October 17, 2019

2861 words 14 mins read

Paper Group ANR 896

An adaptive multiclass nearest neighbor classifier. Cooperative Multi-Agent Policy Gradients with Sub-optimal Demonstration. Intent Detection for code-mix utterances in task oriented dialogue systems. Deep Recurrent Electricity Theft Detection in AMI Networks with Random Tuning of Hyper-parameters. Distributed Stochastic Optimization via Adaptive S …

An adaptive multiclass nearest neighbor classifier


Title	An adaptive multiclass nearest neighbor classifier
Authors	Nikita Puchkin, Vladimir Spokoiny
Abstract	We consider a problem of multiclass classification, where the training sample $S_n = {(X_i, Y_i)}_{i=1}^n$ is generated from the model $\mathbb P(Y = m X = x) = \eta_m(x)$, $1 \leq m \leq M$, and $\eta_1(x), \dots, \eta_M(x)$ are unknown $\alpha$-Holder continuous functions.Given a test point $X$, our goal is to predict its label. A widely used $\mathsf k$-nearest-neighbors classifier constructs estimates of $\eta_1(X), \dots, \eta_M(X)$ and uses a plug-in rule for the prediction. However, it requires a proper choice of the smoothing parameter $\mathsf k$, which may become tricky in some situations. In our solution, we fix several integers $n_1, \dots, n_K$, compute corresponding $n_k$-nearest-neighbor estimates for each $m$ and each $n_k$ and apply an aggregation procedure. We study an algorithm, which constructs a convex combination of these estimates such that the aggregated estimate behaves approximately as well as an oracle choice. We also provide a non-asymptotic analysis of the procedure, prove its adaptation to the unknown smoothness parameter $\alpha$ and to the margin and establish rates of convergence under mild assumptions.
Tasks
Published	2018-04-08
URL	https://arxiv.org/abs/1804.02756v4
PDF	https://arxiv.org/pdf/1804.02756v4.pdf
PWC	https://paperswithcode.com/paper/adaptive-multiclass-nearest-neighbor
Repo
Framework

Cooperative Multi-Agent Policy Gradients with Sub-optimal Demonstration


Title	Cooperative Multi-Agent Policy Gradients with Sub-optimal Demonstration
Authors	Peixi Peng, Junliang Xing, Lu Pang
Abstract	Many reality tasks such as robot coordination can be naturally modelled as multi-agent cooperative system where the rewards are sparse. This paper focuses on learning decentralized policies for such tasks using sub-optimal demonstration. To learn the multi-agent cooperation effectively and tackle the sub-optimality of demonstration, a self-improving learning method is proposed: On the one hand, the centralized state-action values are initialized by the demonstration and updated by the learned decentralized policy to improve the sub-optimality. On the other hand, the Nash Equilibrium are found by the current state-action value and are used as a guide to learn the policy. The proposed method is evaluated on the combat RTS games which requires a high level of multi-agent cooperation. Extensive experimental results on various combat scenarios demonstrate that the proposed method can learn multi-agent cooperation effectively. It significantly outperforms many state-of-the-art demonstration based approaches.
Tasks
Published	2018-12-05
URL	http://arxiv.org/abs/1812.01825v1
PDF	http://arxiv.org/pdf/1812.01825v1.pdf
PWC	https://paperswithcode.com/paper/cooperative-multi-agent-policy-gradients-with
Repo
Framework

Intent Detection for code-mix utterances in task oriented dialogue systems


Title	Intent Detection for code-mix utterances in task oriented dialogue systems
Authors	Pratik Jayarao, Aman Srivastava
Abstract	Intent detection is an essential component of task oriented dialogue systems. Over the years, extensive research has been conducted resulting in many state of the art models directed towards resolving user’s intents in dialogue. A variety of vector representations foruser utterances have been explored for the same. However, these models and vectorization approaches have more so been evaluated in a single language environment. Dialogude systems generally have to deal with queries in different languages. We thus conduct experiments across combinations of models and various vectors representations for Code Mix as well as multi language utterances and evaluate how these models scale to a multi language environment. Our aim is to find the best suitable combination of vector representation and models for the process of intent detection for Code Mix utterances. we have evaluated the experiments on two different datasets consisting of only Code Mix utterances and the other dataset consisting of English, Hindi and Code Mix English Hindi utterances.
Tasks	Intent Detection, Task-Oriented Dialogue Systems
Published	2018-12-07
URL	http://arxiv.org/abs/1812.02914v1
PDF	http://arxiv.org/pdf/1812.02914v1.pdf
PWC	https://paperswithcode.com/paper/intent-detection-for-code-mix-utterances-in
Repo
Framework

Deep Recurrent Electricity Theft Detection in AMI Networks with Random Tuning of Hyper-parameters


Title	Deep Recurrent Electricity Theft Detection in AMI Networks with Random Tuning of Hyper-parameters
Authors	Mahmoud Nabil, Muhammad Ismail, Mohamed Mahmoud, Mostafa Shahin, Khalid Qaraqe, Erchin Serpedin
Abstract	Modern smart grids rely on advanced metering infrastructure (AMI) networks for monitoring and billing pur- poses. However, such an approach suffers from electricity theft cyberattacks. Different from the existing research that utilizes shallow, static, and customer-specific-based electricity theft de- tectors, this paper proposes a generalized deep recurrent neural network (RNN)-based electricity theft detector that can effectively thwart these cyberattacks. The proposed model exploits the time series nature of the customers’ electricity consumption to implement a gated recurrent unit (GRU)-RNN, hence, improving the detection performance. In addition, the proposed RNN-based detector adopts a random search analysis in its learning stage to appropriately fine-tune its hyper-parameters. Extensive test studies are carried out to investigate the detector’s performance using publicly available real data of 107,200 energy consumption days from 200 customers. Simulation results demonstrate the superior performance of the proposed detector compared with state-of-the-art electricity theft detectors.
Tasks	Time Series
Published	2018-09-06
URL	http://arxiv.org/abs/1809.01774v1
PDF	http://arxiv.org/pdf/1809.01774v1.pdf
PWC	https://paperswithcode.com/paper/deep-recurrent-electricity-theft-detection-in
Repo
Framework

Distributed Stochastic Optimization via Adaptive SGD


Title	Distributed Stochastic Optimization via Adaptive SGD
Authors	Ashok Cutkosky, Robert Busa-Fekete
Abstract	Stochastic convex optimization algorithms are the most popular way to train machine learning models on large-scale data. Scaling up the training process of these models is crucial, but the most popular algorithm, Stochastic Gradient Descent (SGD), is a serial method that is surprisingly hard to parallelize. In this paper, we propose an efficient distributed stochastic optimization method by combining adaptivity with variance reduction techniques. Our analysis yields a linear speedup in the number of machines, constant memory footprint, and only a logarithmic number of communication rounds. Critically, our approach is a black-box reduction that parallelizes any serial online learning algorithm, streamlining prior analysis and allowing us to leverage the significant progress that has been made in designing adaptive algorithms. In particular, we achieve optimal convergence rates without any prior knowledge of smoothness parameters, yielding a more robust algorithm that reduces the need for hyperparameter tuning. We implement our algorithm in the Spark distributed framework and exhibit dramatic performance gains on large-scale logistic regression problems.
Tasks	Stochastic Optimization
Published	2018-02-16
URL	http://arxiv.org/abs/1802.05811v3
PDF	http://arxiv.org/pdf/1802.05811v3.pdf
PWC	https://paperswithcode.com/paper/distributed-stochastic-optimization-via-1
Repo
Framework

Text-Adaptive Generative Adversarial Networks: Manipulating Images with Natural Language


Title	Text-Adaptive Generative Adversarial Networks: Manipulating Images with Natural Language
Authors	Seonghyeon Nam, Yunji Kim, Seon Joo Kim
Abstract	This paper addresses the problem of manipulating images using natural language description. Our task aims to semantically modify visual attributes of an object in an image according to the text describing the new visual appearance. Although existing methods synthesize images having new attributes, they do not fully preserve text-irrelevant contents of the original image. In this paper, we propose the text-adaptive generative adversarial network (TAGAN) to generate semantically manipulated images while preserving text-irrelevant contents. The key to our method is the text-adaptive discriminator that creates word-level local discriminators according to input text to classify fine-grained attributes independently. With this discriminator, the generator learns to generate images where only regions that correspond to the given text are modified. Experimental results show that our method outperforms existing methods on CUB and Oxford-102 datasets, and our results were mostly preferred on a user study. Extensive analysis shows that our method is able to effectively disentangle visual attributes and produce pleasing outputs.
Tasks
Published	2018-10-29
URL	http://arxiv.org/abs/1810.11919v2
PDF	http://arxiv.org/pdf/1810.11919v2.pdf
PWC	https://paperswithcode.com/paper/text-adaptive-generative-adversarial-networks
Repo
Framework

Genetic algorithms in Forth


Title	Genetic algorithms in Forth
Authors	S. I. Khashin, S. E. Vaganov
Abstract	A method for automatically finding a program (bytecode) realizing the given algorithm is developed. The algorithm is specified as a set of tests (input_data) $ \rightarrow $ (output_data). Genetic methods made it possible to find the implementation of relatively complex algorithms: sorting, decimal digits, GCD, LCM, factorial, prime divisors, binomial coefficients, and others. The algorithms are implemented on a highly simplified version of Forth language.
Tasks
Published	2018-07-17
URL	http://arxiv.org/abs/1807.06230v1
PDF	http://arxiv.org/pdf/1807.06230v1.pdf
PWC	https://paperswithcode.com/paper/genetic-algorithms-in-forth
Repo
Framework

Vietnamese Open Information Extraction


Title	Vietnamese Open Information Extraction
Authors	Diem Truong, Duc-Thuan Vo, U. T Nguyen
Abstract	Open information extraction (OIE) is the process to extract relations and their arguments automatically from textual documents without the need to restrict the search to predefined relations. In recent years, several OIE systems for the English language have been created but there is not any system for the Vietnamese language. In this paper, we propose a method of OIE for Vietnamese using a clause-based approach. Accordingly, we exploit Vietnamese dependency parsing using grammar clauses that strives to consider all possible relations in a sentence. The corresponding clause types are identified by their propositions as extractable relations based on their grammatical functions of constituents. As a result, our system is the first OIE system named vnOIE for the Vietnamese language that can generate open relations and their arguments from Vietnamese text with highly scalable extraction while being domain independent. Experimental results show that our OIE system achieves promising results with a precision of 83.71%.
Tasks	Dependency Parsing, Open Information Extraction
Published	2018-01-23
URL	http://arxiv.org/abs/1801.07804v1
PDF	http://arxiv.org/pdf/1801.07804v1.pdf
PWC	https://paperswithcode.com/paper/vietnamese-open-information-extraction
Repo
Framework

Improving Hospital Mortality Prediction with Medical Named Entities and Multimodal Learning


Title	Improving Hospital Mortality Prediction with Medical Named Entities and Multimodal Learning
Authors	Mengqi Jin, Mohammad Taha Bahadori, Aaron Colak, Parminder Bhatia, Busra Celikkaya, Ram Bhakta, Selvan Senthivel, Mohammed Khalilia, Daniel Navarro, Borui Zhang, Tiberiu Doman, Arun Ravi, Matthieu Liger, Taha Kass-hout
Abstract	Clinical text provides essential information to estimate the acuity of a patient during hospital stays in addition to structured clinical data. In this study, we explore how clinical text can complement a clinical predictive learning task. We leverage an internal medical natural language processing service to perform named entity extraction and negation detection on clinical notes and compose selected entities into a new text corpus to train document representations. We then propose a multimodal neural network to jointly train time series signals and unstructured clinical text representations to predict the in-hospital mortality risk for ICU patients. Our model outperforms the benchmark by 2% AUC.
Tasks	Entity Extraction, Mortality Prediction, Negation Detection, Time Series
Published	2018-11-29
URL	http://arxiv.org/abs/1811.12276v2
PDF	http://arxiv.org/pdf/1811.12276v2.pdf
PWC	https://paperswithcode.com/paper/improving-hospital-mortality-prediction-with
Repo
Framework

Dense Pose Transfer


Title	Dense Pose Transfer
Authors	Natalia Neverova, Riza Alp Guler, Iasonas Kokkinos
Abstract	In this work we integrate ideas from surface-based modeling with neural synthesis: we propose a combination of surface-based pose estimation and deep generative models that allows us to perform accurate pose transfer, i.e. synthesize a new image of a person based on a single image of that person and the image of a pose donor. We use a dense pose estimation system that maps pixels from both images to a common surface-based coordinate system, allowing the two images to be brought in correspondence with each other. We inpaint and refine the source image intensities in the surface coordinate system, prior to warping them onto the target pose. These predictions are fused with those of a convolutional predictive module through a neural synthesis module allowing for training the whole pipeline jointly end-to-end, optimizing a combination of adversarial and perceptual losses. We show that dense pose estimation is a substantially more powerful conditioning input than landmark-, or mask-based alternatives, and report systematic improvements over state of the art generators on DeepFashion and MVC datasets.
Tasks	Pose Estimation, Pose Transfer
Published	2018-09-06
URL	http://arxiv.org/abs/1809.01995v1
PDF	http://arxiv.org/pdf/1809.01995v1.pdf
PWC	https://paperswithcode.com/paper/dense-pose-transfer
Repo
Framework

DGPose: Deep Generative Models for Human Body Analysis


Title	DGPose: Deep Generative Models for Human Body Analysis
Authors	Rodrigo de Bem, Arnab Ghosh, Thalaiyasingam Ajanthan, Ondrej Miksik, Adnane Boukhayma, N. Siddharth, Philip Torr
Abstract	Deep generative modelling for human body analysis is an emerging problem with many interesting applications. However, the latent space learned by such approaches is typically not interpretable, resulting in less flexibility. In this work, we present deep generative models for human body analysis in which the body pose and the visual appearance are disentangled. Such a disentanglement allows independent manipulation of pose and appearance, and hence enables applications such as pose-transfer without specific training for such a task. Our proposed models, the Conditional-DGPose and the Semi-DGPose, have different characteristics. In the first, body pose labels are taken as conditioners, from a fully-supervised training set. In the second, our structured semi-supervised approach allows for pose estimation to be performed by the model itself and relaxes the need for labelled data. Therefore, the Semi-DGPose aims for the joint understanding and generation of people in images. It is not only capable of mapping images to interpretable latent representations but also able to map these representations back to the image space. We compare our models with relevant baselines, the ClothNet-Body and the Pose Guided Person Generation networks, demonstrating their merits on the Human3.6M, ChictopiaPlus and DeepFashion benchmarks.
Tasks	Pose Estimation, Pose Transfer
Published	2018-04-17
URL	https://arxiv.org/abs/1804.06364v2
PDF	https://arxiv.org/pdf/1804.06364v2.pdf
PWC	https://paperswithcode.com/paper/dgpose-disentangled-semi-supervised-deep
Repo
Framework

k-Nearest Neighbors by Means of Sequence to Sequence Deep Neural Networks and Memory Networks


Title	k-Nearest Neighbors by Means of Sequence to Sequence Deep Neural Networks and Memory Networks
Authors	Yiming Xu, Diego Klabjan
Abstract	k-Nearest Neighbors is one of the most fundamental but effective classification models. In this paper, we propose two families of models built on a sequence to sequence model and a memory network model to mimic the k-Nearest Neighbors model, which generate a sequence of labels, a sequence of out-of-sample feature vectors and a final label for classification, and thus they could also function as oversamplers. We also propose ‘out-of-core’ versions of our models which assume that only a small portion of data can be loaded into memory. Computational experiments show that our models on structured datasets outperform k-Nearest Neighbors, a feed-forward neural network, XGBoost, lightGBM, random forest and a memory network, due to the fact that our models must produce additional output and not just the label. On image and text datasets, the performance of our model is close to many state-of-the-art deep models. As an oversampler on imbalanced datasets, the sequence to sequence kNN model often outperforms Synthetic Minority Over-sampling Technique and Adaptive Synthetic Sampling.
Tasks
Published	2018-04-27
URL	https://arxiv.org/abs/1804.11214v4
PDF	https://arxiv.org/pdf/1804.11214v4.pdf
PWC	https://paperswithcode.com/paper/k-nearest-neighbors-by-means-of-sequence-to
Repo
Framework

Conditional End-to-End Audio Transforms


Title	Conditional End-to-End Audio Transforms
Authors	Albert Haque, Michelle Guo, Prateek Verma
Abstract	We present an end-to-end method for transforming audio from one style to another. For the case of speech, by conditioning on speaker identities, we can train a single model to transform words spoken by multiple people into multiple target voices. For the case of music, we can specify musical instruments and achieve the same result. Architecturally, our method is a fully-differentiable sequence-to-sequence model based on convolutional and hierarchical recurrent neural networks. It is designed to capture long-term acoustic dependencies, requires minimal post-processing, and produces realistic audio transforms. Ablation studies confirm that our model can separate speaker and instrument properties from acoustic content at different receptive fields. Empirically, our method achieves competitive performance on community-standard datasets.
Tasks
Published	2018-03-30
URL	http://arxiv.org/abs/1804.00047v2
PDF	http://arxiv.org/pdf/1804.00047v2.pdf
PWC	https://paperswithcode.com/paper/conditional-end-to-end-audio-transforms
Repo
Framework

Exploring the Deep Feature Space of a Cell Classification Neural Network


Title	Exploring the Deep Feature Space of a Cell Classification Neural Network
Authors	Ezra Webb, Cheng Lei, Chun-Jung Huang, Hirofumi Kobayashi, Hideharu Mikami, Keisuke Goda
Abstract	In this paper, we present contemporary techniques for visualising the feature space of a deep learning image classification neural network. These techniques are viewed in the context of a feed-forward network trained to classify low resolution fluorescence images of white blood cells captured using optofluidic imaging. The model has two output classes corresponding to two different cell types, which are often difficult to distinguish by eye. This paper has two major sections. The first looks to develop the information space presented by dimension reduction techniques, such as t-SNE, used to embed high-dimensional pre-softmax layer activations into a two-dimensional plane. The second section looks at feature visualisation by optimisation to generate feature images representing the learned features of the network. Using and developing these techniques we visualise class separation and structures within the dataset at various depths using clustering algorithms and feature images; track the development of feature complexity as we ascend the network; and begin to extract the features the network has learnt by modulating single-channel feature images with up-scaled neuron activation maps to distinguish their most salient parts.
Tasks	Dimensionality Reduction, Image Classification
Published	2018-11-15
URL	http://arxiv.org/abs/1811.06488v1
PDF	http://arxiv.org/pdf/1811.06488v1.pdf
PWC	https://paperswithcode.com/paper/exploring-the-deep-feature-space-of-a-cell
Repo
Framework

Automated Speed and Lane Change Decision Making using Deep Reinforcement Learning


Title	Automated Speed and Lane Change Decision Making using Deep Reinforcement Learning
Authors	Carl-Johan Hoel, Krister Wolff, Leo Laine
Abstract	This paper introduces a method, based on deep reinforcement learning, for automatically generating a general purpose decision making function. A Deep Q-Network agent was trained in a simulated environment to handle speed and lane change decisions for a truck-trailer combination. In a highway driving case, it is shown that the method produced an agent that matched or surpassed the performance of a commonly used reference model. To demonstrate the generality of the method, the exact same algorithm was also tested by training it for an overtaking case on a road with oncoming traffic. Furthermore, a novel way of applying a convolutional neural network to high level input that represents interchangeable objects is also introduced.
Tasks	Decision Making
Published	2018-03-14
URL	http://arxiv.org/abs/1803.10056v2
PDF	http://arxiv.org/pdf/1803.10056v2.pdf
PWC	https://paperswithcode.com/paper/automated-speed-and-lane-change-decision
Repo
Framework