Paper Group ANR 950
Deep Diabetologist: Learning to Prescribe Hyperglycemia Medications with Hierarchical Recurrent Neural Networks. Error Detection in a Large-Scale Lexical Taxonomy. Cleaning up the neighborhood: A full classification for adversarial partial monitoring. The Dynamics of Learning: A Random Matrix Approach. User-Guided Deep Anime Line Art Colorization w …
Deep Diabetologist: Learning to Prescribe Hyperglycemia Medications with Hierarchical Recurrent Neural Networks
| Title | Deep Diabetologist: Learning to Prescribe Hyperglycemia Medications with Hierarchical Recurrent Neural Networks |
| Authors | Jing Mei, Shiwan Zhao, Feng Jin, Eryu Xia, Haifeng Liu, Xiang Li |
| Abstract | In healthcare, applying deep learning models to electronic health records (EHRs) has drawn considerable attention. EHR data consist of a sequence of medical visits, i.e. a multivariate time series of diagnosis, medications, physical examinations, lab tests, etc. This sequential nature makes EHR well matching the power of Recurrent Neural Network (RNN). In this paper, we propose “Deep Diabetologist” - using RNNs for EHR sequential data modelling, to provide the personalized hyperglycemia medication prediction for diabetic patients. Particularly, we develop a hierarchical RNN to capture the heterogeneous sequential information in the EHR data. Our experimental results demonstrate the improved performance, compared with a baseline classifier using logistic regression. Moreover, hierarchical RNN models outperform basic ones, providing deeper data insights for clinical decision support. |
| Tasks | Time Series |
| Published | 2018-10-17 |
| URL | http://arxiv.org/abs/1810.07692v1 |
| http://arxiv.org/pdf/1810.07692v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-diabetologist-learning-to-prescribe |
| Repo | |
| Framework | |
Error Detection in a Large-Scale Lexical Taxonomy
| Title | Error Detection in a Large-Scale Lexical Taxonomy |
| Authors | Sifan Liu, Hongzhi Wang |
| Abstract | Knowledge base (KB) is an important aspect in artificial intelligence. One significant challenge faced by KB construction is that it contains many noises, which prevents its effective usage. Even though some KB cleansing algorithms have been proposed, they focus on the structure of the knowledge graph and neglect the relation between the concepts, which could be helpful to discover wrong relations in KB. Motived by this, we measure the relation of two concepts by the distance between their corresponding instances and detect errors within the intersection of the conflicting concept sets. For efficient and effective knowledge base cleansing, we first apply a distance-based Model to determine the conflicting concept sets using two different methods. Then, we propose and analyze several algorithms on how to detect and repairing the errors based on our model, where we use hash method for an efficient way to calculate distance. Experimental results demonstrate that the proposed approaches could cleanse the knowledge bases efficiently and effectively. |
| Tasks | |
| Published | 2018-08-05 |
| URL | http://arxiv.org/abs/1808.01690v1 |
| http://arxiv.org/pdf/1808.01690v1.pdf | |
| PWC | https://paperswithcode.com/paper/error-detection-in-a-large-scale-lexical |
| Repo | |
| Framework | |
Cleaning up the neighborhood: A full classification for adversarial partial monitoring
| Title | Cleaning up the neighborhood: A full classification for adversarial partial monitoring |
| Authors | Tor Lattimore, Csaba Szepesvari |
| Abstract | Partial monitoring is a generalization of the well-known multi-armed bandit framework where the loss is not directly observed by the learner. We complete the classification of finite adversarial partial monitoring to include all games, solving an open problem posed by Bartok et al. [2014]. Along the way we simplify and improve existing algorithms and correct errors in previous analyses. Our second contribution is a new algorithm for the class of games studied by Bartok [2013] where we prove upper and lower regret bounds that shed more light on the dependence of the regret on the game structure. |
| Tasks | |
| Published | 2018-05-23 |
| URL | http://arxiv.org/abs/1805.09247v1 |
| http://arxiv.org/pdf/1805.09247v1.pdf | |
| PWC | https://paperswithcode.com/paper/cleaning-up-the-neighborhood-a-full |
| Repo | |
| Framework | |
The Dynamics of Learning: A Random Matrix Approach
| Title | The Dynamics of Learning: A Random Matrix Approach |
| Authors | Zhenyu Liao, Romain Couillet |
| Abstract | Understanding the learning dynamics of neural networks is one of the key issues for the improvement of optimization algorithms as well as for the theoretical comprehension of why deep neural nets work so well today. In this paper, we introduce a random matrix-based framework to analyze the learning dynamics of a single-layer linear network on a binary classification problem, for data of simultaneously large dimension and size, trained by gradient descent. Our results provide rich insights into common questions in neural nets, such as overfitting, early stopping and the initialization of training, thereby opening the door for future studies of more elaborate structures and models appearing in today’s neural networks. |
| Tasks | |
| Published | 2018-05-30 |
| URL | http://arxiv.org/abs/1805.11917v2 |
| http://arxiv.org/pdf/1805.11917v2.pdf | |
| PWC | https://paperswithcode.com/paper/the-dynamics-of-learning-a-random-matrix |
| Repo | |
| Framework | |
User-Guided Deep Anime Line Art Colorization with Conditional Adversarial Networks
| Title | User-Guided Deep Anime Line Art Colorization with Conditional Adversarial Networks |
| Authors | Yuanzheng Ci, Xinzhu Ma, Zhihui Wang, Haojie Li, Zhongxuan Luo |
| Abstract | Scribble colors based line art colorization is a challenging computer vision problem since neither greyscale values nor semantic information is presented in line arts, and the lack of authentic illustration-line art training pairs also increases difficulty of model generalization. Recently, several Generative Adversarial Nets (GANs) based methods have achieved great success. They can generate colorized illustrations conditioned on given line art and color hints. However, these methods fail to capture the authentic illustration distributions and are hence perceptually unsatisfying in the sense that they often lack accurate shading. To address these challenges, we propose a novel deep conditional adversarial architecture for scribble based anime line art colorization. Specifically, we integrate the conditional framework with WGAN-GP criteria as well as the perceptual loss to enable us to robustly train a deep network that makes the synthesized images more natural and real. We also introduce a local features network that is independent of synthetic data. With GANs conditioned on features from such network, we notably increase the generalization capability over “in the wild” line arts. Furthermore, we collect two datasets that provide high-quality colorful illustrations and authentic line arts for training and benchmarking. With the proposed model trained on our illustration dataset, we demonstrate that images synthesized by the presented approach are considerably more realistic and precise than alternative approaches. |
| Tasks | Colorization, Line Art Colorization |
| Published | 2018-08-09 |
| URL | http://arxiv.org/abs/1808.03240v2 |
| http://arxiv.org/pdf/1808.03240v2.pdf | |
| PWC | https://paperswithcode.com/paper/user-guided-deep-anime-line-art-colorization |
| Repo | |
| Framework | |
Linear and Nonlinear Identification of Dryer System Using Artificial Intelligence and Neural Networks
| Title | Linear and Nonlinear Identification of Dryer System Using Artificial Intelligence and Neural Networks |
| Authors | Mostafa Darvishi |
| Abstract | As you read these words you are using a complex biological neural network. You have a highly interconnected set of some neurons to facilitate your reading, breathing, motion and thinking. Each of your biological neurons, a rich assembly of tissue and chemistry, has the complexity, if not the speed, of a microprocessor. Some of your neural structure was with you at birth. Other parts have been established by experience. |
| Tasks | |
| Published | 2018-11-16 |
| URL | http://arxiv.org/abs/1811.11534v2 |
| http://arxiv.org/pdf/1811.11534v2.pdf | |
| PWC | https://paperswithcode.com/paper/linear-and-nonlinear-identification-of-dryer |
| Repo | |
| Framework | |
Machine Learning for semi linear PDEs
| Title | Machine Learning for semi linear PDEs |
| Authors | Quentin Chan-Wai-Nam, Joseph Mikael, Xavier Warin |
| Abstract | Recent machine learning algorithms dedicated to solving semi-linear PDEs are improved by using different neural network architectures and different parameterizations. These algorithms are compared to a new one that solves a fixed point problem by using deep learning techniques. This new algorithm appears to be competitive in terms of accuracy with the best existing algorithms. |
| Tasks | |
| Published | 2018-09-20 |
| URL | http://arxiv.org/abs/1809.07609v2 |
| http://arxiv.org/pdf/1809.07609v2.pdf | |
| PWC | https://paperswithcode.com/paper/machine-learning-for-semi-linear-pdes |
| Repo | |
| Framework | |
Quantum Neural Network and Soft Quantum Computing
| Title | Quantum Neural Network and Soft Quantum Computing |
| Authors | Zeng-Bing Chen |
| Abstract | A new paradigm of quantum computing, namely, soft quantum computing, is proposed for nonclassical computation using real world quantum systems with naturally occurring environment-induced decoherence and dissipation. As a specific example of soft quantum computing, we suggest a quantum neural network, where the neurons connect pairwise via the “controlled Kraus operations”, hoping to pave an easier and more realistic way to quantum artificial intelligence and even to better understanding certain functioning of the human brain. Our quantum neuron model mimics as much as possible the realistic neurons and meanwhile, uses quantum laws for processing information. The quantum features of the noisy neural network are uncovered by the presence of quantum discord and by non-commutability of quantum operations. We believe that our model puts quantum computing into a wider context and inspires the hope to build a soft quantum computer much earlier than the standard one. |
| Tasks | |
| Published | 2018-10-10 |
| URL | http://arxiv.org/abs/1810.05025v1 |
| http://arxiv.org/pdf/1810.05025v1.pdf | |
| PWC | https://paperswithcode.com/paper/quantum-neural-network-and-soft-quantum |
| Repo | |
| Framework | |
Learning to Globally Edit Images with Textual Description
| Title | Learning to Globally Edit Images with Textual Description |
| Authors | Hai Wang, Jason D. Williams, SingBing Kang |
| Abstract | We show how we can globally edit images using textual instructions: given a source image and a textual instruction for the edit, generate a new image transformed under this instruction. To tackle this novel problem, we develop three different trainable models based on RNN and Generative Adversarial Network (GAN). The models (bucket, filter bank, and end-to-end) differ in how much expert knowledge is encoded, with the most general version being purely end-to-end. To train these systems, we use Amazon Mechanical Turk to collect textual descriptions for around 2000 image pairs sampled from several datasets. Experimental results evaluated on our dataset validate our approaches. In addition, given that the filter bank model is a good compromise between generality and performance, we investigate it further by replacing RNN with Graph RNN, and show that Graph RNN improves performance. To the best of our knowledge, this is the first computational photography work on global image editing that is purely based on free-form textual instructions. |
| Tasks | |
| Published | 2018-10-13 |
| URL | http://arxiv.org/abs/1810.05786v1 |
| http://arxiv.org/pdf/1810.05786v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-to-globally-edit-images-with-textual |
| Repo | |
| Framework | |
Global Pose Estimation with an Attention-based Recurrent Network
| Title | Global Pose Estimation with an Attention-based Recurrent Network |
| Authors | Emilio Parisotto, Devendra Singh Chaplot, Jian Zhang, Ruslan Salakhutdinov |
| Abstract | The ability for an agent to localize itself within an environment is crucial for many real-world applications. For unknown environments, Simultaneous Localization and Mapping (SLAM) enables incremental and concurrent building of and localizing within a map. We present a new, differentiable architecture, Neural Graph Optimizer, progressing towards a complete neural network solution for SLAM by designing a system composed of a local pose estimation model, a novel pose selection module, and a novel graph optimization process. The entire architecture is trained in an end-to-end fashion, enabling the network to automatically learn domain-specific features relevant to the visual odometry and avoid the involved process of feature engineering. We demonstrate the effectiveness of our system on a simulated 2D maze and the 3D ViZ-Doom environment. |
| Tasks | Feature Engineering, Pose Estimation, Simultaneous Localization and Mapping, Visual Odometry |
| Published | 2018-02-19 |
| URL | http://arxiv.org/abs/1802.06857v1 |
| http://arxiv.org/pdf/1802.06857v1.pdf | |
| PWC | https://paperswithcode.com/paper/global-pose-estimation-with-an-attention |
| Repo | |
| Framework | |
Evaluating Gammatone Frequency Cepstral Coefficients with Neural Networks for Emotion Recognition from Speech
| Title | Evaluating Gammatone Frequency Cepstral Coefficients with Neural Networks for Emotion Recognition from Speech |
| Authors | Gabrielle K. Liu |
| Abstract | Current approaches to speech emotion recognition focus on speech features that can capture the emotional content of a speech signal. Mel Frequency Cepstral Coefficients (MFCCs) are one of the most commonly used representations for audio speech recognition and classification. This paper proposes Gammatone Frequency Cepstral Coefficients (GFCCs) as a potentially better representation of speech signals for emotion recognition. The effectiveness of MFCC and GFCC representations are compared and evaluated over emotion and intensity classification tasks with fully connected and recurrent neural network architectures. The results provide evidence that GFCCs outperform MFCCs in speech emotion recognition. |
| Tasks | Emotion Recognition, Speech Emotion Recognition, Speech Recognition |
| Published | 2018-06-23 |
| URL | http://arxiv.org/abs/1806.09010v1 |
| http://arxiv.org/pdf/1806.09010v1.pdf | |
| PWC | https://paperswithcode.com/paper/evaluating-gammatone-frequency-cepstral |
| Repo | |
| Framework | |
Perfect match: Improved cross-modal embeddings for audio-visual synchronisation
| Title | Perfect match: Improved cross-modal embeddings for audio-visual synchronisation |
| Authors | Soo-Whan Chung, Joon Son Chung, Hong-Goo Kang |
| Abstract | This paper proposes a new strategy for learning powerful cross-modal embeddings for audio-to-video synchronization. Here, we set up the problem as one of cross-modal retrieval, where the objective is to find the most relevant audio segment given a short video clip. The method builds on the recent advances in learning representations from cross-modal self-supervision. The main contributions of this paper are as follows: (1) we propose a new learning strategy where the embeddings are learnt via a multi-way matching problem, as opposed to a binary classification (matching or non-matching) problem as proposed by recent papers; (2) we demonstrate that performance of this method far exceeds the existing baselines on the synchronization task; (3) we use the learnt embeddings for visual speech recognition in self-supervision, and show that the performance matches the representations learnt end-to-end in a fully-supervised manner. |
| Tasks | Cross-Modal Retrieval, Speech Recognition, Video Synchronization, Visual Speech Recognition |
| Published | 2018-09-21 |
| URL | http://arxiv.org/abs/1809.08001v2 |
| http://arxiv.org/pdf/1809.08001v2.pdf | |
| PWC | https://paperswithcode.com/paper/perfect-match-improved-cross-modal-embeddings |
| Repo | |
| Framework | |
Improving Explorability in Variational Inference with Annealed Variational Objectives
| Title | Improving Explorability in Variational Inference with Annealed Variational Objectives |
| Authors | Chin-Wei Huang, Shawn Tan, Alexandre Lacoste, Aaron Courville |
| Abstract | Despite the advances in the representational capacity of approximate distributions for variational inference, the optimization process can still limit the density that is ultimately learned. We demonstrate the drawbacks of biasing the true posterior to be unimodal, and introduce Annealed Variational Objectives (AVO) into the training of hierarchical variational methods. Inspired by Annealed Importance Sampling, the proposed method facilitates learning by incorporating energy tempering into the optimization objective. In our experiments, we demonstrate our method’s robustness to deterministic warm up, and the benefits of encouraging exploration in the latent space. |
| Tasks | |
| Published | 2018-09-06 |
| URL | http://arxiv.org/abs/1809.01818v3 |
| http://arxiv.org/pdf/1809.01818v3.pdf | |
| PWC | https://paperswithcode.com/paper/improving-explorability-in-variational |
| Repo | |
| Framework | |
Object Sorting Using a Global Texture-Shape 3D Feature Descriptor
| Title | Object Sorting Using a Global Texture-Shape 3D Feature Descriptor |
| Authors | Zhun Fan, Zhongxing Li, Benzhang Qiu, Wenji Li, Jianye Hu, Alex Noel Josephraj, Heping Chen |
| Abstract | Object recognition and grasping plays a key role in robotic systems, especially for the autonomous robots to implement object sorting tasks in a warehouse. In this paper, we present a global texture-shape 3D feature descriptor which can be utilized in a system of object recognition and grasping, and can perform object sorting tasks well. Our proposed descriptor stems from the clustered viewpoint feature histogram (CVFH), which relies on the geometrical information of the whole 3D object surface only, and can not perform well in recognizing the objects with similar geometrical information. Therefore, we extend the CVFH descriptor with texture and color information to generate a new global 3D feature descriptor. The proposed descriptor is evaluated in tasks of recognizing and classifying 3D objects by applying multi-class support vector machines (SVM) in both public 3D image dataset and real scenes. The results of evaluation show that the proposed descriptor achieves a significant better performance for object recognition compared with the original CVFH. Then, the proposed descriptor is applied in our object recognition and grasping system, showing that the proposed descriptor helps the system implement the object recognition, object grasping and object sorting tasks well. |
| Tasks | Object Detection, Object Recognition |
| Published | 2018-02-04 |
| URL | https://arxiv.org/abs/1802.01116v3 |
| https://arxiv.org/pdf/1802.01116v3.pdf | |
| PWC | https://paperswithcode.com/paper/object-detection-and-sorting-by-using-a |
| Repo | |
| Framework | |
FrameNet automatic analysis : a study on a French corpus of encyclopedic texts
| Title | FrameNet automatic analysis : a study on a French corpus of encyclopedic texts |
| Authors | Gabriel Marzinotto, Géraldine Damnati, Frederic Bechet |
| Abstract | This article presents an automatic frame analysis system evaluated on a corpus of French encyclopedic history texts annotated according to the FrameNet formalism. The chosen approach relies on an integrated sequence labeling model which jointly optimizes frame identification and semantic role segmentation and identification. The purpose of this study is to analyze the task complexity from several dimensions. Hence we provide detailed evaluations from a feature selection point of view and from the data point of view. |
| Tasks | Feature Selection |
| Published | 2018-12-19 |
| URL | http://arxiv.org/abs/1812.08044v1 |
| http://arxiv.org/pdf/1812.08044v1.pdf | |
| PWC | https://paperswithcode.com/paper/framenet-automatic-analysis-a-study-on-a |
| Repo | |
| Framework | |
