Paper Group AWR 203
Data Augmentation of Spectral Data for Convolutional Neural Network (CNN) Based Deep Chemometrics. Federated Control with Hierarchical Multi-Agent Deep Reinforcement Learning. Inertial Odometry on Handheld Smartphones. TURN TAP: Temporal Unit Regression Network for Temporal Action Proposals. Deep Forecast: Deep Learning-based Spatio-Temporal Foreca …
Data Augmentation of Spectral Data for Convolutional Neural Network (CNN) Based Deep Chemometrics
| Title | Data Augmentation of Spectral Data for Convolutional Neural Network (CNN) Based Deep Chemometrics |
| Authors | Esben Jannik Bjerrum, Mads Glahder, Thomas Skov |
| Abstract | Deep learning methods are used on spectroscopic data to predict drug content in tablets from near infrared (NIR) spectra. Using convolutional neural networks (CNNs), features are ex- tracted from the spectroscopic data. Extended multiplicative scatter correction (EMSC) and a novel spectral data augmentation method are benchmarked as preprocessing steps. The learned models perform better or on par with hypothetical optimal partial least squares (PLS) models for all combinations of preprocessing. Data augmentation with subsequent EMSC in combination gave the best results. The deep learning model CNNs also outperform the PLS models in an extrapolation chal- lenge created using data from a second instrument and from an analyte concentration not covered by the training data. Qualitative investigations of the CNNs kernel activations show their resemblance to wellknown data processing methods such as smoothing, slope/derivative, thresholds and spectral region selection. |
| Tasks | Data Augmentation |
| Published | 2017-10-05 |
| URL | http://arxiv.org/abs/1710.01927v1 |
| http://arxiv.org/pdf/1710.01927v1.pdf | |
| PWC | https://paperswithcode.com/paper/data-augmentation-of-spectral-data-for |
| Repo | https://github.com/EBjerrum/Deep-Chemometrics |
| Framework | none |
Federated Control with Hierarchical Multi-Agent Deep Reinforcement Learning
| Title | Federated Control with Hierarchical Multi-Agent Deep Reinforcement Learning |
| Authors | Saurabh Kumar, Pararth Shah, Dilek Hakkani-Tur, Larry Heck |
| Abstract | We present a framework combining hierarchical and multi-agent deep reinforcement learning approaches to solve coordination problems among a multitude of agents using a semi-decentralized model. The framework extends the multi-agent learning setup by introducing a meta-controller that guides the communication between agent pairs, enabling agents to focus on communicating with only one other agent at any step. This hierarchical decomposition of the task allows for efficient exploration to learn policies that identify globally optimal solutions even as the number of collaborating agents increases. We show promising initial experimental results on a simulated distributed scheduling problem. |
| Tasks | Efficient Exploration |
| Published | 2017-12-22 |
| URL | http://arxiv.org/abs/1712.08266v1 |
| http://arxiv.org/pdf/1712.08266v1.pdf | |
| PWC | https://paperswithcode.com/paper/federated-control-with-hierarchical-multi |
| Repo | https://github.com/skumar9876/FCRL |
| Framework | none |
Inertial Odometry on Handheld Smartphones
| Title | Inertial Odometry on Handheld Smartphones |
| Authors | Arno Solin, Santiago Cortes, Esa Rahtu, Juho Kannala |
| Abstract | Building a complete inertial navigation system using the limited quality data provided by current smartphones has been regarded challenging, if not impossible. This paper shows that by careful crafting and accounting for the weak information in the sensor samples, smartphones are capable of pure inertial navigation. We present a probabilistic approach for orientation and use-case free inertial odometry, which is based on double-integrating rotated accelerations. The strength of the model is in learning additive and multiplicative IMU biases online. We are able to track the phone position, velocity, and pose in real-time and in a computationally lightweight fashion by solving the inference with an extended Kalman filter. The information fusion is completed with zero-velocity updates (if the phone remains stationary), altitude correction from barometric pressure readings (if available), and pseudo-updates constraining the momentary speed. We demonstrate our approach using an iPad and iPhone in several indoor dead-reckoning applications and in a measurement tool setup. |
| Tasks | |
| Published | 2017-03-01 |
| URL | http://arxiv.org/abs/1703.00154v2 |
| http://arxiv.org/pdf/1703.00154v2.pdf | |
| PWC | https://paperswithcode.com/paper/inertial-odometry-on-handheld-smartphones |
| Repo | https://github.com/dmckinnon/mapper |
| Framework | none |
TURN TAP: Temporal Unit Regression Network for Temporal Action Proposals
| Title | TURN TAP: Temporal Unit Regression Network for Temporal Action Proposals |
| Authors | Jiyang Gao, Zhenheng Yang, Chen Sun, Kan Chen, Ram Nevatia |
| Abstract | Temporal Action Proposal (TAP) generation is an important problem, as fast and accurate extraction of semantically important (e.g. human actions) segments from untrimmed videos is an important step for large-scale video analysis. We propose a novel Temporal Unit Regression Network (TURN) model. There are two salient aspects of TURN: (1) TURN jointly predicts action proposals and refines the temporal boundaries by temporal coordinate regression; (2) Fast computation is enabled by unit feature reuse: a long untrimmed video is decomposed into video units, which are reused as basic building blocks of temporal proposals. TURN outperforms the state-of-the-art methods under average recall (AR) by a large margin on THUMOS-14 and ActivityNet datasets, and runs at over 880 frames per second (FPS) on a TITAN X GPU. We further apply TURN as a proposal generation stage for existing temporal action localization pipelines, it outperforms state-of-the-art performance on THUMOS-14 and ActivityNet. |
| Tasks | Action Localization, Temporal Action Localization |
| Published | 2017-03-17 |
| URL | http://arxiv.org/abs/1703.06189v2 |
| http://arxiv.org/pdf/1703.06189v2.pdf | |
| PWC | https://paperswithcode.com/paper/turn-tap-temporal-unit-regression-network-for |
| Repo | https://github.com/jiyanggao/TURN-TAP |
| Framework | tf |
Deep Forecast: Deep Learning-based Spatio-Temporal Forecasting
| Title | Deep Forecast: Deep Learning-based Spatio-Temporal Forecasting |
| Authors | Amir Ghaderi, Borhan M. Sanandaji, Faezeh Ghaderi |
| Abstract | The paper presents a spatio-temporal wind speed forecasting algorithm using Deep Learning (DL)and in particular, Recurrent Neural Networks(RNNs). Motivated by recent advances in renewable energy integration and smart grids, we apply our proposed algorithm for wind speed forecasting. Renewable energy resources (wind and solar)are random in nature and, thus, their integration is facilitated with accurate short-term forecasts. In our proposed framework, we model the spatiotemporal information by a graph whose nodes are data generating entities and its edges basically model how these nodes are interacting with each other. One of the main contributions of our work is the fact that we obtain forecasts of all nodes of the graph at the same time based on one framework. Results of a case study on recorded time series data from a collection of wind mills in the north-east of the U.S. show that the proposed DL-based forecasting algorithm significantly improves the short-term forecasts compared to a set of widely-used benchmarks models. |
| Tasks | Spatio-Temporal Forecasting, Time Series |
| Published | 2017-07-24 |
| URL | http://arxiv.org/abs/1707.08110v1 |
| http://arxiv.org/pdf/1707.08110v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-forecast-deep-learning-based-spatio |
| Repo | https://github.com/amirstar/Deep-Forecast |
| Framework | tf |
Generic Axiomatization of Families of Noncrossing Graphs in Dependency Parsing
| Title | Generic Axiomatization of Families of Noncrossing Graphs in Dependency Parsing |
| Authors | Anssi Yli-Jyrä, Carlos Gómez-Rodríguez |
| Abstract | We present a simple encoding for unlabeled noncrossing graphs and show how its latent counterpart helps us to represent several families of directed and undirected graphs used in syntactic and semantic parsing of natural language as context-free languages. The families are separated purely on the basis of forbidden patterns in latent encoding, eliminating the need to differentiate the families of non-crossing graphs in inference algorithms: one algorithm works for all when the search space can be controlled in parser input. |
| Tasks | Dependency Parsing, Semantic Parsing |
| Published | 2017-06-11 |
| URL | http://arxiv.org/abs/1706.03357v1 |
| http://arxiv.org/pdf/1706.03357v1.pdf | |
| PWC | https://paperswithcode.com/paper/generic-axiomatization-of-families-of-1 |
| Repo | https://github.com/amikael/ncdigraphs |
| Framework | none |
Deep Reinforcement Learning: An Overview
| Title | Deep Reinforcement Learning: An Overview |
| Authors | Yuxi Li |
| Abstract | We give an overview of recent exciting achievements of deep reinforcement learning (RL). We discuss six core elements, six important mechanisms, and twelve applications. We start with background of machine learning, deep learning and reinforcement learning. Next we discuss core RL elements, including value function, in particular, Deep Q-Network (DQN), policy, reward, model, planning, and exploration. After that, we discuss important mechanisms for RL, including attention and memory, unsupervised learning, transfer learning, multi-agent RL, hierarchical RL, and learning to learn. Then we discuss various applications of RL, including games, in particular, AlphaGo, robotics, natural language processing, including dialogue systems, machine translation, and text generation, computer vision, neural architecture design, business management, finance, healthcare, Industry 4.0, smart grid, intelligent transportation systems, and computer systems. We mention topics not reviewed yet, and list a collection of RL resources. After presenting a brief summary, we close with discussions. Please see Deep Reinforcement Learning, arXiv:1810.06339, for a significant update. |
| Tasks | Machine Translation, Text Generation, Transfer Learning |
| Published | 2017-01-25 |
| URL | http://arxiv.org/abs/1701.07274v6 |
| http://arxiv.org/pdf/1701.07274v6.pdf | |
| PWC | https://paperswithcode.com/paper/deep-reinforcement-learning-an-overview |
| Repo | https://github.com/anthonyalford/Linkdump |
| Framework | tf |
An Embedded Deep Learning based Word Prediction
| Title | An Embedded Deep Learning based Word Prediction |
| Authors | Seunghak Yu, Nilesh Kulkarni, Haejun Lee, Jihie Kim |
| Abstract | Recent developments in deep learning with application to language modeling have led to success in tasks of text processing, summarizing and machine translation. However, deploying huge language models for mobile device such as on-device keyboards poses computation as a bottle-neck due to their puny computation capacities. In this work we propose an embedded deep learning based word prediction method that optimizes run-time memory and also provides a real time prediction environment. Our model size is 7.40MB and has average prediction time of 6.47 ms. We improve over the existing methods for word prediction in terms of key stroke savings and word prediction rate. |
| Tasks | Language Modelling, Machine Translation |
| Published | 2017-07-06 |
| URL | http://arxiv.org/abs/1707.01662v1 |
| http://arxiv.org/pdf/1707.01662v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-embedded-deep-learning-based-word |
| Repo | https://github.com/meinwerk/WordPrediction |
| Framework | none |
Thinking Fast and Slow with Deep Learning and Tree Search
| Title | Thinking Fast and Slow with Deep Learning and Tree Search |
| Authors | Thomas Anthony, Zheng Tian, David Barber |
| Abstract | Sequential decision making problems, such as structured prediction, robotic control, and game playing, require a combination of planning policies and generalisation of those plans. In this paper, we present Expert Iteration (ExIt), a novel reinforcement learning algorithm which decomposes the problem into separate planning and generalisation tasks. Planning new policies is performed by tree search, while a deep neural network generalises those plans. Subsequently, tree search is improved by using the neural network policy to guide search, increasing the strength of new plans. In contrast, standard deep Reinforcement Learning algorithms rely on a neural network not only to generalise plans, but to discover them too. We show that ExIt outperforms REINFORCE for training a neural network to play the board game Hex, and our final tree search agent, trained tabula rasa, defeats MoHex 1.0, the most recent Olympiad Champion player to be publicly released. |
| Tasks | Decision Making, Structured Prediction |
| Published | 2017-05-23 |
| URL | http://arxiv.org/abs/1705.08439v4 |
| http://arxiv.org/pdf/1705.08439v4.pdf | |
| PWC | https://paperswithcode.com/paper/thinking-fast-and-slow-with-deep-learning-and |
| Repo | https://github.com/richemslie/galvanise_zero |
| Framework | tf |
Variational Deep Semantic Hashing for Text Documents
| Title | Variational Deep Semantic Hashing for Text Documents |
| Authors | Suthee Chaidaroon, Yi Fang |
| Abstract | As the amount of textual data has been rapidly increasing over the past decade, efficient similarity search methods have become a crucial component of large-scale information retrieval systems. A popular strategy is to represent original data samples by compact binary codes through hashing. A spectrum of machine learning methods have been utilized, but they often lack expressiveness and flexibility in modeling to learn effective representations. The recent advances of deep learning in a wide range of applications has demonstrated its capability to learn robust and powerful feature representations for complex data. Especially, deep generative models naturally combine the expressiveness of probabilistic generative models with the high capacity of deep neural networks, which is very suitable for text modeling. However, little work has leveraged the recent progress in deep learning for text hashing. In this paper, we propose a series of novel deep document generative models for text hashing. The first proposed model is unsupervised while the second one is supervised by utilizing document labels/tags for hashing. The third model further considers document-specific factors that affect the generation of words. The probabilistic generative formulation of the proposed models provides a principled framework for model extension, uncertainty estimation, simulation, and interpretability. Based on variational inference and reparameterization, the proposed models can be interpreted as encoder-decoder deep neural networks and thus they are capable of learning complex nonlinear distributed representations of the original documents. We conduct a comprehensive set of experiments on four public testbeds. The experimental results have demonstrated the effectiveness of the proposed supervised learning models for text hashing. |
| Tasks | Information Retrieval |
| Published | 2017-08-11 |
| URL | http://arxiv.org/abs/1708.03436v1 |
| http://arxiv.org/pdf/1708.03436v1.pdf | |
| PWC | https://paperswithcode.com/paper/variational-deep-semantic-hashing-for-text |
| Repo | https://github.com/unsuthee/VariationalDeepSemanticHashing |
| Framework | tf |
Controllable Invariance through Adversarial Feature Learning
| Title | Controllable Invariance through Adversarial Feature Learning |
| Authors | Qizhe Xie, Zihang Dai, Yulun Du, Eduard Hovy, Graham Neubig |
| Abstract | Learning meaningful representations that maintain the content necessary for a particular task while filtering away detrimental variations is a problem of great interest in machine learning. In this paper, we tackle the problem of learning representations invariant to a specific factor or trait of data. The representation learning process is formulated as an adversarial minimax game. We analyze the optimal equilibrium of such a game and find that it amounts to maximizing the uncertainty of inferring the detrimental factor given the representation while maximizing the certainty of making task-specific predictions. On three benchmark tasks, namely fair and bias-free classification, language-independent generation, and lighting-independent image classification, we show that the proposed framework induces an invariant representation, and leads to better generalization evidenced by the improved performance. |
| Tasks | Image Classification, Representation Learning |
| Published | 2017-05-31 |
| URL | http://arxiv.org/abs/1705.11122v3 |
| http://arxiv.org/pdf/1705.11122v3.pdf | |
| PWC | https://paperswithcode.com/paper/controllable-invariance-through-adversarial |
| Repo | https://github.com/qizhex/Controllable-Invariance |
| Framework | pytorch |
DeepStack: Expert-Level Artificial Intelligence in No-Limit Poker
| Title | DeepStack: Expert-Level Artificial Intelligence in No-Limit Poker |
| Authors | Matej Moravčík, Martin Schmid, Neil Burch, Viliam Lisý, Dustin Morrill, Nolan Bard, Trevor Davis, Kevin Waugh, Michael Johanson, Michael Bowling |
| Abstract | Artificial intelligence has seen several breakthroughs in recent years, with games often serving as milestones. A common feature of these games is that players have perfect information. Poker is the quintessential game of imperfect information, and a longstanding challenge problem in artificial intelligence. We introduce DeepStack, an algorithm for imperfect information settings. It combines recursive reasoning to handle information asymmetry, decomposition to focus computation on the relevant decision, and a form of intuition that is automatically learned from self-play using deep learning. In a study involving 44,000 hands of poker, DeepStack defeated with statistical significance professional poker players in heads-up no-limit Texas hold’em. The approach is theoretically sound and is shown to produce more difficult to exploit strategies than prior approaches. |
| Tasks | Game of Poker |
| Published | 2017-01-06 |
| URL | http://arxiv.org/abs/1701.01724v3 |
| http://arxiv.org/pdf/1701.01724v3.pdf | |
| PWC | https://paperswithcode.com/paper/deepstack-expert-level-artificial |
| Repo | https://github.com/lifrordi/DeepStack-Leduc |
| Framework | torch |
Quicksilver: Fast Predictive Image Registration - a Deep Learning Approach
| Title | Quicksilver: Fast Predictive Image Registration - a Deep Learning Approach |
| Authors | Xiao Yang, Roland Kwitt, Martin Styner, Marc Niethammer |
| Abstract | This paper introduces Quicksilver, a fast deformable image registration method. Quicksilver registration for image-pairs works by patch-wise prediction of a deformation model based directly on image appearance. A deep encoder-decoder network is used as the prediction model. While the prediction strategy is general, we focus on predictions for the Large Deformation Diffeomorphic Metric Mapping (LDDMM) model. Specifically, we predict the momentum-parameterization of LDDMM, which facilitates a patch-wise prediction strategy while maintaining the theoretical properties of LDDMM, such as guaranteed diffeomorphic mappings for sufficiently strong regularization. We also provide a probabilistic version of our prediction network which can be sampled during the testing time to calculate uncertainties in the predicted deformations. Finally, we introduce a new correction network which greatly increases the prediction accuracy of an already existing prediction network. We show experimental results for uni-modal atlas-to-image as well as uni- / multi- modal image-to-image registrations. These experiments demonstrate that our method accurately predicts registrations obtained by numerical optimization, is very fast, achieves state-of-the-art registration results on four standard validation datasets, and can jointly learn an image similarity measure. Quicksilver is freely available as an open-source software. |
| Tasks | Image Registration |
| Published | 2017-03-31 |
| URL | http://arxiv.org/abs/1703.10908v4 |
| http://arxiv.org/pdf/1703.10908v4.pdf | |
| PWC | https://paperswithcode.com/paper/quicksilver-fast-predictive-image |
| Repo | https://github.com/rkwitt/quicksilver |
| Framework | pytorch |
Simple and Effective Dimensionality Reduction for Word Embeddings
| Title | Simple and Effective Dimensionality Reduction for Word Embeddings |
| Authors | Vikas Raunak |
| Abstract | Word embeddings have become the basic building blocks for several natural language processing and information retrieval tasks. Pre-trained word embeddings are used in several downstream applications as well as for constructing representations for sentences, paragraphs and documents. Recently, there has been an emphasis on further improving the pre-trained word vectors through post-processing algorithms. One such area of improvement is the dimensionality reduction of the word embeddings. Reducing the size of word embeddings through dimensionality reduction can improve their utility in memory constrained devices, benefiting several real-world applications. In this work, we present a novel algorithm that effectively combines PCA based dimensionality reduction with a recently proposed post-processing algorithm, to construct word embeddings of lower dimensions. Empirical evaluations on 12 standard word similarity benchmarks show that our algorithm reduces the embedding dimensionality by 50%, while achieving similar or (more often) better performance than the higher dimension embeddings. |
| Tasks | Dimensionality Reduction, Information Retrieval, Word Embeddings |
| Published | 2017-08-11 |
| URL | http://arxiv.org/abs/1708.03629v3 |
| http://arxiv.org/pdf/1708.03629v3.pdf | |
| PWC | https://paperswithcode.com/paper/simple-and-effective-dimensionality-reduction |
| Repo | https://github.com/vyraun/Half-Size |
| Framework | none |
GPflowOpt: A Bayesian Optimization Library using TensorFlow
| Title | GPflowOpt: A Bayesian Optimization Library using TensorFlow |
| Authors | Nicolas Knudde, Joachim van der Herten, Tom Dhaene, Ivo Couckuyt |
| Abstract | A novel Python framework for Bayesian optimization known as GPflowOpt is introduced. The package is based on the popular GPflow library for Gaussian processes, leveraging the benefits of TensorFlow including automatic differentiation, parallelization and GPU computations for Bayesian optimization. Design goals focus on a framework that is easy to extend with custom acquisition functions and models. The framework is thoroughly tested and well documented, and provides scalability. The current released version of GPflowOpt includes some standard single-objective acquisition functions, the state-of-the-art max-value entropy search, as well as a Bayesian multi-objective approach. Finally, it permits easy use of custom modeling strategies implemented in GPflow. |
| Tasks | Gaussian Processes |
| Published | 2017-11-10 |
| URL | http://arxiv.org/abs/1711.03845v1 |
| http://arxiv.org/pdf/1711.03845v1.pdf | |
| PWC | https://paperswithcode.com/paper/gpflowopt-a-bayesian-optimization-library |
| Repo | https://github.com/yanpei18345156216/GPflowOpt |
| Framework | tf |
