Paper Group AWR 194
Efficient Policy Learning. Bayesian Optimization for Probabilistic Programs. Dendritic error backpropagation in deep cortical microcircuits. Reinforcement Learning with Deep Energy-Based Policies. Model Transfer for Tagging Low-resource Languages using a Bilingual Dictionary. A Comparison of Audio Signal Preprocessing Methods for Deep Neural Networ …
Efficient Policy Learning
| Title | Efficient Policy Learning |
| Authors | Susan Athey, Stefan Wager |
| Abstract | In many areas, practitioners seek to use observational data to learn a treatment assignment policy that satisfies application-specific constraints, such as budget, fairness, simplicity, or other functional form constraints. For example, policies may be restricted to take the form of decision trees based on a limited set of easily observable individual characteristics. We propose a new approach to this problem motivated by the theory of semiparametrically efficient estimation. Our method can be used to optimize either binary treatments or infinitesimal nudges to continuous treatments, and can leverage observational data where causal effects are identified using a variety of strategies, including selection on observables and instrumental variables. Given a doubly robust estimator of the causal effect of assigning everyone to treatment, we develop an algorithm for choosing whom to treat, and establish strong guarantees for the asymptotic utilitarian regret of the resulting policy. |
| Tasks | |
| Published | 2017-02-09 |
| URL | https://arxiv.org/abs/1702.02896v5 |
| https://arxiv.org/pdf/1702.02896v5.pdf | |
| PWC | https://paperswithcode.com/paper/efficient-policy-learning |
| Repo | https://github.com/grf-labs/policyTree |
| Framework | none |
Bayesian Optimization for Probabilistic Programs
| Title | Bayesian Optimization for Probabilistic Programs |
| Authors | Tom Rainforth, Tuan Anh Le, Jan-Willem van de Meent, Michael A. Osborne, Frank Wood |
| Abstract | We present the first general purpose framework for marginal maximum a posteriori estimation of probabilistic program variables. By using a series of code transformations, the evidence of any probabilistic program, and therefore of any graphical model, can be optimized with respect to an arbitrary subset of its sampled variables. To carry out this optimization, we develop the first Bayesian optimization package to directly exploit the source code of its target, leading to innovations in problem-independent hyperpriors, unbounded optimization, and implicit constraint satisfaction; delivering significant performance improvements over prominent existing packages. We present applications of our method to a number of tasks including engineering design and parameter optimization. |
| Tasks | |
| Published | 2017-07-13 |
| URL | http://arxiv.org/abs/1707.04314v1 |
| http://arxiv.org/pdf/1707.04314v1.pdf | |
| PWC | https://paperswithcode.com/paper/bayesian-optimization-for-probabilistic |
| Repo | https://github.com/probprog/bopp |
| Framework | none |
Dendritic error backpropagation in deep cortical microcircuits
| Title | Dendritic error backpropagation in deep cortical microcircuits |
| Authors | João Sacramento, Rui Ponte Costa, Yoshua Bengio, Walter Senn |
| Abstract | Animal behaviour depends on learning to associate sensory stimuli with the desired motor command. Understanding how the brain orchestrates the necessary synaptic modifications across different brain areas has remained a longstanding puzzle. Here, we introduce a multi-area neuronal network model in which synaptic plasticity continuously adapts the network towards a global desired output. In this model synaptic learning is driven by a local dendritic prediction error that arises from a failure to predict the top-down input given the bottom-up activities. Such errors occur at apical dendrites of pyramidal neurons where both long-range excitatory feedback and local inhibitory predictions are integrated. When local inhibition fails to match excitatory feedback an error occurs which triggers plasticity at bottom-up synapses at basal dendrites of the same pyramidal neurons. We demonstrate the learning capabilities of the model in a number of tasks and show that it approximates the classical error backpropagation algorithm. Finally, complementing this cortical circuit with a disinhibitory mechanism enables attention-like stimulus denoising and generation. Our framework makes several experimental predictions on the function of dendritic integration and cortical microcircuits, is consistent with recent observations of cross-area learning, and suggests a biological implementation of deep learning. |
| Tasks | Denoising |
| Published | 2017-12-30 |
| URL | http://arxiv.org/abs/1801.00062v1 |
| http://arxiv.org/pdf/1801.00062v1.pdf | |
| PWC | https://paperswithcode.com/paper/dendritic-error-backpropagation-in-deep |
| Repo | https://github.com/EntropicEffect/dendritic_backprop |
| Framework | pytorch |
Reinforcement Learning with Deep Energy-Based Policies
| Title | Reinforcement Learning with Deep Energy-Based Policies |
| Authors | Tuomas Haarnoja, Haoran Tang, Pieter Abbeel, Sergey Levine |
| Abstract | We propose a method for learning expressive energy-based policies for continuous states and actions, which has been feasible only in tabular domains before. We apply our method to learning maximum entropy policies, resulting into a new algorithm, called soft Q-learning, that expresses the optimal policy via a Boltzmann distribution. We use the recently proposed amortized Stein variational gradient descent to learn a stochastic sampling network that approximates samples from this distribution. The benefits of the proposed algorithm include improved exploration and compositionality that allows transferring skills between tasks, which we confirm in simulated experiments with swimming and walking robots. We also draw a connection to actor-critic methods, which can be viewed performing approximate inference on the corresponding energy-based model. |
| Tasks | Q-Learning |
| Published | 2017-02-27 |
| URL | http://arxiv.org/abs/1702.08165v2 |
| http://arxiv.org/pdf/1702.08165v2.pdf | |
| PWC | https://paperswithcode.com/paper/reinforcement-learning-with-deep-energy-based |
| Repo | https://github.com/shakedzy/gin |
| Framework | none |
Model Transfer for Tagging Low-resource Languages using a Bilingual Dictionary
| Title | Model Transfer for Tagging Low-resource Languages using a Bilingual Dictionary |
| Authors | Meng Fang, Trevor Cohn |
| Abstract | Cross-lingual model transfer is a compelling and popular method for predicting annotations in a low-resource language, whereby parallel corpora provide a bridge to a high-resource language and its associated annotated corpora. However, parallel data is not readily available for many languages, limiting the applicability of these approaches. We address these drawbacks in our framework which takes advantage of cross-lingual word embeddings trained solely on a high coverage bilingual dictionary. We propose a novel neural network model for joint training from both sources of data based on cross-lingual word embeddings, and show substantial empirical improvements over baseline techniques. We also propose several active learning heuristics, which result in improvements over competitive benchmark methods. |
| Tasks | Active Learning, Word Embeddings |
| Published | 2017-05-01 |
| URL | http://arxiv.org/abs/1705.00424v1 |
| http://arxiv.org/pdf/1705.00424v1.pdf | |
| PWC | https://paperswithcode.com/paper/model-transfer-for-tagging-low-resource |
| Repo | https://github.com/mengf1/trpos |
| Framework | none |
A Comparison of Audio Signal Preprocessing Methods for Deep Neural Networks on Music Tagging
| Title | A Comparison of Audio Signal Preprocessing Methods for Deep Neural Networks on Music Tagging |
| Authors | Keunwoo Choi, György Fazekas, Kyunghyun Cho, Mark Sandler |
| Abstract | In this paper, we empirically investigate the effect of audio preprocessing on music tagging with deep neural networks. We perform comprehensive experiments involving audio preprocessing using different time-frequency representations, logarithmic magnitude compression, frequency weighting, and scaling. We show that many commonly used input preprocessing techniques are redundant except magnitude compression. |
| Tasks | |
| Published | 2017-09-06 |
| URL | http://arxiv.org/abs/1709.01922v2 |
| http://arxiv.org/pdf/1709.01922v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-comparison-of-audio-signal-preprocessing |
| Repo | https://github.com/GorillaBus/urban-audio-classifier |
| Framework | tf |
liquidSVM: A Fast and Versatile SVM package
| Title | liquidSVM: A Fast and Versatile SVM package |
| Authors | Ingo Steinwart, Philipp Thomann |
| Abstract | liquidSVM is a package written in C++ that provides SVM-type solvers for various classification and regression tasks. Because of a fully integrated hyper-parameter selection, very carefully implemented solvers, multi-threading and GPU support, and several built-in data decomposition strategies it provides unprecedented speed for small training sizes as well as for data sets of tens of millions of samples. Besides the C++ API and a command line interface, bindings to R, MATLAB, Java, Python, and Spark are available. We present a brief description of the package and report experimental comparisons to other SVM packages. |
| Tasks | |
| Published | 2017-02-22 |
| URL | http://arxiv.org/abs/1702.06899v1 |
| http://arxiv.org/pdf/1702.06899v1.pdf | |
| PWC | https://paperswithcode.com/paper/liquidsvm-a-fast-and-versatile-svm-package |
| Repo | https://github.com/liquidSVM/liquidSVM |
| Framework | none |
PL-SLAM: a Stereo SLAM System through the Combination of Points and Line Segments
| Title | PL-SLAM: a Stereo SLAM System through the Combination of Points and Line Segments |
| Authors | Ruben Gomez-Ojeda, David Zuñiga-Noël, Francisco-Angel Moreno, Davide Scaramuzza, Javier Gonzalez-Jimenez |
| Abstract | Traditional approaches to stereo visual SLAM rely on point features to estimate the camera trajectory and build a map of the environment. In low-textured environments, though, it is often difficult to find a sufficient number of reliable point features and, as a consequence, the performance of such algorithms degrades. This paper proposes PL-SLAM, a stereo visual SLAM system that combines both points and line segments to work robustly in a wider variety of scenarios, particularly in those where point features are scarce or not well-distributed in the image. PL-SLAM leverages both points and segments at all the instances of the process: visual odometry, keyframe selection, bundle adjustment, etc. We contribute also with a loop closure procedure through a novel bag-of-words approach that exploits the combined descriptive power of the two kinds of features. Additionally, the resulting map is richer and more diverse in 3D elements, which can be exploited to infer valuable, high-level scene structures like planes, empty spaces, ground plane, etc. (not addressed in this work). Our proposal has been tested with several popular datasets (such as KITTI and EuRoC), and is compared to state of the art methods like ORB-SLAM, revealing a more robust performance in most of the experiments, while still running in real-time. An open source version of the PL-SLAM C++ code will be released for the benefit of the community. |
| Tasks | Visual Odometry |
| Published | 2017-05-26 |
| URL | http://arxiv.org/abs/1705.09479v2 |
| http://arxiv.org/pdf/1705.09479v2.pdf | |
| PWC | https://paperswithcode.com/paper/pl-slam-a-stereo-slam-system-through-the |
| Repo | https://github.com/rubengooj/pl-slam |
| Framework | none |
Fully Automatic and Real-Time Catheter Segmentation in X-Ray Fluoroscopy
| Title | Fully Automatic and Real-Time Catheter Segmentation in X-Ray Fluoroscopy |
| Authors | Pierre Ambrosini, Daniel Ruijters, Wiro J. Niessen, Adriaan Moelker, Theo van Walsum |
| Abstract | Augmenting X-ray imaging with 3D roadmap to improve guidance is a common strategy. Such approaches benefit from automated analysis of the X-ray images, such as the automatic detection and tracking of instruments. In this paper, we propose a real-time method to segment the catheter and guidewire in 2D X-ray fluoroscopic sequences. The method is based on deep convolutional neural networks. The network takes as input the current image and the three previous ones, and segments the catheter and guidewire in the current image. Subsequently, a centerline model of the catheter is constructed from the segmented image. A small set of annotated data combined with data augmentation is used to train the network. We trained the method on images from 182 X-ray sequences from 23 different interventions. On a testing set with images of 55 X-ray sequences from 5 other interventions, a median centerline distance error of 0.2 mm and a median tip distance error of 0.9 mm was obtained. The segmentation of the instruments in 2D X-ray sequences is performed in a real-time fully-automatic manner. |
| Tasks | Data Augmentation |
| Published | 2017-07-17 |
| URL | http://arxiv.org/abs/1707.05137v1 |
| http://arxiv.org/pdf/1707.05137v1.pdf | |
| PWC | https://paperswithcode.com/paper/fully-automatic-and-real-time-catheter |
| Repo | https://github.com/pambros/CNN-2D-X-Ray-Catheter-Detection |
| Framework | tf |
Co-attending Free-form Regions and Detections with Multi-modal Multiplicative Feature Embedding for Visual Question Answering
| Title | Co-attending Free-form Regions and Detections with Multi-modal Multiplicative Feature Embedding for Visual Question Answering |
| Authors | Pan Lu, Hongsheng Li, Wei Zhang, Jianyong Wang, Xiaogang Wang |
| Abstract | Recently, the Visual Question Answering (VQA) task has gained increasing attention in artificial intelligence. Existing VQA methods mainly adopt the visual attention mechanism to associate the input question with corresponding image regions for effective question answering. The free-form region based and the detection-based visual attention mechanisms are mostly investigated, with the former ones attending free-form image regions and the latter ones attending pre-specified detection-box regions. We argue that the two attention mechanisms are able to provide complementary information and should be effectively integrated to better solve the VQA problem. In this paper, we propose a novel deep neural network for VQA that integrates both attention mechanisms. Our proposed framework effectively fuses features from free-form image regions, detection boxes, and question representations via a multi-modal multiplicative feature embedding scheme to jointly attend question-related free-form image regions and detection boxes for more accurate question answering. The proposed method is extensively evaluated on two publicly available datasets, COCO-QA and VQA, and outperforms state-of-the-art approaches. Source code is available at https://github.com/lupantech/dual-mfa-vqa. |
| Tasks | Visual Question Answering |
| Published | 2017-11-18 |
| URL | http://arxiv.org/abs/1711.06794v2 |
| http://arxiv.org/pdf/1711.06794v2.pdf | |
| PWC | https://paperswithcode.com/paper/co-attending-free-form-regions-and-detections |
| Repo | https://github.com/lupantech/dual-mfa-vqa |
| Framework | torch |
Simultaneous Recognition and Pose Estimation of Instruments in Minimally Invasive Surgery
| Title | Simultaneous Recognition and Pose Estimation of Instruments in Minimally Invasive Surgery |
| Authors | Thomas Kurmann, Pablo Marquez Neila, Xiaofei Du, Pascal Fua, Danail Stoyanov, Sebastian Wolf, Raphael Sznitman |
| Abstract | Detection of surgical instruments plays a key role in ensuring patient safety in minimally invasive surgery. In this paper, we present a novel method for 2D vision-based recognition and pose estimation of surgical instruments that generalizes to different surgical applications. At its core, we propose a novel scene model in order to simultaneously recognize multiple instruments as well as their parts. We use a Convolutional Neural Network architecture to embody our model and show that the cross-entropy loss is well suited to optimize its parameters which can be trained in an end-to-end fashion. An additional advantage of our approach is that instrument detection at test time is achieved while avoiding the need for scale-dependent sliding window evaluation. This allows our approach to be relatively parameter free at test time and shows good performance for both instrument detection and tracking. We show that our approach surpasses state-of-the-art results on in-vivo retinal microsurgery image data, as well as ex-vivo laparoscopic sequences. |
| Tasks | Pose Estimation |
| Published | 2017-10-18 |
| URL | http://arxiv.org/abs/1710.06668v1 |
| http://arxiv.org/pdf/1710.06668v1.pdf | |
| PWC | https://paperswithcode.com/paper/simultaneous-recognition-and-pose-estimation |
| Repo | https://github.com/otl-artorg/instrument-pose |
| Framework | tf |
Letter-Based Speech Recognition with Gated ConvNets
| Title | Letter-Based Speech Recognition with Gated ConvNets |
| Authors | Vitaliy Liptchinsky, Gabriel Synnaeve, Ronan Collobert |
| Abstract | In the recent literature, “end-to-end” speech systems often refer to letter-based acoustic models trained in a sequence-to-sequence manner, either via a recurrent model or via a structured output learning approach (such as CTC). In contrast to traditional phone (or senone)-based approaches, these “end-to-end’’ approaches alleviate the need of word pronunciation modeling, and do not require a “forced alignment” step at training time. Phone-based approaches remain however state of the art on classical benchmarks. In this paper, we propose a letter-based speech recognition system, leveraging a ConvNet acoustic model. Key ingredients of the ConvNet are Gated Linear Units and high dropout. The ConvNet is trained to map audio sequences to their corresponding letter transcriptions, either via a classical CTC approach, or via a recent variant called ASG. Coupled with a simple decoder at inference time, our system matches the best existing letter-based systems on WSJ (in word error rate), and shows near state of the art performance on LibriSpeech. |
| Tasks | Language Modelling, Speech Recognition |
| Published | 2017-12-22 |
| URL | http://arxiv.org/abs/1712.09444v2 |
| http://arxiv.org/pdf/1712.09444v2.pdf | |
| PWC | https://paperswithcode.com/paper/letter-based-speech-recognition-with-gated |
| Repo | https://github.com/MrMao/wav2letter |
| Framework | torch |
Virtual-to-real Deep Reinforcement Learning: Continuous Control of Mobile Robots for Mapless Navigation
| Title | Virtual-to-real Deep Reinforcement Learning: Continuous Control of Mobile Robots for Mapless Navigation |
| Authors | Lei Tai, Giuseppe Paolo, Ming Liu |
| Abstract | We present a learning-based mapless motion planner by taking the sparse 10-dimensional range findings and the target position with respect to the mobile robot coordinate frame as input and the continuous steering commands as output. Traditional motion planners for mobile ground robots with a laser range sensor mostly depend on the obstacle map of the navigation environment where both the highly precise laser sensor and the obstacle map building work of the environment are indispensable. We show that, through an asynchronous deep reinforcement learning method, a mapless motion planner can be trained end-to-end without any manually designed features and prior demonstrations. The trained planner can be directly applied in unseen virtual and real environments. The experiments show that the proposed mapless motion planner can navigate the nonholonomic mobile robot to the desired targets without colliding with any obstacles. |
| Tasks | Continuous Control |
| Published | 2017-03-01 |
| URL | http://arxiv.org/abs/1703.00420v4 |
| http://arxiv.org/pdf/1703.00420v4.pdf | |
| PWC | https://paperswithcode.com/paper/virtual-to-real-deep-reinforcement-learning |
| Repo | https://github.com/m5823779/DDPG |
| Framework | tf |
Ask Me Even More: Dynamic Memory Tensor Networks (Extended Model)
| Title | Ask Me Even More: Dynamic Memory Tensor Networks (Extended Model) |
| Authors | Govardana Sachithanandam Ramachandran, Ajay Sohmshetty |
| Abstract | We examine Memory Networks for the task of question answering (QA), under common real world scenario where training examples are scarce and under weakly supervised scenario, that is only extrinsic labels are available for training. We propose extensions for the Dynamic Memory Network (DMN), specifically within the attention mechanism, we call the resulting Neural Architecture as Dynamic Memory Tensor Network (DMTN). Ultimately, we see that our proposed extensions results in over 80% improvement in the number of task passed against the baselined standard DMN and 20% more task passed compared to state-of-the-art End-to-End Memory Network for Facebook’s single task weakly trained 1K bAbi dataset. |
| Tasks | Question Answering, Tensor Networks |
| Published | 2017-03-11 |
| URL | http://arxiv.org/abs/1703.03939v1 |
| http://arxiv.org/pdf/1703.03939v1.pdf | |
| PWC | https://paperswithcode.com/paper/ask-me-even-more-dynamic-memory-tensor |
| Repo | https://github.com/rgsachin/DMTN |
| Framework | none |
Provable Dynamic Robust PCA or Robust Subspace Tracking
| Title | Provable Dynamic Robust PCA or Robust Subspace Tracking |
| Authors | Praneeth Narayanamurthy, Namrata Vaswani |
| Abstract | Dynamic robust PCA refers to the dynamic (time-varying) extension of robust PCA (RPCA). It assumes that the true (uncorrupted) data lies in a low-dimensional subspace that can change with time, albeit slowly. The goal is to track this changing subspace over time in the presence of sparse outliers. We develop and study a novel algorithm, that we call simple-ReProCS, based on the recently introduced Recursive Projected Compressive Sensing (ReProCS) framework. Our work provides the first guarantee for dynamic RPCA that holds under weakened versions of standard RPCA assumptions, slow subspace change and a lower bound assumption on most outlier magnitudes. Our result is significant because (i) it removes the strong assumptions needed by the two previous complete guarantees for ReProCS-based algorithms; (ii) it shows that it is possible to achieve significantly improved outlier tolerance, compared with all existing RPCA or dynamic RPCA solutions by exploiting the above two simple extra assumptions; and (iii) it proves that simple-ReProCS is online (after initialization), fast, and, has near-optimal memory complexity. |
| Tasks | Compressive Sensing |
| Published | 2017-05-24 |
| URL | http://arxiv.org/abs/1705.08948v4 |
| http://arxiv.org/pdf/1705.08948v4.pdf | |
| PWC | https://paperswithcode.com/paper/provable-dynamic-robust-pca-or-robust |
| Repo | https://github.com/andrewssobral/lrslibrary |
| Framework | none |
