Paper Group ANR 740
Structure Learning of Deep Networks via DNA Computing Algorithm. A Byte-sized Approach to Named Entity Recognition. Broadband Analog Aggregation for Low-Latency Federated Edge Learning (Extended Version). On Reinforcement Learning for Full-length Game of StarCraft. Application of Bounded Total Variation Denoising in Urban Traffic Analysis. Multiple …
Structure Learning of Deep Networks via DNA Computing Algorithm
| Title | Structure Learning of Deep Networks via DNA Computing Algorithm |
| Authors | Guoqiang Zhong, Tao Li, Wenxue Liu, Yang Chen |
| Abstract | Convolutional Neural Network (CNN) has gained state-of-the-art results in many pattern recognition and computer vision tasks. However, most of the CNN structures are manually designed by experienced researchers. Therefore, auto- matically building high performance networks becomes an important problem. In this paper, we introduce the idea of using DNA computing algorithm to automatically learn high-performance architectures. In DNA computing algorithm, we use short DNA strands to represent layers and long DNA strands to represent overall networks. We found that most of the learned models perform similarly, and only those performing worse during the first runs of training will perform worse finally than others. The indicates that: 1) Using DNA computing algorithm to learn deep architectures is feasible; 2) Local minima should not be a problem of deep networks; 3) We can use early stop to kill the models with the bad performance just after several runs of training. In our experiments, an accuracy 99.73% was obtained on the MNIST data set and an accuracy 95.10% was obtained on the CIFAR-10 data set. |
| Tasks | |
| Published | 2018-10-25 |
| URL | http://arxiv.org/abs/1810.10687v1 |
| http://arxiv.org/pdf/1810.10687v1.pdf | |
| PWC | https://paperswithcode.com/paper/structure-learning-of-deep-networks-via-dna |
| Repo | |
| Framework | |
A Byte-sized Approach to Named Entity Recognition
| Title | A Byte-sized Approach to Named Entity Recognition |
| Authors | Emily Sheng, Prem Natarajan |
| Abstract | In biomedical literature, it is common for entity boundaries to not align with word boundaries. Therefore, effective identification of entity spans requires approaches capable of considering tokens that are smaller than words. We introduce a novel, subword approach for named entity recognition (NER) that uses byte-pair encodings (BPE) in combination with convolutional and recurrent neural networks to produce byte-level tags of entities. We present experimental results on several standard biomedical datasets, namely the BioCreative VI Bio-ID, JNLPBA, and GENETAG datasets. We demonstrate competitive performance while bypassing the specialized domain expertise needed to create biomedical text tokenization rules. |
| Tasks | Named Entity Recognition, Tokenization |
| Published | 2018-09-22 |
| URL | http://arxiv.org/abs/1809.08386v1 |
| http://arxiv.org/pdf/1809.08386v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-byte-sized-approach-to-named-entity |
| Repo | |
| Framework | |
Broadband Analog Aggregation for Low-Latency Federated Edge Learning (Extended Version)
| Title | Broadband Analog Aggregation for Low-Latency Federated Edge Learning (Extended Version) |
| Authors | Guangxu Zhu, Yong Wang, Kaibin Huang |
| Abstract | The popularity of mobile devices results in the availability of enormous data and computational resources at the network edge. To leverage the data and resources, a new machine learning paradigm, called edge learning, has emerged where learning algorithms are deployed at the edge for providing fast and intelligent services to mobile users. While computing speeds are advancing rapidly, the communication latency is becoming the bottleneck of fast edge learning. To address this issue, this work is focused on designing a low latency multi-access scheme for edge learning. We consider a popular framework, federated edge learning (FEEL), where edge-server and on-device learning are synchronized to train a model without violating user-data privacy. It is proposed that model updates simultaneously transmitted by devices over broadband channels should be analog aggregated “over-the-air” by exploiting the superposition property of a multi-access channel. Thereby, “interference” is harnessed to provide fast implementation of the model aggregation. This results in dramatical latency reduction compared with the traditional orthogonal access (i.e., OFDMA). In this work, the performance of FEEL is characterized targeting a single-cell random network. First, due to power alignment between devices as required for aggregation, a fundamental tradeoff is shown to exist between the update-reliability and the expected update-truncation ratio. This motivates the design of an opportunistic scheduling scheme for FEEL that selects devices within a distance threshold. This scheme is shown using real datasets to yield satisfactory learning performance in the presence of high mobility. Second, both the multi-access latency of the proposed analog aggregation and the OFDMA scheme are analyzed. Their ratio, which quantifies the latency reduction of the former, is proved to scale almost linearly with device population. |
| Tasks | |
| Published | 2018-12-30 |
| URL | http://arxiv.org/abs/1812.11494v3 |
| http://arxiv.org/pdf/1812.11494v3.pdf | |
| PWC | https://paperswithcode.com/paper/broadband-analog-aggregation-for-low-latency |
| Repo | |
| Framework | |
On Reinforcement Learning for Full-length Game of StarCraft
| Title | On Reinforcement Learning for Full-length Game of StarCraft |
| Authors | Zhen-Jia Pang, Ruo-Ze Liu, Zhou-Yu Meng, Yi Zhang, Yang Yu, Tong Lu |
| Abstract | StarCraft II poses a grand challenge for reinforcement learning. The main difficulties of it include huge state and action space and a long-time horizon. In this paper, we investigate a hierarchical reinforcement learning approach for StarCraft II. The hierarchy involves two levels of abstraction. One is the macro-action automatically extracted from expert’s trajectories, which reduces the action space in an order of magnitude yet remains effective. The other is a two-layer hierarchical architecture which is modular and easy to scale, enabling a curriculum transferring from simpler tasks to more complex tasks. The reinforcement training algorithm for this architecture is also investigated. On a 64x64 map and using restrictive units, we achieve a winning rate of more than 99% against the difficulty level-1 built-in AI. Through the curriculum transfer learning algorithm and a mixture of combat model, we can achieve over 93% winning rate of Protoss against the most difficult non-cheating built-in AI (level-7) of Terran, training within two days using a single machine with only 48 CPU cores and 8 K40 GPUs. It also shows strong generalization performance, when tested against never seen opponents including cheating levels built-in AI and all levels of Zerg and Protoss built-in AI. We hope this study could shed some light on the future research of large-scale reinforcement learning. |
| Tasks | Hierarchical Reinforcement Learning, Starcraft, Starcraft II, Transfer Learning |
| Published | 2018-09-23 |
| URL | http://arxiv.org/abs/1809.09095v2 |
| http://arxiv.org/pdf/1809.09095v2.pdf | |
| PWC | https://paperswithcode.com/paper/on-reinforcement-learning-for-full-length |
| Repo | |
| Framework | |
Application of Bounded Total Variation Denoising in Urban Traffic Analysis
| Title | Application of Bounded Total Variation Denoising in Urban Traffic Analysis |
| Authors | Shanshan Tang, Haijun Yu |
| Abstract | While it is believed that denoising is not always necessary in many big data applications, we show in this paper that denoising is helpful in urban traffic analysis by applying the method of bounded total variation denoising to the urban road traffic prediction and clustering problem. We propose two easy-to-implement methods to estimate the noise strength parameter in the denoising algorithm, and apply the denoising algorithm to GPS-based traffic data from Beijing taxi system. For the traffic prediction problem, we combine neural network and history matching method for roads randomly chosen from an urban area of Beijing. Numerical experiments show that the predicting accuracy is improved significantly by applying the proposed bounded total variation denoising algorithm. We also test the algorithm on clustering problem, where a recently developed clustering analysis method is applied to more than one hundred urban road segments in Beijing based on their velocity profiles. Better clustering result is obtained after denoising. |
| Tasks | Denoising, Traffic Prediction |
| Published | 2018-08-04 |
| URL | http://arxiv.org/abs/1808.03258v2 |
| http://arxiv.org/pdf/1808.03258v2.pdf | |
| PWC | https://paperswithcode.com/paper/application-of-bounded-total-variation |
| Repo | |
| Framework | |
Multiple Description Convolutional Neural Networks for Image Compression
| Title | Multiple Description Convolutional Neural Networks for Image Compression |
| Authors | Lijun Zhao, Huihui Bai, Anhong Wang, Yao Zhao |
| Abstract | Multiple description coding (MDC) is able to stably transmit the signal in the un-reliable and non-prioritized networks, which has been broadly studied for several decades. However, the traditional MDC doesn’t well leverage image’s context features to generate multiple descriptions. In this paper, we propose a novel standard-compliant convolutional neural network-based MDC framework in term of image’s context features. Firstly, multiple description generator network (MDGN) is designed to produce appearance-similar yet feature-different multiple descriptions automatically according to image’s content, which are compressed by standard codec. Secondly, we present multiple description reconstruction network (MDRN) including side reconstruction network (SRN) and central reconstruction network (CRN). When any one of two lossy descriptions is received at the decoder, SRN network is used to improve the quality of this decoded lossy description by removing the compression artifact and up-sampling simultaneously. Meanwhile, we utilize CRN network with two decoded descriptions as inputs for better reconstruction, if both of lossy descriptions are available. Thirdly, multiple description virtual codec network (MDVCN) is proposed to bridge the gap between MDGN network and MDRN network in order to train an end-to-end MDC framework. Here, two learning algorithms are provided to train our whole framework. In addition to structural similarity loss function, the produced descriptions are used as opposing labels with multiple description distance loss function to regularize the training of MDGN network. These losses guarantee that the generated description images are structurally similar yet finely diverse. Experimental results show a great deal of objective and subjective quality measurements to validate the efficiency of the proposed method. |
| Tasks | Image Compression |
| Published | 2018-01-20 |
| URL | http://arxiv.org/abs/1801.06611v2 |
| http://arxiv.org/pdf/1801.06611v2.pdf | |
| PWC | https://paperswithcode.com/paper/multiple-description-convolutional-neural |
| Repo | |
| Framework | |
A Perceptual Prediction Framework for Self Supervised Event Segmentation
| Title | A Perceptual Prediction Framework for Self Supervised Event Segmentation |
| Authors | Sathyanarayanan N. Aakur, Sudeep Sarkar |
| Abstract | Temporal segmentation of long videos is an important problem, that has largely been tackled through supervised learning, often requiring large amounts of annotated training data. In this paper, we tackle the problem of self-supervised temporal segmentation of long videos that alleviate the need for any supervision. We introduce a self-supervised, predictive learning framework that draws inspiration from cognitive psychology to segment long, visually complex videos into individual, stable segments that share the same semantics. We also introduce a new adaptive learning paradigm that helps reduce the effect of catastrophic forgetting in recurrent neural networks. Extensive experiments on three publicly available datasets - Breakfast Actions, 50 Salads, and INRIA Instructional Videos datasets show the efficacy of the proposed approach. We show that the proposed approach is able to outperform weakly-supervised and other unsupervised learning approaches by up to 24% and have competitive performance compared to fully supervised approaches. We also show that the proposed approach is able to learn highly discriminative features that help improve action recognition when used in a representation learning paradigm. |
| Tasks | Action Localization, Representation Learning |
| Published | 2018-11-12 |
| URL | http://arxiv.org/abs/1811.04869v3 |
| http://arxiv.org/pdf/1811.04869v3.pdf | |
| PWC | https://paperswithcode.com/paper/a-perceptual-prediction-framework-for-self |
| Repo | |
| Framework | |
Spectral State Compression of Markov Processes
| Title | Spectral State Compression of Markov Processes |
| Authors | Anru Zhang, Mengdi Wang |
| Abstract | Model reduction of Markov processes is a basic problem in modeling state-transition systems. Motivated by the state aggregation approach rooted in control theory, we study the statistical state compression of a discrete-state Markov chain from empirical trajectories. Through the lens of spectral decomposition, we study the rank and features of Markov processes, as well as properties like representability, aggregability, and lumpability. We develop spectral methods for estimating the transition matrix of a low-rank Markov model, estimating the leading subspace spanned by Markov features, and recovering latent structures like state aggregation and lumpable partition of the state space. We prove statistical upper bounds for the estimation errors and nearly matching minimax lower bounds. Numerical studies are performed on synthetic data and a dataset of New York City taxi trips. |
| Tasks | |
| Published | 2018-02-08 |
| URL | https://arxiv.org/abs/1802.02920v3 |
| https://arxiv.org/pdf/1802.02920v3.pdf | |
| PWC | https://paperswithcode.com/paper/spectral-state-compression-of-markov |
| Repo | |
| Framework | |
The effects of negative adaptation in Model-Agnostic Meta-Learning
| Title | The effects of negative adaptation in Model-Agnostic Meta-Learning |
| Authors | Tristan Deleu, Yoshua Bengio |
| Abstract | The capacity of meta-learning algorithms to quickly adapt to a variety of tasks, including ones they did not experience during meta-training, has been a key factor in the recent success of these methods on few-shot learning problems. This particular advantage of using meta-learning over standard supervised or reinforcement learning is only well founded under the assumption that the adaptation phase does improve the performance of our model on the task of interest. However, in the classical framework of meta-learning, this constraint is only mildly enforced, if not at all, and we only see an improvement on average over a distribution of tasks. In this paper, we show that the adaptation in an algorithm like MAML can significantly decrease the performance of an agent in a meta-reinforcement learning setting, even on a range of meta-training tasks. |
| Tasks | Few-Shot Learning, Meta-Learning |
| Published | 2018-12-05 |
| URL | http://arxiv.org/abs/1812.02159v1 |
| http://arxiv.org/pdf/1812.02159v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-effects-of-negative-adaptation-in-model |
| Repo | |
| Framework | |
Fast Motion Deblurring for Feature Detection and Matching Using Inertial Measurements
| Title | Fast Motion Deblurring for Feature Detection and Matching Using Inertial Measurements |
| Authors | Janne Mustaniemi, Juho Kannala, Simo Särkkä, Jiri Matas, Janne Heikkilä |
| Abstract | Many computer vision and image processing applications rely on local features. It is well-known that motion blur decreases the performance of traditional feature detectors and descriptors. We propose an inertial-based deblurring method for improving the robustness of existing feature detectors and descriptors against the motion blur. Unlike most deblurring algorithms, the method can handle spatially-variant blur and rolling shutter distortion. Furthermore, it is capable of running in real-time contrary to state-of-the-art algorithms. The limitations of inertial-based blur estimation are taken into account by validating the blur estimates using image data. The evaluation shows that when the method is used with traditional feature detector and descriptor, it increases the number of detected keypoints, provides higher repeatability and improves the localization accuracy. We also demonstrate that such features will lead to more accurate and complete reconstructions when used in the application of 3D visual reconstruction. |
| Tasks | Deblurring |
| Published | 2018-05-22 |
| URL | http://arxiv.org/abs/1805.08542v1 |
| http://arxiv.org/pdf/1805.08542v1.pdf | |
| PWC | https://paperswithcode.com/paper/fast-motion-deblurring-for-feature-detection |
| Repo | |
| Framework | |
Too many secants: a hierarchical approach to secant-based dimensionality reduction on large data sets
| Title | Too many secants: a hierarchical approach to secant-based dimensionality reduction on large data sets |
| Authors | Henry Kvinge, Elin Farnell, Michael Kirby, Chris Peterson |
| Abstract | A fundamental question in many data analysis settings is the problem of discerning the “natural” dimension of a data set. That is, when a data set is drawn from a manifold (possibly with noise), a meaningful aspect of the data is the dimension of that manifold. Various approaches exist for estimating this dimension, such as the method of Secant-Avoidance Projection (SAP). Intuitively, the SAP algorithm seeks to determine a projection which best preserves the lengths of all secants between points in a data set; by applying the algorithm to find the best projections to vector spaces of various dimensions, one may infer the dimension of the manifold of origination. That is, one may learn the dimension at which it is possible to construct a diffeomorphic copy of the data in a lower-dimensional Euclidean space. Using Whitney’s embedding theorem, we can relate this information to the natural dimension of the data. A drawback of the SAP algorithm is that a data set with $T$ points has $O(T^2)$ secants, making the computation and storage of all secants infeasible for very large data sets. In this paper, we propose a novel algorithm that generalizes the SAP algorithm with an emphasis on addressing this issue. That is, we propose a hierarchical secant-based dimensionality-reduction method, which can be employed for data sets where explicitly calculating all secants is not feasible. |
| Tasks | Dimensionality Reduction |
| Published | 2018-08-05 |
| URL | http://arxiv.org/abs/1808.01686v1 |
| http://arxiv.org/pdf/1808.01686v1.pdf | |
| PWC | https://paperswithcode.com/paper/too-many-secants-a-hierarchical-approach-to |
| Repo | |
| Framework | |
Learning to Deblur Images with Exemplars
| Title | Learning to Deblur Images with Exemplars |
| Authors | Jinshan Pan, Wenqi Ren, Zhe Hu, Ming-Hsuan Yang |
| Abstract | Human faces are one interesting object class with numerous applications. While significant progress has been made in the generic deblurring problem, existing methods are less effective for blurry face images. The success of the state-of-the-art image deblurring algorithms stems mainly from implicit or explicit restoration of salient edges for kernel estimation. However, existing methods are less effective as only few edges can be restored from blurry face images for kernel estimation. In this paper, we address the problem of deblurring face images by exploiting facial structures. We propose a deblurring algorithm based on an exemplar dataset without using coarse-to-fine strategies or heuristic edge selections. In addition, we develop a convolutional neural network to restore sharp edges from blurry images for deblurring. Extensive experiments against the state-of-the-art methods demonstrate the effectiveness of the proposed algorithms for deblurring face images. In addition, we show the proposed algorithms can be applied to image deblurring for other object classes. |
| Tasks | Deblurring |
| Published | 2018-05-15 |
| URL | http://arxiv.org/abs/1805.05503v1 |
| http://arxiv.org/pdf/1805.05503v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-to-deblur-images-with-exemplars |
| Repo | |
| Framework | |
On the Computational Complexity of Model Checking for Dynamic Epistemic Logic with S5 Models
| Title | On the Computational Complexity of Model Checking for Dynamic Epistemic Logic with S5 Models |
| Authors | Ronald de Haan, Iris van de Pol |
| Abstract | Dynamic epistemic logic (DEL) is a logical framework for representing and reasoning about knowledge change for multiple agents. An important computational task in this framework is the model checking problem, which has been shown to be PSPACE-hard even for S5 models and two agents. We answer open questions in the literature about the complexity of this problem in more restricted settings. We provide a detailed complexity analysis of the model checking problem for DEL, where we consider various combinations of restrictions, such as the number of agents, whether the models are single-pointed or multi-pointed, and whether postconditions are allowed in the updates. In particular, we show that the problem is already PSPACE-hard in (1) the case of one agent, multi-pointed S5 models, and no postconditions, and (2) the case of two agents, only single-pointed S5 models, and no postconditions. In addition, we study the setting where only semi-private announcements are allowed as updates. We show that for this case the problem is already PSPACE-hard when restricted to two agents and three propositional variables. |
| Tasks | |
| Published | 2018-05-24 |
| URL | http://arxiv.org/abs/1805.09880v1 |
| http://arxiv.org/pdf/1805.09880v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-computational-complexity-of-model |
| Repo | |
| Framework | |
Skeletal Movement to Color Map: A Novel Representation for 3D Action Recognition with Inception Residual Networks
| Title | Skeletal Movement to Color Map: A Novel Representation for 3D Action Recognition with Inception Residual Networks |
| Authors | Huy Hieu Pham, Louahdi Khoudour, Alain Crouzil, Pablo Zegers, Sergio A. Velastin |
| Abstract | We propose a novel skeleton-based representation for 3D action recognition in videos using Deep Convolutional Neural Networks (D-CNNs). Two key issues have been addressed: First, how to construct a robust representation that easily captures the spatial-temporal evolutions of motions from skeleton sequences. Second, how to design D-CNNs capable of learning discriminative features from the new representation in a effective manner. To address these tasks, a skeletonbased representation, namely, SPMF (Skeleton Pose-Motion Feature) is proposed. The SPMFs are built from two of the most important properties of a human action: postures and their motions. Therefore, they are able to effectively represent complex actions. For learning and recognition tasks, we design and optimize new D-CNNs based on the idea of Inception Residual networks to predict actions from SPMFs. Our method is evaluated on two challenging datasets including MSR Action3D and NTU-RGB+D. Experimental results indicated that the proposed method surpasses state-of-the-art methods whilst requiring less computation. |
| Tasks | 3D Human Action Recognition, Action Recognition In Videos, Temporal Action Localization |
| Published | 2018-07-18 |
| URL | http://arxiv.org/abs/1807.07033v1 |
| http://arxiv.org/pdf/1807.07033v1.pdf | |
| PWC | https://paperswithcode.com/paper/skeletal-movement-to-color-map-a-novel |
| Repo | |
| Framework | |
A Scoring Method for Driving Safety Credit Using Trajectory Data
| Title | A Scoring Method for Driving Safety Credit Using Trajectory Data |
| Authors | Wenfu Wang, Weijie Yang, An Chen, Zhijie Pan |
| Abstract | Urban traffic systems worldwide are suffering from severe traffic safety problems. Traffic safety is affected by many complex factors, and heavily related to all drivers’ behaviors involved in traffic system. Drivers with aggressive driving behaviors increase the risk of traffic accidents. In order to manage the safety level of traffic system, we propose Driving Safety Credit inspired by credit score in financial security field, and design a scoring method using trajectory data and violation records. First, we extract driving habits, aggressive driving behaviors and traffic violation behaviors from driver’s trajectories and traffic violation records. Next, we train a classification model to filtered out irrelevant features. And at last, we score each driver with selected features. We verify our proposed scoring method using 40 days of traffic simulation, and proves the effectiveness of our scoring method. |
| Tasks | |
| Published | 2018-11-28 |
| URL | http://arxiv.org/abs/1811.12223v1 |
| http://arxiv.org/pdf/1811.12223v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-scoring-method-for-driving-safety-credit |
| Repo | |
| Framework | |
