Paper Group ANR 529
Seeing and Hearing Egocentric Actions: How Much Can We Learn?. ADEPOS: A Novel Approximate Computing Framework for Anomaly Detection Systems and its Implementation in 65nm CMOS. Deep density ratio estimation for change point detection. Towards Distributed Logic Programming based on Computability Logic. On Simulation and Trajectory Prediction with G …
Seeing and Hearing Egocentric Actions: How Much Can We Learn?
| Title | Seeing and Hearing Egocentric Actions: How Much Can We Learn? |
| Authors | Alejandro Cartas, Jordi Luque, Petia Radeva, Carlos Segura, Mariella Dimiccoli |
| Abstract | Our interaction with the world is an inherently multimodal experience. However, the understanding of human-to-object interactions has historically been addressed focusing on a single modality. In particular, a limited number of works have considered to integrate the visual and audio modalities for this purpose. In this work, we propose a multimodal approach for egocentric action recognition in a kitchen environment that relies on audio and visual information. Our model combines a sparse temporal sampling strategy with a late fusion of audio, spatial, and temporal streams. Experimental results on the EPIC-Kitchens dataset show that multimodal integration leads to better performance than unimodal approaches. In particular, we achieved a 5.18% improvement over the state of the art on verb classification. |
| Tasks | |
| Published | 2019-10-15 |
| URL | https://arxiv.org/abs/1910.06693v1 |
| https://arxiv.org/pdf/1910.06693v1.pdf | |
| PWC | https://paperswithcode.com/paper/seeing-and-hearing-egocentric-actions-how |
| Repo | |
| Framework | |
ADEPOS: A Novel Approximate Computing Framework for Anomaly Detection Systems and its Implementation in 65nm CMOS
| Title | ADEPOS: A Novel Approximate Computing Framework for Anomaly Detection Systems and its Implementation in 65nm CMOS |
| Authors | Sumon Kumar Bose, Bapi Kar, Mohendra Roy, Pradeep Kumar Gopalakrishnan, Zhang Lei, Aakash Patil, Arindam Basu |
| Abstract | To overcome the energy and bandwidth limitations of traditional IoT systems, edge computing or information extraction at the sensor node has become popular. However, now it is important to create very low energy information extraction or pattern recognition systems. In this paper, we present an approximate computing method to reduce the computation energy of a specific type of IoT system used for anomaly detection (e.g. in predictive maintenance, epileptic seizure detection, etc). Termed as Anomaly Detection Based Power Savings (ADEPOS), our proposed method uses low precision computing and low complexity neural networks at the beginning when it is easy to distinguish healthy data. However, on the detection of anomalies, the complexity of the network and computing precision are adaptively increased for accurate predictions. We show that ensemble approaches are well suited for adaptively changing network size. To validate our proposed scheme, a chip has been fabricated in UMC65nm process that includes an MSP430 microprocessor along with an on-chip switching mode DC-DC converter for dynamic voltage and frequency scaling. Using NASA bearing dataset for machine health monitoring, we show that using ADEPOS we can achieve 8.95X saving of energy along the lifetime without losing any detection accuracy. The energy savings are obtained by reducing the execution time of the neural network on the microprocessor. |
| Tasks | Anomaly Detection, Seizure Detection |
| Published | 2019-12-04 |
| URL | https://arxiv.org/abs/1912.01853v1 |
| https://arxiv.org/pdf/1912.01853v1.pdf | |
| PWC | https://paperswithcode.com/paper/adepos-a-novel-approximate-computing |
| Repo | |
| Framework | |
Deep density ratio estimation for change point detection
| Title | Deep density ratio estimation for change point detection |
| Authors | Haidar Khan, Lara Marcuse, Bülent Yener |
| Abstract | In this work, we propose new objective functions to train deep neural network based density ratio estimators and apply it to a change point detection problem. Existing methods use linear combinations of kernels to approximate the density ratio function by solving a convex constrained minimization problem. Approximating the density ratio function using a deep neural network requires defining a suitable objective function to optimize. We formulate and compare objective functions that can be minimized using gradient descent and show that the network can effectively learn to approximate the density ratio function. Using our deep density ratio estimation objective function results in better performance on a seizure detection task than other (kernel and neural network based) density ratio estimation methods and other window-based change point detection algorithms. We also show that the method can still support other neural network architectures, such as convolutional networks. |
| Tasks | Change Point Detection, Seizure Detection |
| Published | 2019-05-23 |
| URL | https://arxiv.org/abs/1905.09876v1 |
| https://arxiv.org/pdf/1905.09876v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-density-ratio-estimation-for-change |
| Repo | |
| Framework | |
Towards Distributed Logic Programming based on Computability Logic
| Title | Towards Distributed Logic Programming based on Computability Logic |
| Authors | Keehang Kwon |
| Abstract | {\em Computability logic} (CoL) is a powerful computational model which views computational problems as games played by a machine and its environment. It uses formulas to represent computational problems. In this paper, we show that CoL naturally supports multiagent programming models with distributed control. To be specific, we discuss a web-based implemention of a distributed logic programming model based on CoL (CL1 to be exact). |
| Tasks | |
| Published | 2019-09-16 |
| URL | https://arxiv.org/abs/1909.07036v1 |
| https://arxiv.org/pdf/1909.07036v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-distributed-logic-programming-based |
| Repo | |
| Framework | |
On Simulation and Trajectory Prediction with Gaussian Process Dynamics
| Title | On Simulation and Trajectory Prediction with Gaussian Process Dynamics |
| Authors | Lukas Hewing, Elena Arcari, Lukas P. Fröhlich, Melanie N. Zeilinger |
| Abstract | Established techniques for simulation and prediction with Gaussian process (GP) dynamics often implicitly make use of an independence assumption on successive function evaluations of the dynamics model. This can result in significant error and underestimation of the prediction uncertainty, potentially leading to failures in safety-critical applications. This paper discusses methods that explicitly take the correlation of successive function evaluations into account. We first describe two sampling-based techniques; one approach provides samples of the true trajectory distribution, suitable for `ground truth’ simulations, while the other draws function samples from basis function approximations of the GP. Second, we propose a linearization-based technique that directly provides approximations of the trajectory distribution, taking correlations explicitly into account. We demonstrate the procedures in simple numerical examples, contrasting the results with established methods. | |
| Tasks | Trajectory Prediction |
| Published | 2019-12-23 |
| URL | https://arxiv.org/abs/1912.10900v2 |
| https://arxiv.org/pdf/1912.10900v2.pdf | |
| PWC | https://paperswithcode.com/paper/on-simulation-and-trajectory-prediction-with |
| Repo | |
| Framework | |
Near-optimal Bayesian Solution For Unknown Discrete Markov Decision Process
| Title | Near-optimal Bayesian Solution For Unknown Discrete Markov Decision Process |
| Authors | Aristide Tossou, Christos Dimitrakakis, Debabrota Basu |
| Abstract | We tackle the problem of acting in an unknown finite and discrete Markov Decision Process (MDP) for which the expected shortest path from any state to any other state is bounded by a finite number $D$. An MDP consists of $S$ states and $A$ possible actions per state. Upon choosing an action $a_t$ at state $s_t$, one receives a real value reward $r_t$, then one transits to a next state $s_{t+1}$. The reward $r_t$ is generated from a fixed reward distribution depending only on $(s_t, a_t)$ and similarly, the next state $s_{t+1}$ is generated from a fixed transition distribution depending only on $(s_t, a_t)$. The objective is to maximize the accumulated rewards after $T$ interactions. In this paper, we consider the case where the reward distributions, the transitions, $T$ and $D$ are all unknown. We derive the first polynomial time Bayesian algorithm, BUCRL{} that achieves up to logarithm factors, a regret (i.e the difference between the accumulated rewards of the optimal policy and our algorithm) of the optimal order $\tilde{\mathcal{O}}(\sqrt{DSAT})$. Importantly, our result holds with high probability for the worst-case (frequentist) regret and not the weaker notion of Bayesian regret. We perform experiments in a variety of environments that demonstrate the superiority of our algorithm over previous techniques. Our work also illustrates several results that will be of independent interest. In particular, we derive a sharper upper bound for the KL-divergence of Bernoulli random variables. We also derive sharper upper and lower bounds for Beta and Binomial quantiles. All the bound are very simple and only use elementary functions. |
| Tasks | |
| Published | 2019-06-20 |
| URL | https://arxiv.org/abs/1906.09114v2 |
| https://arxiv.org/pdf/1906.09114v2.pdf | |
| PWC | https://paperswithcode.com/paper/near-optimal-reinforcement-learning-using |
| Repo | |
| Framework | |
Contextual Aware Joint Probability Model Towards Question Answering System
| Title | Contextual Aware Joint Probability Model Towards Question Answering System |
| Authors | Liu Yang, Lijing Song |
| Abstract | In this paper, we address the question answering challenge with the SQuAD 2.0 dataset. We design a model architecture which leverages BERT’s capability of context-aware word embeddings and BiDAF’s context interactive exploration mechanism. By integrating these two state-of-the-art architectures, our system tries to extract the contextual word representation at word and character levels, for better comprehension of both question and context and their correlations. We also propose our original joint posterior probability predictor module and its associated loss functions. Our best model so far obtains F1 score of 75.842% and EM score of 72.24% on the test PCE leaderboad. |
| Tasks | Question Answering, Word Embeddings |
| Published | 2019-04-17 |
| URL | http://arxiv.org/abs/1904.08109v1 |
| http://arxiv.org/pdf/1904.08109v1.pdf | |
| PWC | https://paperswithcode.com/paper/contextual-aware-joint-probability-model |
| Repo | |
| Framework | |
Machine Learning for Fluid Mechanics
| Title | Machine Learning for Fluid Mechanics |
| Authors | Steven Brunton, Bernd Noack, Petros Koumoutsakos |
| Abstract | The field of fluid mechanics is rapidly advancing, driven by unprecedented volumes of data from field measurements, experiments and large-scale simulations at multiple spatiotemporal scales. Machine learning offers a wealth of techniques to extract information from data that could be translated into knowledge about the underlying fluid mechanics. Moreover, machine learning algorithms can augment domain knowledge and automate tasks related to flow control and optimization. This article presents an overview of past history, current developments, and emerging opportunities of machine learning for fluid mechanics. It outlines fundamental machine learning methodologies and discusses their uses for understanding, modeling, optimizing, and controlling fluid flows. The strengths and limitations of these methods are addressed from the perspective of scientific inquiry that considers data as an inherent part of modeling, experimentation, and simulation. Machine learning provides a powerful information processing framework that can enrich, and possibly even transform, current lines of fluid mechanics research and industrial applications. |
| Tasks | |
| Published | 2019-05-27 |
| URL | https://arxiv.org/abs/1905.11075v3 |
| https://arxiv.org/pdf/1905.11075v3.pdf | |
| PWC | https://paperswithcode.com/paper/machine-learning-for-fluid-mechanics |
| Repo | |
| Framework | |
B-Script: Transcript-based B-roll Video Editing with Recommendations
| Title | B-Script: Transcript-based B-roll Video Editing with Recommendations |
| Authors | Bernd Huber, Hijung Valentina Shin, Bryan Russell, Oliver Wang, Gautham J. Mysore |
| Abstract | In video production, inserting B-roll is a widely used technique to enrich the story and make a video more engaging. However, determining the right content and positions of B-roll and actually inserting it within the main footage can be challenging, and novice producers often struggle to get both timing and content right. We present B-Script, a system that supports B-roll video editing via interactive transcripts. B-Script has a built-in recommendation system trained on expert-annotated data, recommending users B-roll position and content. To evaluate the system, we conducted a within-subject user study with 110 participants, and compared three interface variations: a timeline-based editor, a transcript-based editor, and a transcript-based editor with recommendations. Users found it easier and were faster to insert B-roll using the transcript-based interface, and they created more engaging videos when recommendations were provided. |
| Tasks | |
| Published | 2019-02-28 |
| URL | http://arxiv.org/abs/1902.11216v1 |
| http://arxiv.org/pdf/1902.11216v1.pdf | |
| PWC | https://paperswithcode.com/paper/b-script-transcript-based-b-roll-video |
| Repo | |
| Framework | |
Approximate Variational Inference Based on a Finite Sample of Gaussian Latent Variables
| Title | Approximate Variational Inference Based on a Finite Sample of Gaussian Latent Variables |
| Authors | Nikolaos Gianniotis, Christoph Schnörr, Christian Molkenthin, Sanjay Singh Bora |
| Abstract | Variational methods are employed in situations where exact Bayesian inference becomes intractable due to the difficulty in performing certain integrals. Typically, variational methods postulate a tractable posterior and formulate a lower bound on the desired integral to be approximated, e.g. marginal likelihood. The lower bound is then optimised with respect to its free parameters, the so called variational parameters. However, this is not always possible as for certain integrals it is very challenging (or tedious) to come up with a suitable lower bound. Here we propose a simple scheme that overcomes some of the awkward cases where the usual variational treatment becomes difficult. The scheme relies on a rewriting of the lower bound on the model log-likelihood. We demonstrate the proposed scheme on a number of synthetic and real examples, as well as on a real geophysical model for which the standard variational approaches are inapplicable. |
| Tasks | Bayesian Inference |
| Published | 2019-06-11 |
| URL | https://arxiv.org/abs/1906.04507v1 |
| https://arxiv.org/pdf/1906.04507v1.pdf | |
| PWC | https://paperswithcode.com/paper/approximate-variational-inference-based-on-a |
| Repo | |
| Framework | |
Semantic Parsing with Dual Learning
| Title | Semantic Parsing with Dual Learning |
| Authors | Ruisheng Cao, Su Zhu, Chen Liu, Jieyu Li, Kai Yu |
| Abstract | Semantic parsing converts natural language queries into structured logical forms. The paucity of annotated training samples is a fundamental challenge in this field. In this work, we develop a semantic parsing framework with the dual learning algorithm, which enables a semantic parser to make full use of data (labeled and even unlabeled) through a dual-learning game. This game between a primal model (semantic parsing) and a dual model (logical form to query) forces them to regularize each other, and can achieve feedback signals from some prior-knowledge. By utilizing the prior-knowledge of logical form structures, we propose a novel reward signal at the surface and semantic levels which tends to generate complete and reasonable logical forms. Experimental results show that our approach achieves new state-of-the-art performance on ATIS dataset and gets competitive performance on Overnight dataset. |
| Tasks | Semantic Parsing |
| Published | 2019-07-10 |
| URL | https://arxiv.org/abs/1907.05343v2 |
| https://arxiv.org/pdf/1907.05343v2.pdf | |
| PWC | https://paperswithcode.com/paper/semantic-parsing-with-dual-learning |
| Repo | |
| Framework | |
MultiDEC: Multi-Modal Clustering of Image-Caption Pairs
| Title | MultiDEC: Multi-Modal Clustering of Image-Caption Pairs |
| Authors | Sean Yang, Kuan-Hao Huang, BIll Howe |
| Abstract | In this paper, we propose a method for clustering image-caption pairs by simultaneously learning image representations and text representations that are constrained to exhibit similar distributions. These image-caption pairs arise frequently in high-value applications where structured training data is expensive to produce but free-text descriptions are common. MultiDEC initializes parameters with stacked autoencoders, then iteratively minimizes the Kullback-Leibler divergence between the distribution of the images (and text) to that of a combined joint target distribution. We regularize by penalizing non-uniform distributions across clusters. The representations that minimize this objective produce clusters that outperform both single-view and multi-view techniques on large benchmark image-caption datasets. |
| Tasks | |
| Published | 2019-01-04 |
| URL | http://arxiv.org/abs/1901.01860v1 |
| http://arxiv.org/pdf/1901.01860v1.pdf | |
| PWC | https://paperswithcode.com/paper/multidec-multi-modal-clustering-of-image |
| Repo | |
| Framework | |
Identifying Low-Dimensional Structures in Markov Chains: A Nonnegative Matrix Factorization Approach
| Title | Identifying Low-Dimensional Structures in Markov Chains: A Nonnegative Matrix Factorization Approach |
| Authors | Mahsa Ghasemi, Abolfazl Hashemi, Haris Vikalo, Ufuk Topcu |
| Abstract | A variety of queries about stochastic systems boil down to study of Markov chains and their properties. If the Markov chain is large, as is typically true for discretized continuous spaces, such analysis may be computationally intractable. Nevertheless, in many scenarios, Markov chains have underlying structural properties that allow them to admit a low-dimensional representation. For instance, the transition matrix associated with the model may be low-rank and hence, representable in a lower-dimensional space. We consider the problem of learning low-dimensional representations for large-scale Markov chains. To that end, we formulate the task of representation learning as that of mapping the state space of the model to a low-dimensional state space, referred to as the kernel space. The kernel space contains a set of meta states which are desired to be representative of only a small subset of original states. To promote this structural property, we constrain the number of nonzero entries of the mappings between the state space and the kernel space. By imposing the desired characteristics of the structured representation, we cast the problem as the task of nonnegative matrix factorization. To compute the solution, we propose an efficient block coordinate gradient descent and theoretically analyze its convergence properties. Our extensive simulation results demonstrate the efficacy of the proposed algorithm in terms of the quality of the low-dimensional representation as well as its computational cost. |
| Tasks | Representation Learning |
| Published | 2019-09-27 |
| URL | https://arxiv.org/abs/1909.12898v1 |
| https://arxiv.org/pdf/1909.12898v1.pdf | |
| PWC | https://paperswithcode.com/paper/identifying-low-dimensional-structures-in |
| Repo | |
| Framework | |
Synthèse non quadratique H$\infty$ de contrôleurs décentralisés pour un ensemble de descripteurs flous T-S interconnectés
| Title | Synthèse non quadratique H$\infty$ de contrôleurs décentralisés pour un ensemble de descripteurs flous T-S interconnectés |
| Authors | Dalel Jabri, Kevin Guelton, Noureddine Manamanni, Mohammed Naceur Abdelkrim |
| Abstract | This paper deals with the non-quadratic decentralized stabilization of a set of n Takagi-Sugeno descriptors. To ensure the stability of the whole closed-loop dynamics and to minimize interconnection effects between subsystems, the main result allows designing a network of non Parallel Distributed Compensation control laws via a H $\infty$ criterion. Sufficient conditions, obtained from a non quadratic fuzzy Lyapunov approach, are provided in terms of Linear Matrix Inequalities. Finally, a numerical example illustrates the efficiency of the proposed decentralized control approach. |
| Tasks | |
| Published | 2019-09-19 |
| URL | https://arxiv.org/abs/1909.09151v1 |
| https://arxiv.org/pdf/1909.09151v1.pdf | |
| PWC | https://paperswithcode.com/paper/synthese-non-quadratique-hinfty-de |
| Repo | |
| Framework | |
Knowledge-Based Sequential Decision-Making Under Uncertainty
| Title | Knowledge-Based Sequential Decision-Making Under Uncertainty |
| Authors | Daoming Lyu |
| Abstract | Deep reinforcement learning (DRL) algorithms have achieved great success on sequential decision-making problems, yet is criticized for the lack of data-efficiency and explainability. Especially, explainability of subtasks is critical in hierarchical decision-making since it enhances the transparency of black-box-style DRL methods and helps the RL practitioners to understand the high-level behavior of the system better. To improve the data-efficiency and explainability of DRL, declarative knowledge is introduced in this work and a novel algorithm is proposed by integrating DRL with symbolic planning. Experimental analysis on publicly available benchmarks validates the explainability of the subtasks and shows that our method can outperform the state-of-the-art approach in terms of data-efficiency. |
| Tasks | Decision Making, Decision Making Under Uncertainty |
| Published | 2019-05-16 |
| URL | https://arxiv.org/abs/1905.07030v1 |
| https://arxiv.org/pdf/1905.07030v1.pdf | |
| PWC | https://paperswithcode.com/paper/knowledge-based-sequential-decision-making |
| Repo | |
| Framework | |
