Paper Group ANR 409
Deep Recurrent Neural Networks for seizure detection and early seizure detection systems. Calligraphic Stylisation Learning with a Physiologically Plausible Model of Movement and Recurrent Neural Networks. Weighted Low-rank Tensor Recovery for Hyperspectral Image Restoration. Deep scattering transform applied to note onset detection and instrument …
Deep Recurrent Neural Networks for seizure detection and early seizure detection systems
| Title | Deep Recurrent Neural Networks for seizure detection and early seizure detection systems |
| Authors | Sachin S. Talathi |
| Abstract | Epilepsy is common neurological diseases, affecting about 0.6-0.8 % of world population. Epileptic patients suffer from chronic unprovoked seizures, which can result in broad spectrum of debilitating medical and social consequences. Since seizures, in general, occur infrequently and are unpredictable, automated seizure detection systems are recommended to screen for seizures during long-term electroencephalogram (EEG) recordings. In addition, systems for early seizure detection can lead to the development of new types of intervention systems that are designed to control or shorten the duration of seizure events. In this article, we investigate the utility of recurrent neural networks (RNNs) in designing seizure detection and early seizure detection systems. We propose a deep learning framework via the use of Gated Recurrent Unit (GRU) RNNs for seizure detection. We use publicly available data in order to evaluate our method and demonstrate very promising evaluation results with overall accuracy close to 100 %. We also systematically investigate the application of our method for early seizure warning systems. Our method can detect about 98% of seizure events within the first 5 seconds of the overall epileptic seizure duration. |
| Tasks | EEG, Seizure Detection |
| Published | 2017-06-10 |
| URL | http://arxiv.org/abs/1706.03283v1 |
| http://arxiv.org/pdf/1706.03283v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-recurrent-neural-networks-for-seizure |
| Repo | |
| Framework | |
Calligraphic Stylisation Learning with a Physiologically Plausible Model of Movement and Recurrent Neural Networks
| Title | Calligraphic Stylisation Learning with a Physiologically Plausible Model of Movement and Recurrent Neural Networks |
| Authors | Daniel Berio, Memo Akten, Frederic Fol Leymarie, Mick Grierson, Réjean Plamondon |
| Abstract | We propose a computational framework to learn stylisation patterns from example drawings or writings, and then generate new trajectories that possess similar stylistic qualities. We particularly focus on the generation and stylisation of trajectories that are similar to the ones that can be seen in calligraphy and graffiti art. Our system is able to extract and learn dynamic and visual qualities from a small number of user defined examples which can be recorded with a digitiser device, such as a tablet, mouse or motion capture sensors. Our system is then able to transform new user drawn traces to be kinematically and stylistically similar to the training examples. We implement the system using a Recurrent Mixture Density Network (RMDN) combined with a representation given by the parameters of the Sigma Lognormal model, a physiologically plausible model of movement that has been shown to closely reproduce the velocity and trace of human handwriting gestures. |
| Tasks | Motion Capture |
| Published | 2017-09-24 |
| URL | http://arxiv.org/abs/1710.01214v1 |
| http://arxiv.org/pdf/1710.01214v1.pdf | |
| PWC | https://paperswithcode.com/paper/calligraphic-stylisation-learning-with-a |
| Repo | |
| Framework | |
Weighted Low-rank Tensor Recovery for Hyperspectral Image Restoration
| Title | Weighted Low-rank Tensor Recovery for Hyperspectral Image Restoration |
| Authors | Yi Chang, Luxin Yan, Houzhang Fang, Sheng Zhong, Zhijun Zhang |
| Abstract | Hyperspectral imaging, providing abundant spatial and spectral information simultaneously, has attracted a lot of interest in recent years. Unfortunately, due to the hardware limitations, the hyperspectral image (HSI) is vulnerable to various degradations, such noises (random noise, HSI denoising), blurs (Gaussian and uniform blur, HSI deblurring), and down-sampled (both spectral and spatial downsample, HSI super-resolution). Previous HSI restoration methods are designed for one specific task only. Besides, most of them start from the 1-D vector or 2-D matrix models and cannot fully exploit the structurally spectral-spatial correlation in 3-D HSI. To overcome these limitations, in this work, we propose a unified low-rank tensor recovery model for comprehensive HSI restoration tasks, in which non-local similarity between spectral-spatial cubic and spectral correlation are simultaneously captured by 3-order tensors. Further, to improve the capability and flexibility, we formulate it as a weighted low-rank tensor recovery (WLRTR) model by treating the singular values differently, and study its analytical solution. We also consider the exclusive stripe noise in HSI as the gross error by extending WLRTR to robust principal component analysis (WLRTR-RPCA). Extensive experiments demonstrate the proposed WLRTR models consistently outperform state-of-the-arts in typical low level vision HSI tasks, including denoising, destriping, deblurring and super-resolution. |
| Tasks | Deblurring, Denoising, Image Restoration, Super-Resolution |
| Published | 2017-09-01 |
| URL | http://arxiv.org/abs/1709.00192v1 |
| http://arxiv.org/pdf/1709.00192v1.pdf | |
| PWC | https://paperswithcode.com/paper/weighted-low-rank-tensor-recovery-for |
| Repo | |
| Framework | |
Deep scattering transform applied to note onset detection and instrument recognition
| Title | Deep scattering transform applied to note onset detection and instrument recognition |
| Authors | D. Cazau, G. Revillon, O. Adam |
| Abstract | Automatic Music Transcription (AMT) is one of the oldest and most well-studied problems in the field of music information retrieval. Within this challenging research field, onset detection and instrument recognition take important places in transcription systems, as they respectively help to determine exact onset times of notes and to recognize the corresponding instrument sources. The aim of this study is to explore the usefulness of multiscale scattering operators for these two tasks on plucked string instrument and piano music. After resuming the theoretical background and illustrating the key features of this sound representation method, we evaluate its performances comparatively to other classical sound representations. Using both MIDI-driven datasets with real instrument samples and real musical pieces, scattering is proved to outperform other sound representations for these AMT subtasks, putting forward its richer sound representation and invariance properties. |
| Tasks | Information Retrieval, Music Information Retrieval |
| Published | 2017-03-28 |
| URL | http://arxiv.org/abs/1703.09775v1 |
| http://arxiv.org/pdf/1703.09775v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-scattering-transform-applied-to-note |
| Repo | |
| Framework | |
Diversification Methods for Zero-One Optimization
| Title | Diversification Methods for Zero-One Optimization |
| Authors | Fred Glover |
| Abstract | We introduce new diversification methods for zero-one optimization that significantly extend strategies previously introduced in the setting of metaheuristic search. Our methods incorporate easily implemented strategies for partitioning assignments of values to variables, accompanied by processes called augmentation and shifting which create greater flexibility and generality. We then show how the resulting collection of diversified solutions can be further diversified by means of permutation mappings, which equally can be used to generate diversified collections of permutations for applications such as scheduling and routing. These methods can be applied to non-binary vectors by the use of binarization procedures and by Diversification-Based Learning (DBL) procedures which also provide connections to applications in clustering and machine learning. Detailed pseudocode and numerical illustrations are provided to show the operation of our methods and the collections of solutions they create. |
| Tasks | |
| Published | 2017-01-30 |
| URL | http://arxiv.org/abs/1701.08709v2 |
| http://arxiv.org/pdf/1701.08709v2.pdf | |
| PWC | https://paperswithcode.com/paper/diversification-methods-for-zero-one |
| Repo | |
| Framework | |
Joint Layout Estimation and Global Multi-View Registration for Indoor Reconstruction
| Title | Joint Layout Estimation and Global Multi-View Registration for Indoor Reconstruction |
| Authors | Jeong-Kyun Lee, Jae-Won Yea, Min-Gyu Park, Kuk-Jin Yoon |
| Abstract | In this paper, we propose a novel method to jointly solve scene layout estimation and global registration problems for accurate indoor 3D reconstruction. Given a sequence of range data, we first build a set of scene fragments using KinectFusion and register them through pose graph optimization. Afterwards, we alternate between layout estimation and layout-based global registration processes in iterative fashion to complement each other. We extract the scene layout through hierarchical agglomerative clustering and energy-based multi-model fitting in consideration of noisy measurements. Having the estimated scene layout in one hand, we register all the range data through the global iterative closest point algorithm where the positions of 3D points that belong to the layout such as walls and a ceiling are constrained to be close to the layout. We experimentally verify the proposed method with the publicly available synthetic and real-world datasets in both quantitative and qualitative ways. |
| Tasks | 3D Reconstruction |
| Published | 2017-04-25 |
| URL | http://arxiv.org/abs/1704.07632v2 |
| http://arxiv.org/pdf/1704.07632v2.pdf | |
| PWC | https://paperswithcode.com/paper/joint-layout-estimation-and-global-multi-view |
| Repo | |
| Framework | |
Exact upper and lower bounds on the misclassification probability
| Title | Exact upper and lower bounds on the misclassification probability |
| Authors | Iosif Pinelis |
| Abstract | Exact lower and upper bounds on the best possible misclassification probability for a finite number of classes are obtained in terms of the total variation norms of the differences between the sub-distributions over the classes. These bounds are compared with the exact bounds in terms of the conditional entropy obtained by Feder and Merhav. |
| Tasks | |
| Published | 2017-12-03 |
| URL | http://arxiv.org/abs/1712.00812v4 |
| http://arxiv.org/pdf/1712.00812v4.pdf | |
| PWC | https://paperswithcode.com/paper/exact-upper-and-lower-bounds-on-the |
| Repo | |
| Framework | |
Segmentation-Aware Convolutional Networks Using Local Attention Masks
| Title | Segmentation-Aware Convolutional Networks Using Local Attention Masks |
| Authors | Adam W. Harley, Konstantinos G. Derpanis, Iasonas Kokkinos |
| Abstract | We introduce an approach to integrate segmentation information within a convolutional neural network (CNN). This counter-acts the tendency of CNNs to smooth information across regions and increases their spatial precision. To obtain segmentation information, we set up a CNN to provide an embedding space where region co-membership can be estimated based on Euclidean distance. We use these embeddings to compute a local attention mask relative to every neuron position. We incorporate such masks in CNNs and replace the convolution operation with a “segmentation-aware” variant that allows a neuron to selectively attend to inputs coming from its own region. We call the resulting network a segmentation-aware CNN because it adapts its filters at each image point according to local segmentation cues. We demonstrate the merit of our method on two widely different dense prediction tasks, that involve classification (semantic segmentation) and regression (optical flow). Our results show that in semantic segmentation we can match the performance of DenseCRFs while being faster and simpler, and in optical flow we obtain clearly sharper responses than networks that do not use local attention masks. In both cases, segmentation-aware convolution yields systematic improvements over strong baselines. Source code for this work is available online at http://cs.cmu.edu/~aharley/segaware. |
| Tasks | Optical Flow Estimation, Semantic Segmentation |
| Published | 2017-08-15 |
| URL | http://arxiv.org/abs/1708.04607v1 |
| http://arxiv.org/pdf/1708.04607v1.pdf | |
| PWC | https://paperswithcode.com/paper/segmentation-aware-convolutional-networks |
| Repo | |
| Framework | |
On the Benefit of Combining Neural, Statistical and External Features for Fake News Identification
| Title | On the Benefit of Combining Neural, Statistical and External Features for Fake News Identification |
| Authors | Gaurav Bhatt, Aman Sharma, Shivam Sharma, Ankush Nagpal, Balasubramanian Raman, Ankush Mittal |
| Abstract | Identifying the veracity of a news article is an interesting problem while automating this process can be a challenging task. Detection of a news article as fake is still an open question as it is contingent on many factors which the current state-of-the-art models fail to incorporate. In this paper, we explore a subtask to fake news identification, and that is stance detection. Given a news article, the task is to determine the relevance of the body and its claim. We present a novel idea that combines the neural, statistical and external features to provide an efficient solution to this problem. We compute the neural embedding from the deep recurrent model, statistical features from the weighted n-gram bag-of-words model and handcrafted external features with the help of feature engineering heuristics. Finally, using deep neural layer all the features are combined, thereby classifying the headline-body news pair as agree, disagree, discuss, or unrelated. We compare our proposed technique with the current state-of-the-art models on the fake news challenge dataset. Through extensive experiments, we find that the proposed model outperforms all the state-of-the-art techniques including the submissions to the fake news challenge. |
| Tasks | Feature Engineering, Stance Detection |
| Published | 2017-12-11 |
| URL | http://arxiv.org/abs/1712.03935v1 |
| http://arxiv.org/pdf/1712.03935v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-benefit-of-combining-neural |
| Repo | |
| Framework | |
Event Identification as a Decision Process with Non-linear Representation of Text
| Title | Event Identification as a Decision Process with Non-linear Representation of Text |
| Authors | Yukun Yan, Daqi Zheng, Zhengdong Lu, Sen Song |
| Abstract | We propose scale-free Identifier Network(sfIN), a novel model for event identification in documents. In general, sfIN first encodes a document into multi-scale memory stacks, then extracts special events via conducting multi-scale actions, which can be considered as a special type of sequence labelling. The design of large scale actions makes it more efficient processing a long document. The whole model is trained with both supervised learning and reinforcement learning. |
| Tasks | |
| Published | 2017-10-03 |
| URL | http://arxiv.org/abs/1710.00969v1 |
| http://arxiv.org/pdf/1710.00969v1.pdf | |
| PWC | https://paperswithcode.com/paper/event-identification-as-a-decision-process |
| Repo | |
| Framework | |
Comparison of PCA with ICA from data distribution perspective
| Title | Comparison of PCA with ICA from data distribution perspective |
| Authors | Miron Ivanov |
| Abstract | We performed an empirical comparison of ICA and PCA algorithms by applying them on two simulated noisy time series with varying distribution parameters and level of noise. In general, ICA shows better results than PCA because it takes into account higher moments of data distribution. On the other hand, PCA remains quite sensitive to the level of correlations among signals. |
| Tasks | Time Series |
| Published | 2017-09-29 |
| URL | http://arxiv.org/abs/1709.10222v1 |
| http://arxiv.org/pdf/1709.10222v1.pdf | |
| PWC | https://paperswithcode.com/paper/comparison-of-pca-with-ica-from-data |
| Repo | |
| Framework | |
Generalized linear models with low rank effects for network data
| Title | Generalized linear models with low rank effects for network data |
| Authors | Yun-Jhong Wu, Elizaveta Levina, Ji Zhu |
| Abstract | Networks are a useful representation for data on connections between units of interests, but the observed connections are often noisy and/or include missing values. One common approach to network analysis is to treat the network as a realization from a random graph model, and estimate the underlying edge probability matrix, which is sometimes referred to as network denoising. Here we propose a generalized linear model with low rank effects to model network edges. This model can be applied to various types of networks, including directed and undirected, binary and weighted, and it can naturally utilize additional information such as node and/or edge covariates. We develop an efficient projected gradient ascent algorithm to fit the model, establish asymptotic consistency, and demonstrate empirical performance of the method on both simulated and real networks. |
| Tasks | Denoising |
| Published | 2017-05-18 |
| URL | http://arxiv.org/abs/1705.06772v1 |
| http://arxiv.org/pdf/1705.06772v1.pdf | |
| PWC | https://paperswithcode.com/paper/generalized-linear-models-with-low-rank |
| Repo | |
| Framework | |
DeepWear: Adaptive Local Offloading for On-Wearable Deep Learning
| Title | DeepWear: Adaptive Local Offloading for On-Wearable Deep Learning |
| Authors | Mengwei Xu, Feng Qian, Mengze Zhu, Feifan Huang, Saumay Pushp, Xuanzhe Liu |
| Abstract | Due to their on-body and ubiquitous nature, wearables can generate a wide range of unique sensor data creating countless opportunities for deep learning tasks. We propose DeepWear, a deep learning (DL) framework for wearable devices to improve the performance and reduce the energy footprint. DeepWear strategically offloads DL tasks from a wearable device to its paired handheld device through local network. Compared to the remote-cloud-based offloading, DeepWear requires no Internet connectivity, consumes less energy, and is robust to privacy breach. DeepWear provides various novel techniques such as context-aware offloading, strategic model partition, and pipelining support to efficiently utilize the processing capacity from nearby paired handhelds. Deployed as a user-space library, DeepWear offers developer-friendly APIs that are as simple as those in traditional DL libraries such as TensorFlow. We have implemented DeepWear on the Android OS and evaluated it on COTS smartphones and smartwatches with real DL models. DeepWear brings up to 5.08X and 23.0X execution speedup, as well as 53.5% and 85.5% energy saving compared to wearable-only and handheld-only strategies, respectively. |
| Tasks | |
| Published | 2017-12-01 |
| URL | https://arxiv.org/abs/1712.03073v2 |
| https://arxiv.org/pdf/1712.03073v2.pdf | |
| PWC | https://paperswithcode.com/paper/enabling-cooperative-inference-of-deep |
| Repo | |
| Framework | |
Is writing style predictive of scientific fraud?
| Title | Is writing style predictive of scientific fraud? |
| Authors | Chloé Braud, Anders Søgaard |
| Abstract | The problem of detecting scientific fraud using machine learning was recently introduced, with initial, positive results from a model taking into account various general indicators. The results seem to suggest that writing style is predictive of scientific fraud. We revisit these initial experiments, and show that the leave-one-out testing procedure they used likely leads to a slight over-estimate of the predictability, but also that simple models can outperform their proposed model by some margin. We go on to explore more abstract linguistic features, such as linguistic complexity and discourse structure, only to obtain negative results. Upon analyzing our models, we do see some interesting patterns, though: Scientific fraud, for examples, contains less comparison, as well as different types of hedging and ways of presenting logical reasoning. |
| Tasks | |
| Published | 2017-07-13 |
| URL | http://arxiv.org/abs/1707.04095v1 |
| http://arxiv.org/pdf/1707.04095v1.pdf | |
| PWC | https://paperswithcode.com/paper/is-writing-style-predictive-of-scientific-1 |
| Repo | |
| Framework | |
A Pitfall of Unsupervised Pre-Training
| Title | A Pitfall of Unsupervised Pre-Training |
| Authors | Michele Alberti, Mathias Seuret, Rolf Ingold, Marcus Liwicki |
| Abstract | The point of this paper is to question typical assumptions in deep learning and suggest alternatives. A particular contribution is to prove that even if a Stacked Convolutional Auto-Encoder is good at reconstructing pictures, it is not necessarily good at discriminating their classes. When using Auto-Encoders, intuitively one assumes that features which are good for reconstruction will also lead to high classification accuracy. Indeed, it became research practice and is a suggested strategy by introductory books. However, we prove that this is not always the case. We thoroughly investigate the quality of features produced by Stacked Convolutional Auto-Encoders when trained to reconstruct their input. In particular, we analyze the relation between the reconstruction and classification capabilities of the network, if we were to use the same features for both tasks. Experimental results suggest that in fact, there is no correlation between the reconstruction score and the quality of features for a classification task. This means, more formally, that the sub-dimension representation space learned from the Stacked Convolutional Auto-Encoder (while being trained for input reconstruction) is not necessarily better separable than the initial input space. Furthermore, we show that the reconstruction error is not a good metric to assess the quality of features, because it is biased by the decoder quality. We do not question the usefulness of pre-training, but we conclude that aiming for the lowest reconstruction error is not necessarily a good idea if afterwards one performs a classification task. |
| Tasks | |
| Published | 2017-11-23 |
| URL | http://arxiv.org/abs/1712.01655v3 |
| http://arxiv.org/pdf/1712.01655v3.pdf | |
| PWC | https://paperswithcode.com/paper/a-pitfall-of-unsupervised-pre-training |
| Repo | |
| Framework | |
