Paper Group ANR 567
Algorithmic Aspects of Inverse Problems Using Generative Models. Numerical Aspects for Approximating Governing Equations Using Data. Unsupervised Learning for Surgical Motion by Learning to Predict the Future. ResumeNet: A Learning-based Framework for Automatic Resume Quality Assessment. Realtime Scheduling and Power Allocation Using Deep Neural Ne …
Algorithmic Aspects of Inverse Problems Using Generative Models
| Title | Algorithmic Aspects of Inverse Problems Using Generative Models |
| Authors | Chinmay Hegde |
| Abstract | The traditional approach of hand-crafting priors (such as sparsity) for solving inverse problems is slowly being replaced by the use of richer learned priors (such as those modeled by generative adversarial networks, or GANs). In this work, we study the algorithmic aspects of such a learning-based approach from a theoretical perspective. For certain generative network architectures, we establish a simple non-convex algorithmic approach that (a) theoretically enjoys linear convergence guarantees for certain inverse problems, and (b) empirically improves upon conventional techniques such as back-propagation. We also propose an extension of our approach that can handle model mismatch (i.e., situations where the generative network prior is not exactly applicable.) Together, our contributions serve as building blocks towards a more complete algorithmic understanding of generative models in inverse problems. |
| Tasks | |
| Published | 2018-10-08 |
| URL | http://arxiv.org/abs/1810.03587v1 |
| http://arxiv.org/pdf/1810.03587v1.pdf | |
| PWC | https://paperswithcode.com/paper/algorithmic-aspects-of-inverse-problems-using |
| Repo | |
| Framework | |
Numerical Aspects for Approximating Governing Equations Using Data
| Title | Numerical Aspects for Approximating Governing Equations Using Data |
| Authors | Kailiang Wu, Dongbin Xiu |
| Abstract | We present effective numerical algorithms for locally recovering unknown governing differential equations from measurement data. We employ a set of standard basis functions, e.g., polynomials, to approximate the governing equation with high accuracy. Upon recasting the problem into a function approximation problem, we discuss several important aspects for accurate approximation. Most notably, we discuss the importance of using a large number of short bursts of trajectory data, rather than using data from a single long trajectory. Several options for the numerical algorithms to perform accurate approximation are then presented, along with an error estimate of the final equation approximation. We then present an extensive set of numerical examples of both linear and nonlinear systems to demonstrate the properties and effectiveness of our equation recovery algorithms. |
| Tasks | |
| Published | 2018-09-24 |
| URL | http://arxiv.org/abs/1809.09170v1 |
| http://arxiv.org/pdf/1809.09170v1.pdf | |
| PWC | https://paperswithcode.com/paper/numerical-aspects-for-approximating-governing |
| Repo | |
| Framework | |
Unsupervised Learning for Surgical Motion by Learning to Predict the Future
| Title | Unsupervised Learning for Surgical Motion by Learning to Predict the Future |
| Authors | Robert DiPietro, Gregory D. Hager |
| Abstract | We show that it is possible to learn meaningful representations of surgical motion, without supervision, by learning to predict the future. An architecture that combines an RNN encoder-decoder and mixture density networks (MDNs) is developed to model the conditional distribution over future motion given past motion. We show that the learned encodings naturally cluster according to high-level activities, and we demonstrate the usefulness of these learned encodings in the context of information retrieval, where a database of surgical motion is searched for suturing activity using a motion-based query. Future prediction with MDNs is found to significantly outperform simpler baselines as well as the best previously-published result for this task, advancing state-of-the-art performance from an F1 score of 0.60 +- 0.14 to 0.77 +- 0.05. |
| Tasks | Future prediction, Information Retrieval |
| Published | 2018-06-08 |
| URL | http://arxiv.org/abs/1806.03318v1 |
| http://arxiv.org/pdf/1806.03318v1.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-learning-for-surgical-motion-by |
| Repo | |
| Framework | |
ResumeNet: A Learning-based Framework for Automatic Resume Quality Assessment
| Title | ResumeNet: A Learning-based Framework for Automatic Resume Quality Assessment |
| Authors | Yong Luo, Huaizheng Zhang, Yongjie Wang, Yonggang We, Xinwen Zhang |
| Abstract | Recruitment of appropriate people for certain positions is critical for any companies or organizations. Manually screening to select appropriate candidates from large amounts of resumes can be exhausted and time-consuming. However, there is no public tool that can be directly used for automatic resume quality assessment (RQA). This motivates us to develop a method for automatic RQA. Since there is also no public dataset for model training and evaluation, we build a dataset for RQA by collecting around 10K resumes, which are provided by a private resume management company. By investigating the dataset, we identify some factors or features that could be useful to discriminate good resumes from bad ones, e.g., the consistency between different parts of a resume. Then a neural-network model is designed to predict the quality of each resume, where some text processing techniques are incorporated. To deal with the label deficiency issue in the dataset, we propose several variants of the model by either utilizing the pair/triplet-based loss, or introducing some semi-supervised learning technique to make use of the abundant unlabeled data. Both the presented baseline model and its variants are general and easy to implement. Various popular criteria including the receiver operating characteristic (ROC) curve, F-measure and ranking-based average precision (AP) are adopted for model evaluation. We compare the different variants with our baseline model. Since there is no public algorithm for RQA, we further compare our results with those obtained from a website that can score a resume. Experimental results in terms of different criteria demonstrate the effectiveness of the proposed method. We foresee that our approach would transform the way of future human resources management. |
| Tasks | |
| Published | 2018-10-05 |
| URL | http://arxiv.org/abs/1810.02832v1 |
| http://arxiv.org/pdf/1810.02832v1.pdf | |
| PWC | https://paperswithcode.com/paper/resumenet-a-learning-based-framework-for |
| Repo | |
| Framework | |
Realtime Scheduling and Power Allocation Using Deep Neural Networks
| Title | Realtime Scheduling and Power Allocation Using Deep Neural Networks |
| Authors | Shenghe Xu, Pei Liu, Ran Wang, Shivendra S. Panwar |
| Abstract | With the increasing number of base stations (BSs) and network densification in 5G, interference management using link scheduling and power control are vital for better utilization of radio resources. However, the complexity of solving link scheduling and the power control problem grows exponentially with the number of BS. Due to high computation time, previous methods are useful for research purposes but impractical for real time usage. In this paper we propose to use deep neural networks (DNNs) to approximate optimal link scheduling and power control for the case with multiple small cells. A deep Q-network (DQN) estimates a suitable schedule, then a DNN allocates power for the corresponding schedule. Simulation results show that the proposed method achieves over five orders of magnitude speed-up with less than nine percent performance loss, making real time usage practical. |
| Tasks | |
| Published | 2018-11-18 |
| URL | http://arxiv.org/abs/1811.07416v1 |
| http://arxiv.org/pdf/1811.07416v1.pdf | |
| PWC | https://paperswithcode.com/paper/realtime-scheduling-and-power-allocation |
| Repo | |
| Framework | |
Deep Learning in Spiking Neural Networks
| Title | Deep Learning in Spiking Neural Networks |
| Authors | Amirhossein Tavanaei, Masoud Ghodrati, Saeed Reza Kheradpisheh, Timothee Masquelier, Anthony S. Maida |
| Abstract | In recent years, deep learning has been a revolution in the field of machine learning, for computer vision in particular. In this approach, a deep (multilayer) artificial neural network (ANN) is trained in a supervised manner using backpropagation. Huge amounts of labeled examples are required, but the resulting classification accuracy is truly impressive, sometimes outperforming humans. Neurons in an ANN are characterized by a single, static, continuous-valued activation. Yet biological neurons use discrete spikes to compute and transmit information, and the spike times, in addition to the spike rates, matter. Spiking neural networks (SNNs) are thus more biologically realistic than ANNs, and arguably the only viable option if one wants to understand how the brain computes. SNNs are also more hardware friendly and energy-efficient than ANNs, and are thus appealing for technology, especially for portable devices. However, training deep SNNs remains a challenge. Spiking neurons’ transfer function is usually non-differentiable, which prevents using backpropagation. Here we review recent supervised and unsupervised methods to train deep SNNs, and compare them in terms of accuracy, but also computational cost and hardware friendliness. The emerging picture is that SNNs still lag behind ANNs in terms of accuracy, but the gap is decreasing, and can even vanish on some tasks, while the SNNs typically require much fewer operations. |
| Tasks | |
| Published | 2018-04-22 |
| URL | http://arxiv.org/abs/1804.08150v4 |
| http://arxiv.org/pdf/1804.08150v4.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-in-spiking-neural-networks |
| Repo | |
| Framework | |
Understanding Recurrent Neural State Using Memory Signatures
| Title | Understanding Recurrent Neural State Using Memory Signatures |
| Authors | Skanda Koppula, Khe Chai Sim, Kean Chin |
| Abstract | We demonstrate a network visualization technique to analyze the recurrent state inside the LSTMs/GRUs used commonly in language and acoustic models. Interpreting intermediate state and network activations inside end-to-end models remains an open challenge. Our method allows users to understand exactly how much and what history is encoded inside recurrent state in grapheme sequence models. Our procedure trains multiple decoders that predict prior input history. Compiling results from these decoders, a user can obtain a signature of the recurrent kernel that characterizes its memory behavior. We demonstrate this method’s usefulness in revealing information divergence in the bases of recurrent factorized kernels, visualizing the character-level differences between the memory of n-gram and recurrent language models, and extracting knowledge of history encoded in the layers of grapheme-based end-to-end ASR networks. |
| Tasks | End-To-End Speech Recognition |
| Published | 2018-02-11 |
| URL | http://arxiv.org/abs/1802.03816v1 |
| http://arxiv.org/pdf/1802.03816v1.pdf | |
| PWC | https://paperswithcode.com/paper/understanding-recurrent-neural-state-using |
| Repo | |
| Framework | |
Modality Attention for End-to-End Audio-visual Speech Recognition
| Title | Modality Attention for End-to-End Audio-visual Speech Recognition |
| Authors | Pan Zhou, Wenwen Yang, Wei Chen, Yanfeng Wang, Jia Jia |
| Abstract | Audio-visual speech recognition (AVSR) system is thought to be one of the most promising solutions for robust speech recognition, especially in noisy environment. In this paper, we propose a novel multimodal attention based method for audio-visual speech recognition which could automatically learn the fused representation from both modalities based on their importance. Our method is realized using state-of-the-art sequence-to-sequence (Seq2seq) architectures. Experimental results show that relative improvements from 2% up to 36% over the auditory modality alone are obtained depending on the different signal-to-noise-ratio (SNR). Compared to the traditional feature concatenation methods, our proposed approach can achieve better recognition performance under both clean and noisy conditions. We believe modality attention based end-to-end method can be easily generalized to other multimodal tasks with correlated information. |
| Tasks | Audio-Visual Speech Recognition, Robust Speech Recognition, Speech Recognition, Visual Speech Recognition |
| Published | 2018-11-13 |
| URL | http://arxiv.org/abs/1811.05250v2 |
| http://arxiv.org/pdf/1811.05250v2.pdf | |
| PWC | https://paperswithcode.com/paper/modality-attention-for-end-to-end-audio |
| Repo | |
| Framework | |
Classification of Cervical Cancer Dataset
| Title | Classification of Cervical Cancer Dataset |
| Authors | Avishek Choudhury, Y. M. S Al Wesabi, Daehan Won |
| Abstract | Cervical cancer is the leading gynecological malignancy worldwide. This paper presents diverse classification techniques and shows the advantage of feature selection approaches to the best predicting of cervical cancer disease. There are thirty-two attributes with eight hundred and fifty-eight samples. Besides, this data suffers from missing values and imbalance data. Therefore, over-sampling, under-sampling and embedded over and under sampling have been used. Furthermore, dimensionality reduction techniques are required for improving the accuracy of the classifier. Therefore, feature selection methods have been studied as they divided into two distinct categories, filters and wrappers. The results show that age, first sexual intercourse, number of pregnancies, smokes, hormonal contraceptives, and STDs: genital herpes are the main predictive features with high accuracy with 97.5%. Decision Tree classifier is shown to be advantageous in handling classification assignment with excellent performance. |
| Tasks | Dimensionality Reduction, Feature Selection |
| Published | 2018-12-11 |
| URL | http://arxiv.org/abs/1812.10383v1 |
| http://arxiv.org/pdf/1812.10383v1.pdf | |
| PWC | https://paperswithcode.com/paper/classification-of-cervical-cancer-dataset |
| Repo | |
| Framework | |
Characterizing Transgender Health Issues in Twitter
| Title | Characterizing Transgender Health Issues in Twitter |
| Authors | Amir Karami, Frank Webb, Vanessa L. Kitzie |
| Abstract | Although there are millions of transgender people in the world, a lack of information exists about their health issues. This issue has consequences for the medical field, which only has a nascent understanding of how to identify and meet this population’s health-related needs. Social media sites like Twitter provide new opportunities for transgender people to overcome these barriers by sharing their personal health experiences. Our research employs a computational framework to collect tweets from self-identified transgender users, detect those that are health-related, and identify their information needs. This framework is significant because it provides a macro-scale perspective on an issue that lacks investigation at national or demographic levels. Our findings identified 54 distinct health-related topics that we grouped into 7 broader categories. Further, we found both linguistic and topical differences in the health-related information shared by transgender men (TM) as com-pared to transgender women (TW). These findings can help inform medical and policy-based strategies for health interventions within transgender communities. Also, our proposed approach can inform the development of computational strategies to identify the health-related information needs of other marginalized populations. |
| Tasks | |
| Published | 2018-08-18 |
| URL | http://arxiv.org/abs/1808.06022v2 |
| http://arxiv.org/pdf/1808.06022v2.pdf | |
| PWC | https://paperswithcode.com/paper/characterizing-transgender-health-issues-in |
| Repo | |
| Framework | |
Phase Collaborative Network for Two-Phase Medical Image Segmentation
| Title | Phase Collaborative Network for Two-Phase Medical Image Segmentation |
| Authors | Huangjie Zheng, Lingxi Xie, Tianwei Ni, Ya Zhang, Yan-Feng Wang, Qi Tian, Elliot K. Fishman, Alan L. Yuille |
| Abstract | In real-world practice, medical images acquired in different phases possess complementary information, {\em e.g.}, radiologists often refer to both arterial and venous scans in order to make the diagnosis. However, in medical image analysis, fusing prediction from two phases is often difficult, because (i) there is a domain gap between two phases, and (ii) the semantic labels are not pixel-wise corresponded even for images scanned from the same patient. This paper studies organ segmentation in two-phase CT scans. We propose Phase Collaborative Network (PCN), an end-to-end framework that contains both generative and discriminative modules. PCN can be mathematically explained to formulate phase-to-phase and data-to-label relations jointly. Experiments are performed on a two-phase CT dataset, on which PCN outperforms the baselines working with one-phase data by a large margin, and we empirically verify that the gain comes from inter-phase collaboration. Besides, PCN transfers well to two public single-phase datasets, demonstrating its potential applications. |
| Tasks | Medical Image Segmentation, Semantic Segmentation |
| Published | 2018-11-28 |
| URL | https://arxiv.org/abs/1811.11814v3 |
| https://arxiv.org/pdf/1811.11814v3.pdf | |
| PWC | https://paperswithcode.com/paper/phase-collaborative-network-for-multi-phase |
| Repo | |
| Framework | |
Metric Learning via Maximizing the Lipschitz Margin Ratio
| Title | Metric Learning via Maximizing the Lipschitz Margin Ratio |
| Authors | Mingzhi Dong, Xiaochen Yang, Yang Wu, Jing-Hao Xue |
| Abstract | In this paper, we propose the Lipschitz margin ratio and a new metric learning framework for classification through maximizing the ratio. This framework enables the integration of both the inter-class margin and the intra-class dispersion, as well as the enhancement of the generalization ability of a classifier. To introduce the Lipschitz margin ratio and its associated learning bound, we elaborate the relationship between metric learning and Lipschitz functions, as well as the representability and learnability of the Lipschitz functions. After proposing the new metric learning framework based on the introduced Lipschitz margin ratio, we also prove that some well known metric learning algorithms can be shown as special cases of the proposed framework. In addition, we illustrate the framework by implementing it for learning the squared Mahalanobis metric, and by demonstrating its encouraging results on eight popular datasets of machine learning. |
| Tasks | Metric Learning |
| Published | 2018-02-09 |
| URL | http://arxiv.org/abs/1802.03464v1 |
| http://arxiv.org/pdf/1802.03464v1.pdf | |
| PWC | https://paperswithcode.com/paper/metric-learning-via-maximizing-the-lipschitz |
| Repo | |
| Framework | |
Imitation Learning with Concurrent Actions in 3D Games
| Title | Imitation Learning with Concurrent Actions in 3D Games |
| Authors | Jack Harmer, Linus Gisslén, Jorge del Val, Henrik Holst, Joakim Bergdahl, Tom Olsson, Kristoffer Sjöö, Magnus Nordin |
| Abstract | In this work we describe a novel deep reinforcement learning architecture that allows multiple actions to be selected at every time-step in an efficient manner. Multi-action policies allow complex behaviours to be learnt that would otherwise be hard to achieve when using single action selection techniques. We use both imitation learning and temporal difference (TD) reinforcement learning (RL) to provide a 4x improvement in training time and 2.5x improvement in performance over single action selection TD RL. We demonstrate the capabilities of this network using a complex in-house 3D game. Mimicking the behavior of the expert teacher significantly improves world state exploration and allows the agents vision system to be trained more rapidly than TD RL alone. This initial training technique kick-starts TD learning and the agent quickly learns to surpass the capabilities of the expert. |
| Tasks | Imitation Learning |
| Published | 2018-03-14 |
| URL | http://arxiv.org/abs/1803.05402v5 |
| http://arxiv.org/pdf/1803.05402v5.pdf | |
| PWC | https://paperswithcode.com/paper/imitation-learning-with-concurrent-actions-in |
| Repo | |
| Framework | |
Knowledge Representation for High-Level Norms and Violation Inference in Logic Programming
| Title | Knowledge Representation for High-Level Norms and Violation Inference in Logic Programming |
| Authors | Babatunde Opeoluwa Akinkunmi, Moyin Florence Babalola |
| Abstract | Most of the knowledge Representation formalisms developed for representing prescriptive norms can be categorized as either suitable for representing either low level or high level norms.We argue that low level norm representations do not advance the cause of autonomy in agents in the sense that it is not the agent itself that determines the normative position it should be at a particular time, on the account of a more general rule. In other words an agent on some external system for a nitty gritty prescriptions of its obligations and prohibitions. On the other hand, high level norms which have an explicit description of a norm’s precondition and have some form of implication, do not as they exist in the literature do not support generalized inferences about violation like low level norm representations do. This paper presents a logical formalism for the representation of high level norms in open societies that enable violation inferences that detail the situation in which the norm violation took place and the identity of the norm violation. Norms are formalized as logic programs whose heads specify what an agent is obliged or permitted to do when a situation arises and within what time constraint of the situation.Each norm is also assigned an identity using some reification scheme. The body of each logic program describes the nature of the situation in which the agent is expected to act or desist from acting. This kind of violation is novel in the literature. |
| Tasks | |
| Published | 2018-01-20 |
| URL | http://arxiv.org/abs/1801.06740v1 |
| http://arxiv.org/pdf/1801.06740v1.pdf | |
| PWC | https://paperswithcode.com/paper/knowledge-representation-for-high-level-norms |
| Repo | |
| Framework | |
Densely Semantically Aligned Person Re-Identification
| Title | Densely Semantically Aligned Person Re-Identification |
| Authors | Zhizheng Zhang, Cuiling Lan, Wenjun Zeng, Zhibo Chen |
| Abstract | We propose a densely semantically aligned person re-identification framework. It fundamentally addresses the body misalignment problem caused by pose/viewpoint variations, imperfect person detection, occlusion, etc. By leveraging the estimation of the dense semantics of a person image, we construct a set of densely semantically aligned part images (DSAP-images), where the same spatial positions have the same semantics across different images. We design a two-stream network that consists of a main full image stream (MF-Stream) and a densely semantically-aligned guiding stream (DSAG-Stream). The DSAG-Stream, with the DSAP-images as input, acts as a regulator to guide the MF-Stream to learn densely semantically aligned features from the original image. In the inference, the DSAG-Stream is discarded and only the MF-Stream is needed, which makes the inference system computationally efficient and robust. To the best of our knowledge, we are the first to make use of fine grained semantics to address the misalignment problems for re-ID. Our method achieves rank-1 accuracy of 78.9% (new protocol) on the CUHK03 dataset, 90.4% on the CUHK01 dataset, and 95.7% on the Market1501 dataset, outperforming state-of-the-art methods. |
| Tasks | Human Detection, Person Re-Identification |
| Published | 2018-12-21 |
| URL | http://arxiv.org/abs/1812.08967v2 |
| http://arxiv.org/pdf/1812.08967v2.pdf | |
| PWC | https://paperswithcode.com/paper/densely-semantically-aligned-person-re |
| Repo | |
| Framework | |
