Paper Group ANR 311
Coupled Longitudinal and Lateral Control of a Vehicle using Deep Learning. Large-Scale Video Classification with Feature Space Augmentation coupled with Learned Label Relations and Ensembling. High-dimensional Penalty Selection via Minimum Description Length Principle. Generating retinal flow maps from structural optical coherence tomography with a …
Coupled Longitudinal and Lateral Control of a Vehicle using Deep Learning
Title | Coupled Longitudinal and Lateral Control of a Vehicle using Deep Learning |
Authors | Guillaume Devineau, Philip Polack, Florent Altché, Fabien Moutarde |
Abstract | This paper explores the capability of deep neural networks to capture key characteristics of vehicle dynamics, and their ability to perform coupled longitudinal and lateral control of a vehicle. To this extent, two different artificial neural networks are trained to compute vehicle controls corresponding to a reference trajectory, using a dataset based on high-fidelity simulations of vehicle dynamics. In this study, control inputs are chosen as the steering angle of the front wheels, and the applied torque on each wheel. The performance of both models, namely a Multi-Layer Perceptron (MLP) and a Convolutional Neural Network (CNN), is evaluated based on their ability to drive the vehicle on a challenging test track, shifting between long straight lines and tight curves. A comparison to conventional decoupled controllers on the same track is also provided. |
Tasks | |
Published | 2018-10-22 |
URL | http://arxiv.org/abs/1810.09365v1 |
http://arxiv.org/pdf/1810.09365v1.pdf | |
PWC | https://paperswithcode.com/paper/coupled-longitudinal-and-lateral-control-of-a |
Repo | |
Framework | |
Large-Scale Video Classification with Feature Space Augmentation coupled with Learned Label Relations and Ensembling
Title | Large-Scale Video Classification with Feature Space Augmentation coupled with Learned Label Relations and Ensembling |
Authors | Choongyeun Cho, Benjamin Antin, Sanchit Arora, Shwan Ashrafi, Peilin Duan, Dang The Huynh, Lee James, Hang Tuan Nguyen, Mojtaba Solgi, Cuong Van Than |
Abstract | This paper presents the Axon AI’s solution to the 2nd YouTube-8M Video Understanding Challenge, achieving the final global average precision (GAP) of 88.733% on the private test set (ranked 3rd among 394 teams, not considering the model size constraint), and 87.287% using a model that meets size requirement. Two sets of 7 individual models belonging to 3 different families were trained separately. Then, the inference results on a training data were aggregated from these multiple models and fed to train a compact model that meets the model size requirement. In order to further improve performance we explored and employed data over/sub-sampling in feature space, an additional regularization term during training exploiting label relationship, and learned weights for ensembling different individual models. |
Tasks | Video Classification, Video Understanding |
Published | 2018-09-21 |
URL | http://arxiv.org/abs/1809.07895v1 |
http://arxiv.org/pdf/1809.07895v1.pdf | |
PWC | https://paperswithcode.com/paper/large-scale-video-classification-with-feature |
Repo | |
Framework | |
High-dimensional Penalty Selection via Minimum Description Length Principle
Title | High-dimensional Penalty Selection via Minimum Description Length Principle |
Authors | Kohei Miyaguchi, Kenji Yamanishi |
Abstract | We tackle the problem of penalty selection of regularization on the basis of the minimum description length (MDL) principle. In particular, we consider that the design space of the penalty function is high-dimensional. In this situation, the luckiness-normalized-maximum-likelihood(LNML)-minimization approach is favorable, because LNML quantifies the goodness of regularized models with any forms of penalty functions in view of the minimum description length principle, and guides us to a good penalty function through the high-dimensional space. However, the minimization of LNML entails two major challenges: 1) the computation of the normalizing factor of LNML and 2) its minimization in high-dimensional spaces. In this paper, we present a novel regularization selection method (MDL-RS), in which a tight upper bound of LNML (uLNML) is minimized with local convergence guarantee. Our main contribution is the derivation of uLNML, which is a uniform-gap upper bound of LNML in an analytic expression. This solves the above challenges in an approximate manner because it allows us to accurately approximate LNML and then efficiently minimize it. The experimental results show that MDL-RS improves the generalization performance of regularized estimates specifically when the model has redundant parameters. |
Tasks | |
Published | 2018-04-26 |
URL | http://arxiv.org/abs/1804.09904v1 |
http://arxiv.org/pdf/1804.09904v1.pdf | |
PWC | https://paperswithcode.com/paper/high-dimensional-penalty-selection-via |
Repo | |
Framework | |
Generating retinal flow maps from structural optical coherence tomography with artificial intelligence
Title | Generating retinal flow maps from structural optical coherence tomography with artificial intelligence |
Authors | Cecilia S. Lee, Ariel J. Tyring, Yue Wu, Sa Xiao, Ariel S. Rokem, Nicolaas P. Deruyter, Qinqin Zhang, Adnan Tufail, Ruikang K. Wang, Aaron Y. Lee |
Abstract | Despite significant advances in artificial intelligence (AI) for computer vision, its application in medical imaging has been limited by the burden and limits of expert-generated labels. We used images from optical coherence tomography angiography (OCTA), a relatively new imaging modality that measures perfusion of the retinal vasculature, to train an AI algorithm to generate vasculature maps from standard structural optical coherence tomography (OCT) images of the same retinae, both exceeding the ability and bypassing the need for expert labeling. Deep learning was able to infer perfusion of microvasculature from structural OCT images with similar fidelity to OCTA and significantly better than expert clinicians (P < 0.00001). OCTA suffers from need of specialized hardware, laborious acquisition protocols, and motion artifacts; whereas our model works directly from standard OCT which are ubiquitous and quick to obtain, and allows unlocking of large volumes of previously collected standard OCT data both in existing clinical trials and clinical practice. This finding demonstrates a novel application of AI to medical imaging, whereby subtle regularities between different modalities are used to image the same body part and AI is used to generate detailed and accurate inferences of tissue function from structure imaging. |
Tasks | |
Published | 2018-02-24 |
URL | http://arxiv.org/abs/1802.08925v1 |
http://arxiv.org/pdf/1802.08925v1.pdf | |
PWC | https://paperswithcode.com/paper/generating-retinal-flow-maps-from-structural |
Repo | |
Framework | |
Bayesian functional optimisation with shape prior
Title | Bayesian functional optimisation with shape prior |
Authors | Pratibha Vellanki, Santu Rana, Sunil Gupta, David Rubin de Celis Leal, Alessandra Sutti, Murray Height, Svetha Venkatesh |
Abstract | Real world experiments are expensive, and thus it is important to reach a target in minimum number of experiments. Experimental processes often involve control variables that changes over time. Such problems can be formulated as a functional optimisation problem. We develop a novel Bayesian optimisation framework for such functional optimisation of expensive black-box processes. We represent the control function using Bernstein polynomial basis and optimise in the coefficient space. We derive the theory and practice required to dynamically adjust the order of the polynomial degree, and show how prior information about shape can be integrated. We demonstrate the effectiveness of our approach for short polymer fibre design and optimising learning rate schedules for deep networks. |
Tasks | Bayesian Optimisation |
Published | 2018-09-19 |
URL | https://arxiv.org/abs/1809.07260v2 |
https://arxiv.org/pdf/1809.07260v2.pdf | |
PWC | https://paperswithcode.com/paper/bayesian-functional-optimisation-with-shape |
Repo | |
Framework | |
Fingerprint Policy Optimisation for Robust Reinforcement Learning
Title | Fingerprint Policy Optimisation for Robust Reinforcement Learning |
Authors | Supratik Paul, Michael A. Osborne, Shimon Whiteson |
Abstract | Policy gradient methods ignore the potential value of adjusting environment variables: unobservable state features that are randomly determined by the environment in a physical setting, but are controllable in a simulator. This can lead to slow learning, or convergence to suboptimal policies, if the environment variable has a large impact on the transition dynamics. In this paper, we present fingerprint policy optimisation (FPO), which finds a policy that is optimal in expectation across the distribution of environment variables. The central idea is to use Bayesian optimisation (BO) to actively select the distribution of the environment variable that maximises the improvement generated by each iteration of the policy gradient method. To make this BO practical, we contribute two easy-to-compute low-dimensional fingerprints of the current policy. Our experiments show that FPO can efficiently learn policies that are robust to significant rare events, which are unlikely to be observable under random sampling, but are key to learning good policies. |
Tasks | Bayesian Optimisation, Continuous Control, Policy Gradient Methods |
Published | 2018-05-27 |
URL | https://arxiv.org/abs/1805.10662v3 |
https://arxiv.org/pdf/1805.10662v3.pdf | |
PWC | https://paperswithcode.com/paper/fingerprint-policy-optimisation-for-robust |
Repo | |
Framework | |
Towards Good Practices for Multi-modal Fusion in Large-scale Video Classification
Title | Towards Good Practices for Multi-modal Fusion in Large-scale Video Classification |
Authors | Jinlai Liu, Zehuan Yuan, Changhu Wang |
Abstract | Leveraging both visual frames and audio has been experimentally proven effective to improve large-scale video classification. Previous research on video classification mainly focuses on the analysis of visual content among extracted video frames and their temporal feature aggregation. In contrast, multimodal data fusion is achieved by simple operators like average and concatenation. Inspired by the success of bilinear pooling in the visual and language fusion, we introduce multi-modal factorized bilinear pooling (MFB) to fuse visual and audio representations. We combine MFB with different video-level features and explore its effectiveness in video classification. Experimental results on the challenging Youtube-8M v2 dataset demonstrate that MFB significantly outperforms simple fusion methods in large-scale video classification. |
Tasks | Video Classification |
Published | 2018-09-16 |
URL | http://arxiv.org/abs/1809.05848v4 |
http://arxiv.org/pdf/1809.05848v4.pdf | |
PWC | https://paperswithcode.com/paper/towards-good-practices-for-multi-modal-fusion |
Repo | |
Framework | |
Distributed Simulation and Distributed Inference
Title | Distributed Simulation and Distributed Inference |
Authors | Jayadev Acharya, Clément L. Canonne, Himanshu Tyagi |
Abstract | Independent samples from an unknown probability distribution $\bf p$ on a domain of size $k$ are distributed across $n$ players, with each player holding one sample. Each player can communicate $\ell$ bits to a central referee in a simultaneous message passing model of communication to help the referee infer a property of the unknown $\bf p$. What is the least number of players for inference required in the communication-starved setting of $\ell<\log k$? We begin by exploring a general “simulate-and-infer” strategy for such inference problems where the center simulates the desired number of samples from the unknown distribution and applies standard inference algorithms for the collocated setting. Our first result shows that for $\ell<\log k$ perfect simulation of even a single sample is not possible. Nonetheless, we present a Las Vegas algorithm that simulates a single sample from the unknown distribution using $O(k/2^\ell)$ samples in expectation. As an immediate corollary, we get that simulate-and-infer attains the optimal sample complexity of $\Theta(k^2/2^\ell\epsilon^2)$ for learning the unknown distribution to total variation distance $\epsilon$. For the prototypical testing problem of identity testing, simulate-and-infer works with $O(k^{3/2}/2^\ell\epsilon^2)$ samples, a requirement that seems to be inherent for all communication protocols not using any additional resources. Interestingly, we can break this barrier using public coins. Specifically, we exhibit a public-coin communication protocol that performs identity testing using $O(k/\sqrt{2^\ell}\epsilon^2)$ samples. Furthermore, we show that this is optimal up to constant factors. Our theoretically sample-optimal protocol is easy to implement in practice. Our proof of lower bound entails showing a contraction in $\chi^2$ distance of product distributions due to communication constraints and may be of independent interest. |
Tasks | |
Published | 2018-04-19 |
URL | https://arxiv.org/abs/1804.06952v3 |
https://arxiv.org/pdf/1804.06952v3.pdf | |
PWC | https://paperswithcode.com/paper/distributed-simulation-and-distributed |
Repo | |
Framework | |
A novel methodology on distributed representations of proteins using their interacting ligands
Title | A novel methodology on distributed representations of proteins using their interacting ligands |
Authors | Hakime Öztürk, Elif Ozkirimli, Arzucan Özgür |
Abstract | The effective representation of proteins is a crucial task that directly affects the performance of many bioinformatics problems. Related proteins usually bind to similar ligands. Chemical characteristics of ligands are known to capture the functional and mechanistic properties of proteins suggesting that a ligand based approach can be utilized in protein representation. In this study, we propose SMILESVec, a SMILES-based method to represent ligands and a novel method to compute similarity of proteins by describing them based on their ligands. The proteins are defined utilizing the word-embeddings of the SMILES strings of their ligands. The performance of the proposed protein description method is evaluated in protein clustering task using TransClust and MCL algorithms. Two other protein representation methods that utilize protein sequence, BLAST and ProtVec, and two compound fingerprint based protein representation methods are compared. We showed that ligand-based protein representation, which uses only SMILES strings of the ligands that proteins bind to, performs as well as protein-sequence based representation methods in protein clustering. The results suggest that ligand-based protein description can be an alternative to the traditional sequence or structure based representation of proteins and this novel approach can be applied to different bioinformatics problems such as prediction of new protein-ligand interactions and protein function annotation. |
Tasks | Word Embeddings |
Published | 2018-01-30 |
URL | http://arxiv.org/abs/1801.10199v1 |
http://arxiv.org/pdf/1801.10199v1.pdf | |
PWC | https://paperswithcode.com/paper/a-novel-methodology-on-distributed |
Repo | |
Framework | |
Gradient-based Sampling: An Adaptive Importance Sampling for Least-squares
Title | Gradient-based Sampling: An Adaptive Importance Sampling for Least-squares |
Authors | Rong Zhu |
Abstract | In modern data analysis, random sampling is an efficient and widely-used strategy to overcome the computational difficulties brought by large sample size. In previous studies, researchers conducted random sampling which is according to the input data but independent on the response variable, however the response variable may also be informative for sampling. In this paper we propose an adaptive sampling called the gradient-based sampling which is dependent on both the input data and the output for fast solving of least-square (LS) problems. We draw the data points by random sampling from the full data according to their gradient values. This sampling is computationally saving, since the running time of computing the sampling probabilities is reduced to O(nd) where n is the full sample size and d is the dimension of the input. Theoretically, we establish an error bound analysis of the general importance sampling with respect to LS solution from full data. The result establishes an improved performance of the use of our gradient- based sampling. Synthetic and real data sets are used to empirically argue that the gradient-based sampling has an obvious advantage over existing sampling methods from two aspects of statistical efficiency and computational saving. |
Tasks | |
Published | 2018-03-02 |
URL | http://arxiv.org/abs/1803.00841v1 |
http://arxiv.org/pdf/1803.00841v1.pdf | |
PWC | https://paperswithcode.com/paper/gradient-based-sampling-an-adaptive |
Repo | |
Framework | |
Towards a more flexible Language of Thought: Bayesian grammar updates after each concept exposure
Title | Towards a more flexible Language of Thought: Bayesian grammar updates after each concept exposure |
Authors | Pablo Tano, Sergio Romano, Mariano Sigman, Alejo Salles, Santiago Figueira |
Abstract | Recent approaches to human concept learning have successfully combined the power of symbolic, infinitely productive rule systems and statistical learning to explain our ability to learn new concepts from just a few examples. The aim of most of these studies is to reveal the underlying language structuring these representations and providing a general substrate for thought. However, describing a model of thought that is fixed once trained is against the extensive literature that shows how experience shapes concept learning. Here, we ask about the plasticity of these symbolic descriptive languages. We perform a concept learning experiment that demonstrates that humans can change very rapidly the repertoire of symbols they use to identify concepts, by compiling expressions which are frequently used into new symbols of the language. The pattern of concept learning times is accurately described by a Bayesian agent that rationally updates the probability of compiling a new expression according to how useful it has been to compress concepts so far. By portraying the Language of Thought as a flexible system of rules, we also highlight the difficulties to pin it down empirically. |
Tasks | |
Published | 2018-05-17 |
URL | https://arxiv.org/abs/1805.06924v2 |
https://arxiv.org/pdf/1805.06924v2.pdf | |
PWC | https://paperswithcode.com/paper/learning-is-compiling-experience-shapes |
Repo | |
Framework | |
Zero-Shot Object Detection
Title | Zero-Shot Object Detection |
Authors | Ankan Bansal, Karan Sikka, Gaurav Sharma, Rama Chellappa, Ajay Divakaran |
Abstract | We introduce and tackle the problem of zero-shot object detection (ZSD), which aims to detect object classes which are not observed during training. We work with a challenging set of object classes, not restricting ourselves to similar and/or fine-grained categories as in prior works on zero-shot classification. We present a principled approach by first adapting visual-semantic embeddings for ZSD. We then discuss the problems associated with selecting a background class and motivate two background-aware approaches for learning robust detectors. One of these models uses a fixed background class and the other is based on iterative latent assignments. We also outline the challenge associated with using a limited number of training classes and propose a solution based on dense sampling of the semantic label space using auxiliary data with a large number of categories. We propose novel splits of two standard detection datasets - MSCOCO and VisualGenome, and present extensive empirical results in both the traditional and generalized zero-shot settings to highlight the benefits of the proposed methods. We provide useful insights into the algorithm and conclude by posing some open questions to encourage further research. |
Tasks | Object Detection, Zero-Shot Learning, Zero-Shot Object Detection |
Published | 2018-04-12 |
URL | http://arxiv.org/abs/1804.04340v2 |
http://arxiv.org/pdf/1804.04340v2.pdf | |
PWC | https://paperswithcode.com/paper/zero-shot-object-detection |
Repo | |
Framework | |
Recurrent World Models Facilitate Policy Evolution
Title | Recurrent World Models Facilitate Policy Evolution |
Authors | David Ha, Jürgen Schmidhuber |
Abstract | A generative recurrent neural network is quickly trained in an unsupervised manner to model popular reinforcement learning environments through compressed spatio-temporal representations. The world model’s extracted features are fed into compact and simple policies trained by evolution, achieving state of the art results in various environments. We also train our agent entirely inside of an environment generated by its own internal world model, and transfer this policy back into the actual environment. Interactive version of paper at https://worldmodels.github.io |
Tasks | |
Published | 2018-09-04 |
URL | http://arxiv.org/abs/1809.01999v1 |
http://arxiv.org/pdf/1809.01999v1.pdf | |
PWC | https://paperswithcode.com/paper/recurrent-world-models-facilitate-policy |
Repo | |
Framework | |
Attenuate Locally, Win Globally: An Attenuation-based Framework for Online Stochastic Matching with Timeouts
Title | Attenuate Locally, Win Globally: An Attenuation-based Framework for Online Stochastic Matching with Timeouts |
Authors | Brian Brubach, Karthik Abinav Sankararaman, Aravind Srinivasan, Pan Xu |
Abstract | Online matching problems have garnered significant attention in recent years due to numerous applications in e-commerce, online advertisements, ride-sharing, etc. Many of them capture the uncertainty in the real world by including stochasticity in both the arrival process and the matching process. The Online Stochastic Matching with Timeouts problem introduced by Bansal, et al., (Algorithmica, 2012) models matching markets (e.g., E-Bay, Amazon). Buyers arrive from an independent and identically distributed (i.i.d.) known distribution on buyer profiles and can be shown a list of items one at a time. Each buyer has some probability of purchasing each item and a limit (timeout) on the number of items they can be shown. Bansal et al., (Algorithmica, 2012) gave a 0.12-competitive algorithm which was improved by Adamczyk, et al., (ESA, 2015) to 0.24. We present an online attenuation framework that uses an algorithm for offline stochastic matching as a black box. On the upper bound side, we show that this framework, combined with a black-box adapted from Bansal et al., (Algorithmica, 2012), yields an online algorithm which nearly doubles the ratio to 0.46. On the lower bound side, we show that no algorithm can achieve a ratio better than 0.632 using the standard LP for this problem. This framework has a high potential for further improvements since new algorithms for offline stochastic matching can directly improve the ratio for the online problem. Our online framework also has the potential for a variety of extensions. For example, we introduce a natural generalization: Online Stochastic Matching with Two-sided Timeouts in which both online and offline vertices have timeouts. Our framework provides the first algorithm for this problem achieving a ratio of 0.30. We once again use the algorithm of Adamczyk et al., (ESA, 2015) as a black-box and plug-it into our framework. |
Tasks | |
Published | 2018-04-22 |
URL | https://arxiv.org/abs/1804.08062v2 |
https://arxiv.org/pdf/1804.08062v2.pdf | |
PWC | https://paperswithcode.com/paper/attenuate-locally-win-globally-an-attenuation |
Repo | |
Framework | |
Exploiting statistical dependencies of time series with hierarchical correlation reconstruction
Title | Exploiting statistical dependencies of time series with hierarchical correlation reconstruction |
Authors | Jarek Duda |
Abstract | While we are usually focused on forecasting future values of time series, it is often valuable to additionally predict their entire probability distributions, e.g. to evaluate risk, Monte Carlo simulations. On example of time series of $\approx$ 30000 Dow Jones Industrial Averages, there will be presented application of hierarchical correlation reconstruction for this purpose: MSE estimating polynomial as joint density for (current value, context), where context is for example a few previous values. Then substituting the currently observed context and normalizing density to 1, we get predicted probability distribution for the current value. In contrast to standard machine learning approaches like neural networks, optimal polynomial coefficients here have inexpensive direct formula, have controllable accuracy, are unique and independently calculated, each has a specific cumulant-like interpretation, and such approximation can asymptotically approach complete description of any real joint distribution - providing universal tool to quantitatively describe and exploit statistical dependencies in time series, systematically enhancing ARMA/ARCH-like approaches, also based on different distributions than Gaussian which turns out improper for daily log returns. There is also discussed application for non-stationary time series like calculating linear time trend, or adapting coefficients to local statistical behavior. |
Tasks | Time Series |
Published | 2018-07-11 |
URL | http://arxiv.org/abs/1807.04119v5 |
http://arxiv.org/pdf/1807.04119v5.pdf | |
PWC | https://paperswithcode.com/paper/exploiting-statistical-dependencies-of-time |
Repo | |
Framework | |