Paper Group ANR 219
Refining Raw Sentence Representations for Textual Entailment Recognition via Attention. Transferring Autonomous Driving Knowledge on Simulated and Real Intersections. Robust Locally-Linear Controllable Embedding. Anisotropic Diffusion-based Kernel Matrix Model for Face Liveness Detection. Deep Learning and Model Predictive Control for Self-Tuning M …
Refining Raw Sentence Representations for Textual Entailment Recognition via Attention
| Title | Refining Raw Sentence Representations for Textual Entailment Recognition via Attention |
| Authors | Jorge A. Balazs, Edison Marrese-Taylor, Pablo Loyola, Yutaka Matsuo |
| Abstract | In this paper we present the model used by the team Rivercorners for the 2017 RepEval shared task. First, our model separately encodes a pair of sentences into variable-length representations by using a bidirectional LSTM. Later, it creates fixed-length raw representations by means of simple aggregation functions, which are then refined using an attention mechanism. Finally it combines the refined representations of both sentences into a single vector to be used for classification. With this model we obtained test accuracies of 72.057% and 72.055% in the matched and mismatched evaluation tracks respectively, outperforming the LSTM baseline, and obtaining performances similar to a model that relies on shared information between sentences (ESIM). When using an ensemble both accuracies increased to 72.247% and 72.827% respectively. |
| Tasks | Natural Language Inference |
| Published | 2017-07-11 |
| URL | http://arxiv.org/abs/1707.03103v2 |
| http://arxiv.org/pdf/1707.03103v2.pdf | |
| PWC | https://paperswithcode.com/paper/refining-raw-sentence-representations-for |
| Repo | |
| Framework | |
Transferring Autonomous Driving Knowledge on Simulated and Real Intersections
| Title | Transferring Autonomous Driving Knowledge on Simulated and Real Intersections |
| Authors | David Isele, Akansel Cosgun |
| Abstract | We view intersection handling on autonomous vehicles as a reinforcement learning problem, and study its behavior in a transfer learning setting. We show that a network trained on one type of intersection generally is not able to generalize to other intersections. However, a network that is pre-trained on one intersection and fine-tuned on another performs better on the new task compared to training in isolation. This network also retains knowledge of the prior task, even though some forgetting occurs. Finally, we show that the benefits of fine-tuning hold when transferring simulated intersection handling knowledge to a real autonomous vehicle. |
| Tasks | Autonomous Driving, Autonomous Vehicles, Transfer Learning |
| Published | 2017-11-30 |
| URL | http://arxiv.org/abs/1712.01106v1 |
| http://arxiv.org/pdf/1712.01106v1.pdf | |
| PWC | https://paperswithcode.com/paper/transferring-autonomous-driving-knowledge-on |
| Repo | |
| Framework | |
Robust Locally-Linear Controllable Embedding
| Title | Robust Locally-Linear Controllable Embedding |
| Authors | Ershad Banijamali, Rui Shu, Mohammad Ghavamzadeh, Hung Bui, Ali Ghodsi |
| Abstract | Embed-to-control (E2C) is a model for solving high-dimensional optimal control problems by combining variational auto-encoders with locally-optimal controllers. However, the E2C model suffers from two major drawbacks: 1) its objective function does not correspond to the likelihood of the data sequence and 2) the variational encoder used for embedding typically has large variational approximation error, especially when there is noise in the system dynamics. In this paper, we present a new model for learning robust locally-linear controllable embedding (RCE). Our model directly estimates the predictive conditional density of the future observation given the current one, while introducing the bottleneck between the current and future observations. Although the bottleneck provides a natural embedding candidate for control, our RCE model introduces additional specific structures in the generative graphical model so that the model dynamics can be robustly linearized. We also propose a principled variational approximation of the embedding posterior that takes the future observation into account, and thus, makes the variational approximation more robust against the noise. Experimental results show that RCE outperforms the E2C model, and does so significantly when the underlying dynamics is noisy. |
| Tasks | |
| Published | 2017-10-15 |
| URL | http://arxiv.org/abs/1710.05373v2 |
| http://arxiv.org/pdf/1710.05373v2.pdf | |
| PWC | https://paperswithcode.com/paper/robust-locally-linear-controllable-embedding |
| Repo | |
| Framework | |
Anisotropic Diffusion-based Kernel Matrix Model for Face Liveness Detection
| Title | Anisotropic Diffusion-based Kernel Matrix Model for Face Liveness Detection |
| Authors | Changyong Yu, Yunde Jia |
| Abstract | Facial recognition and verification is a widely used biometric technology in security system. Unfortunately, face biometrics is vulnerable to spoofing attacks using photographs or videos. In this paper, we present an anisotropic diffusion-based kernel matrix model (ADKMM) for face liveness detection to prevent face spoofing attacks. We use the anisotropic diffusion to enhance the edges and boundary locations of a face image, and the kernel matrix model to extract face image features which we call the diffusion-kernel (D-K) features. The D-K features reflect the inner correlation of the face image sequence. We introduce convolution neural networks to extract the deep features, and then, employ a generalized multiple kernel learning method to fuse the D-K features and the deep features to achieve better performance. Our experimental evaluation on the two publicly available datasets shows that the proposed method outperforms the state-of-art face liveness detection methods. |
| Tasks | |
| Published | 2017-07-10 |
| URL | http://arxiv.org/abs/1707.02692v1 |
| http://arxiv.org/pdf/1707.02692v1.pdf | |
| PWC | https://paperswithcode.com/paper/anisotropic-diffusion-based-kernel-matrix |
| Repo | |
| Framework | |
Deep Learning and Model Predictive Control for Self-Tuning Mode-Locked Lasers
| Title | Deep Learning and Model Predictive Control for Self-Tuning Mode-Locked Lasers |
| Authors | Thomas Baumeister, Steven L. Brunton, J. Nathan Kutz |
| Abstract | Self-tuning optical systems are of growing importance in technological applications such as mode-locked fiber lasers. Such self-tuning paradigms require {\em intelligent} algorithms capable of inferring approximate models of the underlying physics and discovering appropriate control laws in order to maintain robust performance for a given objective. In this work, we demonstrate the first integration of a {\em deep learning} (DL) architecture with {\em model predictive control} (MPC) in order to self-tune a mode-locked fiber laser. Not only can our DL-MPC algorithmic architecture approximate the unknown fiber birefringence, it also builds a dynamical model of the laser and appropriate control law for maintaining robust, high-energy pulses despite a stochastically drifting birefringence. We demonstrate the effectiveness of this method on a fiber laser which is mode-locked by nonlinear polarization rotation. The method advocated can be broadly applied to a variety of optical systems that require robust controllers. |
| Tasks | |
| Published | 2017-11-02 |
| URL | http://arxiv.org/abs/1711.02702v1 |
| http://arxiv.org/pdf/1711.02702v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-and-model-predictive-control |
| Repo | |
| Framework | |
The Stochastic Replica Approach to Machine Learning: Stability and Parameter Optimization
| Title | The Stochastic Replica Approach to Machine Learning: Stability and Parameter Optimization |
| Authors | Patrick Chao, Tahereh Mazaheri, Bo Sun, Nicholas B. Weingartner, Zohar Nussinov |
| Abstract | We introduce a statistical physics inspired supervised machine learning algorithm for classification and regression problems. The method is based on the invariances or stability of predicted results when known data is represented as expansions in terms of various stochastic functions. The algorithm predicts the classification/regression values of new data by combining (via voting) the outputs of these numerous linear expansions in randomly chosen functions. The few parameters (typically only one parameter is used in all studied examples) that this model has may be automatically optimized. The algorithm has been tested on 10 diverse training data sets of various types and feature space dimensions. It has been shown to consistently exhibit high accuracy and readily allow for optimization of parameters, while simultaneously avoiding pitfalls of existing algorithms such as those associated with class imbalance. We very briefly speculate on whether spatial coordinates in physical theories may be viewed as emergent “features” that enable a robust machine learning type description of data with generic low order smooth functions. |
| Tasks | |
| Published | 2017-08-18 |
| URL | http://arxiv.org/abs/1708.05715v3 |
| http://arxiv.org/pdf/1708.05715v3.pdf | |
| PWC | https://paperswithcode.com/paper/the-stochastic-replica-approach-to-machine |
| Repo | |
| Framework | |
Convolutional Long Short-Term Memory Networks for Recognizing First Person Interactions
| Title | Convolutional Long Short-Term Memory Networks for Recognizing First Person Interactions |
| Authors | Swathikiran Sudhakaran, Oswald Lanz |
| Abstract | In this paper, we present a novel deep learning based approach for addressing the problem of interaction recognition from a first person perspective. The proposed approach uses a pair of convolutional neural networks, whose parameters are shared, for extracting frame level features from successive frames of the video. The frame level features are then aggregated using a convolutional long short-term memory. The hidden state of the convolutional long short-term memory, after all the input video frames are processed, is used for classification in to the respective categories. The two branches of the convolutional neural network perform feature encoding on a short time interval whereas the convolutional long short term memory encodes the changes on a longer temporal duration. In our network the spatio-temporal structure of the input is preserved till the very final processing stage. Experimental results show that our method outperforms the state of the art on most recent first person interactions datasets that involve complex ego-motion. In particular, on UTKinect-FirstPerson it competes with methods that use depth image and skeletal joints information along with RGB images, while it surpasses all previous methods that use only RGB images by more than 20% in recognition accuracy. |
| Tasks | |
| Published | 2017-09-19 |
| URL | http://arxiv.org/abs/1709.06495v1 |
| http://arxiv.org/pdf/1709.06495v1.pdf | |
| PWC | https://paperswithcode.com/paper/convolutional-long-short-term-memory-networks |
| Repo | |
| Framework | |
Towards Bidirectional Hierarchical Representations for Attention-Based Neural Machine Translation
| Title | Towards Bidirectional Hierarchical Representations for Attention-Based Neural Machine Translation |
| Authors | Baosong Yang, Derek F. Wong, Tong Xiao, Lidia S. Chao, Jingbo Zhu |
| Abstract | This paper proposes a hierarchical attentional neural translation model which focuses on enhancing source-side hierarchical representations by covering both local and global semantic information using a bidirectional tree-based encoder. To maximize the predictive likelihood of target words, a weighted variant of an attention mechanism is used to balance the attentive information between lexical and phrase vectors. Using a tree-based rare word encoding, the proposed model is extended to sub-word level to alleviate the out-of-vocabulary (OOV) problem. Empirical results reveal that the proposed model significantly outperforms sequence-to-sequence attention-based and tree-based neural translation models in English-Chinese translation tasks. |
| Tasks | Machine Translation |
| Published | 2017-07-17 |
| URL | http://arxiv.org/abs/1707.05114v1 |
| http://arxiv.org/pdf/1707.05114v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-bidirectional-hierarchical |
| Repo | |
| Framework | |
All-relevant feature selection using multidimensional filters with exhaustive search
| Title | All-relevant feature selection using multidimensional filters with exhaustive search |
| Authors | Krzysztof Mnich, Witold R. Rudnicki |
| Abstract | This paper describes a method for identification of the informative variables in the information system with discrete decision variables. It is targeted specifically towards discovery of the variables that are non-informative when considered alone, but are informative when the synergistic interactions between multiple variables are considered. To this end, the mutual entropy of all possible k-tuples of variables with decision variable is computed. Then, for each variable the maximal information gain due to interactions with other variables is obtained. For non-informative variables this quantity conforms to the well known statistical distributions. This allows for discerning truly informative variables from non-informative ones. For demonstration of the approach, the method is applied to several synthetic datasets that involve complex multidimensional interactions between variables. It is capable of identifying most important informative variables, even in the case when the dimensionality of the analysis is smaller than the true dimensionality of the problem. What is more, the high sensitivity of the algorithm allows for detection of the influence of nuisance variables on the response variable. |
| Tasks | Feature Selection |
| Published | 2017-05-16 |
| URL | http://arxiv.org/abs/1705.05756v1 |
| http://arxiv.org/pdf/1705.05756v1.pdf | |
| PWC | https://paperswithcode.com/paper/all-relevant-feature-selection-using |
| Repo | |
| Framework | |
Spectral Clustering using PCKID - A Probabilistic Cluster Kernel for Incomplete Data
| Title | Spectral Clustering using PCKID - A Probabilistic Cluster Kernel for Incomplete Data |
| Authors | Sigurd Løkse, Filippo Maria Bianchi, Arnt-Børre Salberg, Robert Jenssen |
| Abstract | In this paper, we propose PCKID, a novel, robust, kernel function for spectral clustering, specifically designed to handle incomplete data. By combining posterior distributions of Gaussian Mixture Models for incomplete data on different scales, we are able to learn a kernel for incomplete data that does not depend on any critical hyperparameters, unlike the commonly used RBF kernel. To evaluate our method, we perform experiments on two real datasets. PCKID outperforms the baseline methods for all fractions of missing values and in some cases outperforms the baseline methods with up to 25 percentage points. |
| Tasks | |
| Published | 2017-02-23 |
| URL | http://arxiv.org/abs/1702.07190v1 |
| http://arxiv.org/pdf/1702.07190v1.pdf | |
| PWC | https://paperswithcode.com/paper/spectral-clustering-using-pckid-a |
| Repo | |
| Framework | |
On the relation between dependency distance, crossing dependencies, and parsing. Comment on “Dependency distance: a new perspective on syntactic patterns in natural languages” by Haitao Liu et al
| Title | On the relation between dependency distance, crossing dependencies, and parsing. Comment on “Dependency distance: a new perspective on syntactic patterns in natural languages” by Haitao Liu et al |
| Authors | Carlos Gómez-Rodríguez |
| Abstract | Liu et al. (2017) provide a comprehensive account of research on dependency distance in human languages. While the article is a very rich and useful report on this complex subject, here I will expand on a few specific issues where research in computational linguistics (specifically natural language processing) can inform DDM research, and vice versa. These aspects have not been explored much in the article by Liu et al. or elsewhere, probably due to the little overlap between both research communities, but they may provide interesting insights for improving our understanding of the evolution of human languages, the mechanisms by which the brain processes and understands language, and the construction of effective computer systems to achieve this goal. |
| Tasks | |
| Published | 2017-05-27 |
| URL | http://arxiv.org/abs/1705.09837v2 |
| http://arxiv.org/pdf/1705.09837v2.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-relation-between-dependency-distance |
| Repo | |
| Framework | |
Face Retrieval using Frequency Decoded Local Descriptor
| Title | Face Retrieval using Frequency Decoded Local Descriptor |
| Authors | Shiv Ram Dubey |
| Abstract | The local descriptors have been the backbone of most of the computer vision problems. Most of the existing local descriptors are generated over the raw input images. In order to increase the discriminative power of the local descriptors, some researchers converted the raw image into multiple images with the help of some high and low pass frequency filters, then the local descriptors are computed over each filtered image and finally concatenated into a single descriptor. By doing so, these approaches do not utilize the inter frequency relationship which causes the less improvement in the discriminative power of the descriptor that could be achieved. In this paper, this problem is solved by utilizing the decoder concept of multi-channel decoded local binary pattern over the multi-frequency patterns. A frequency decoded local binary pattern (FDLBP) is proposed with two decoders. Each decoder works with one low frequency pattern and two high frequency patterns. Finally, the descriptors from both decoders are concatenated to form the single descriptor. The face retrieval experiments are conducted over four benchmarks and challenging databases such as PaSC, LFW, PubFig, and ESSEX. The experimental results confirm the superiority of the FDLBP descriptor as compared to the state-of-the-art descriptors such as LBP, SOBEL_LBP, BoF_LBP, SVD_S_LBP, mdLBP, etc. |
| Tasks | |
| Published | 2017-09-16 |
| URL | http://arxiv.org/abs/1709.06508v2 |
| http://arxiv.org/pdf/1709.06508v2.pdf | |
| PWC | https://paperswithcode.com/paper/face-retrieval-using-frequency-decoded-local |
| Repo | |
| Framework | |
Co-Fusion: Real-time Segmentation, Tracking and Fusion of Multiple Objects
| Title | Co-Fusion: Real-time Segmentation, Tracking and Fusion of Multiple Objects |
| Authors | Martin Rünz, Lourdes Agapito |
| Abstract | In this paper we introduce Co-Fusion, a dense SLAM system that takes a live stream of RGB-D images as input and segments the scene into different objects (using either motion or semantic cues) while simultaneously tracking and reconstructing their 3D shape in real time. We use a multiple model fitting approach where each object can move independently from the background and still be effectively tracked and its shape fused over time using only the information from pixels associated with that object label. Previous attempts to deal with dynamic scenes have typically considered moving regions as outliers, and consequently do not model their shape or track their motion over time. In contrast, we enable the robot to maintain 3D models for each of the segmented objects and to improve them over time through fusion. As a result, our system can enable a robot to maintain a scene description at the object level which has the potential to allow interactions with its working environment; even in the case of dynamic scenes. |
| Tasks | |
| Published | 2017-06-20 |
| URL | http://arxiv.org/abs/1706.06629v1 |
| http://arxiv.org/pdf/1706.06629v1.pdf | |
| PWC | https://paperswithcode.com/paper/co-fusion-real-time-segmentation-tracking-and |
| Repo | |
| Framework | |
Guaranteed Sufficient Decrease for Variance Reduced Stochastic Gradient Descent
| Title | Guaranteed Sufficient Decrease for Variance Reduced Stochastic Gradient Descent |
| Authors | Fanhua Shang, Yuanyuan Liu, James Cheng, Kelvin Kai Wing Ng, Yuichi Yoshida |
| Abstract | In this paper, we propose a novel sufficient decrease technique for variance reduced stochastic gradient descent methods such as SAG, SVRG and SAGA. In order to make sufficient decrease for stochastic optimization, we design a new sufficient decrease criterion, which yields sufficient decrease versions of variance reduction algorithms such as SVRG-SD and SAGA-SD as a byproduct. We introduce a coefficient to scale current iterate and satisfy the sufficient decrease property, which takes the decisions to shrink, expand or move in the opposite direction, and then give two specific update rules of the coefficient for Lasso and ridge regression. Moreover, we analyze the convergence properties of our algorithms for strongly convex problems, which show that both of our algorithms attain linear convergence rates. We also provide the convergence guarantees of our algorithms for non-strongly convex problems. Our experimental results further verify that our algorithms achieve significantly better performance than their counterparts. |
| Tasks | Stochastic Optimization |
| Published | 2017-03-20 |
| URL | http://arxiv.org/abs/1703.06807v2 |
| http://arxiv.org/pdf/1703.06807v2.pdf | |
| PWC | https://paperswithcode.com/paper/guaranteed-sufficient-decrease-for-variance |
| Repo | |
| Framework | |
A comparison of single-trial EEG classification and EEG-informed fMRI across three MR compatible EEG recording systems
| Title | A comparison of single-trial EEG classification and EEG-informed fMRI across three MR compatible EEG recording systems |
| Authors | Josef Faller, Linbi Hong, Jennifer Cummings, Paul Sajda |
| Abstract | Simultaneously recorded electroencephalography (EEG) and functional magnetic resonance imaging (fMRI) can be used to non-invasively measure the spatiotemporal dynamics of the human brain. One challenge is dealing with the artifacts that each modality introduces into the other when the two are recorded concurrently, for example the ballistocardiogram (BCG). We conducted a preliminary comparison of three different MR compatible EEG recording systems and assessed their performance in terms of single-trial classification of the EEG when simultaneously collecting fMRI. We found tradeoffs across all three systems, for example varied ease of setup and improved classification accuracy with reference electrodes (REF) but not for pulse artifact subtraction (PAS) or reference layer adaptive filtering (RLAF). |
| Tasks | EEG |
| Published | 2017-07-25 |
| URL | http://arxiv.org/abs/1707.08077v1 |
| http://arxiv.org/pdf/1707.08077v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-comparison-of-single-trial-eeg |
| Repo | |
| Framework | |
