify the optimization. Such restrictions, however, can prevent learning accurate action-values. In this work, we propose a new policy search objective that facilitates using Q-learning and a framework to optimize this objective, called Actor-Expert. The Expert uses Q-learning to update the action-values towards optimal action-values. The Actor learns the maximal actions over time for these changing action-values. We develop a Cross Entropy Method (CEM) for the Actor, where such a global optimization approach facilitates use of generically parameterized action-values. This method - which we call Conditional CEM - iteratively concentrates density around maximal actions, conditioned on state. We prove that this algorithm tracks the expected CEM update, over states with changing action-values. We demonstrate in a toy environment that previous methods that restrict the action-value parameterization fail whereas Actor-Expert with a more general action-value parameterization succeeds. Finally, we demonstrate that Actor-Expert performs as well as or better than competitors on four benchmark continuous-action environments. |
| Tasks | Q-Learning |
| Published | 2018-10-22 |
| URL | http://arxiv.org/abs/1810.09103v2 |
| http://arxiv.org/pdf/1810.09103v2.pdf | |
| PWC | https://paperswithcode.com/paper/actor-expert-a-framework-for-using-action |
| Repo | |
| Framework | |
Faster RER-CNN: application to the detection of vehicles in aerial images
| Title | Faster RER-CNN: application to the detection of vehicles in aerial images |
| Authors | Jean Ogier du Terrail, Frédéric Jurie |
| Abstract | Detecting small vehicles in aerial images is a difficult job that can be challenging even for humans. Rotating objects, low resolution, small inter-class variability and very large images comprising complicated backgrounds render the work of photo-interpreters tedious and wearisome. Unfortunately even the best classical detection pipelines like Faster R-CNN cannot be used off-the-shelf with good results because they were built to process object centric images from day-to-day life with multi-scale vertical objects. In this work we build on the Faster R-CNN approach to turn it into a detection framework that deals appropriately with the rotation equivariance inherent to any aerial image task. This new pipeline (Faster Rotation Equivariant Regions CNN) gives, without any bells and whistles, state-of-the-art results on one of the most challenging aerial imagery datasets: VeDAI and give good results w.r.t. the baseline Faster R-CNN on two others: Munich and GoogleEarth . |
| Tasks | |
| Published | 2018-09-20 |
| URL | http://arxiv.org/abs/1809.07628v1 |
| http://arxiv.org/pdf/1809.07628v1.pdf | |
| PWC | https://paperswithcode.com/paper/faster-rer-cnn-application-to-the-detection |
| Repo | |
| Framework | |
Generating High Quality Visible Images from SAR Images Using CNNs
| Title | Generating High Quality Visible Images from SAR Images Using CNNs |
| Authors | Puyang Wang, Vishal M. Patel |
| Abstract | We propose a novel approach for generating high quality visible-like images from Synthetic Aperture Radar (SAR) images using Deep Convolutional Generative Adversarial Network (GAN) architectures. The proposed approach is based on a cascaded network of convolutional neural nets (CNNs) for despeckling and image colorization. The cascaded structure results in faster convergence during training and produces high quality visible images from the corresponding SAR images. Experimental results on both simulated and real SAR images show that the proposed method can produce visible-like images better compared to the recent state-of-the-art deep learning-based methods. |
| Tasks | Colorization |
| Published | 2018-02-27 |
| URL | http://arxiv.org/abs/1802.10036v1 |
| http://arxiv.org/pdf/1802.10036v1.pdf | |
| PWC | https://paperswithcode.com/paper/generating-high-quality-visible-images-from |
| Repo | |
| Framework | |
Key Person Aided Re-identification in Partially Ordered Pedestrian Set
| Title | Key Person Aided Re-identification in Partially Ordered Pedestrian Set |
| Authors | Chen Chen, Min Cao, Xiyuan Hu, Silong Peng |
| Abstract | Ideally person re-identification seeks for perfect feature representation and metric model that re-identify all various pedestrians well in non-overlapping views at different locations with different camera configurations, which is very challenging. However, in most pedestrian sets, there always are some outstanding persons who are relatively easy to re-identify. Inspired by the existence of such data division, we propose a novel key person aided person re-identification framework based on the re-defined partially ordered pedestrian sets. The outstanding persons, namely “key persons”, are selected by the K-nearest neighbor based saliency measurement. The partial order defined by pedestrian entering time in surveillance associates the key persons with the query person temporally and helps to locate the possible candidates. Experiments conducted on two video datasets show that the proposed key person aided framework outperforms the state-of-the-art methods and improves the matching accuracy greatly at all ranks. |
| Tasks | Person Re-Identification |
| Published | 2018-05-25 |
| URL | http://arxiv.org/abs/1805.10017v1 |
| http://arxiv.org/pdf/1805.10017v1.pdf | |
| PWC | https://paperswithcode.com/paper/key-person-aided-re-identification-in |
| Repo | |
| Framework | |
The phase transition for the existence of the maximum likelihood estimate in high-dimensional logistic regression
| Title | The phase transition for the existence of the maximum likelihood estimate in high-dimensional logistic regression |
| Authors | Emmanuel J. Candes, Pragya Sur |
| Abstract | This paper rigorously establishes that the existence of the maximum likelihood estimate (MLE) in high-dimensional logistic regression models with Gaussian covariates undergoes a sharp `phase transition’. We introduce an explicit boundary curve $h_{\text{MLE}}$, parameterized by two scalars measuring the overall magnitude of the unknown sequence of regression coefficients, with the following property: in the limit of large sample sizes $n$ and number of features $p$ proportioned in such a way that $p/n \rightarrow \kappa$, we show that if the problem is sufficiently high dimensional in the sense that $\kappa > h_{\text{MLE}}$, then the MLE does not exist with probability one. Conversely, if $\kappa < h_{\text{MLE}}$, the MLE asymptotically exists with probability one. | |
| Tasks | |
| Published | 2018-04-25 |
| URL | http://arxiv.org/abs/1804.09753v1 |
| http://arxiv.org/pdf/1804.09753v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-phase-transition-for-the-existence-of-the |
| Repo | |
| Framework | |
Neural Relation Extraction Within and Across Sentence Boundaries
| Title | Neural Relation Extraction Within and Across Sentence Boundaries |
| Authors | Pankaj Gupta, Subburam Rajaram, Hinrich Schütze, Bernt Andrassy, Thomas Runkler |
| Abstract | Past work in relation extraction mostly focuses on binary relation between entity pairs within single sentence. Recently, the NLP community has gained interest in relation extraction in entity pairs spanning multiple sentences. In this paper, we propose a novel architecture for this task: inter-sentential dependency-based neural networks (iDepNN). iDepNN models the shortest and augmented dependency paths via recurrent and recursive neural networks to extract relationships within (intra-) and across (inter-) sentence boundaries. Compared to SVM and neural network baselines, iDepNN is more robust to false positives in relationships spanning sentences. We evaluate our models on four datasets from newswire (MUC6) and medical (BioNLP shared task) domains that achieve state-of-the-art performance and show a better balance in precision and recall for inter-sentential relationships. We perform better than 11 teams participating in the BioNLP shared task 2016 and achieve a gain of 5.2% (0.587 vs 0.558) in F1 over the winning team. We also release the crosssentence annotations for MUC6. |
| Tasks | Relation Extraction |
| Published | 2018-10-11 |
| URL | http://arxiv.org/abs/1810.05102v2 |
| http://arxiv.org/pdf/1810.05102v2.pdf | |
| PWC | https://paperswithcode.com/paper/neural-relation-extraction-within-and-across |
| Repo | |
| Framework | |
