July 29, 2019

2826 words 14 mins read

Paper Group ANR 110

Hypotheses testing on infinite random graphs. Using Mise-En-Scène Visual Features based on MPEG-7 and Deep Learning for Movie Recommendation. Learning to Predict: A Fast Re-constructive Method to Generate Multimodal Embeddings. Functional connectivity patterns of autism spectrum disorder identified by deep feature learning. SOT for MOT. Fitting Jum …

Hypotheses testing on infinite random graphs


Title	Hypotheses testing on infinite random graphs
Authors	Daniil Ryabko
Abstract	Drawing on some recent results that provide the formalism necessary to definite stationarity for infinite random graphs, this paper initiates the study of statistical and learning questions pertaining to these objects. Specifically, a criterion for the existence of a consistent test for complex hypotheses is presented, generalizing the corresponding results on time series. As an application, it is shown how one can test that a tree has the Markov property, or, more generally, to estimate its memory.
Tasks	Time Series
Published	2017-08-10
URL	http://arxiv.org/abs/1708.03131v1
PDF	http://arxiv.org/pdf/1708.03131v1.pdf
PWC	https://paperswithcode.com/paper/hypotheses-testing-on-infinite-random-graphs
Repo
Framework

Using Mise-En-Scène Visual Features based on MPEG-7 and Deep Learning for Movie Recommendation


Title	Using Mise-En-Scène Visual Features based on MPEG-7 and Deep Learning for Movie Recommendation
Authors	Yashar Deldjoo, Massimo Quadrana, Mehdi Elahi, Paolo Cremonesi
Abstract	Item features play an important role in movie recommender systems, where recommendations can be generated by using explicit or implicit preferences of users on traditional features (attributes) such as tag, genre, and cast. Typically, movie features are human-generated, either editorially (e.g., genre and cast) or by leveraging the wisdom of the crowd (e.g., tag), and as such, they are prone to noise and are expensive to collect. Moreover, these features are often rare or absent for new items, making it difficult or even impossible to provide good quality recommendations. In this paper, we show that user’s preferences on movies can be better described in terms of the mise-en-sc`ene features, i.e., the visual aspects of a movie that characterize design, aesthetics and style (e.g., colors, textures). We use both MPEG-7 visual descriptors and Deep Learning hidden layers as example of mise-en-sc`ene features that can visually describe movies. Interestingly, mise-en-sc`ene features can be computed automatically from video files or even from trailers, offering more flexibility in handling new items, avoiding the need for costly and error-prone human-based tagging, and providing good scalability. We have conducted a set of experiments on a large catalogue of 4K movies. Results show that recommendations based on mise-en-sc`ene features consistently provide the best performance with respect to richer sets of more traditional features, such as genre and tag.
Tasks	Recommendation Systems
Published	2017-04-20
URL	http://arxiv.org/abs/1704.06109v1
PDF	http://arxiv.org/pdf/1704.06109v1.pdf
PWC	https://paperswithcode.com/paper/using-mise-en-scene-visual-features-based-on
Repo
Framework

Learning to Predict: A Fast Re-constructive Method to Generate Multimodal Embeddings


Title	Learning to Predict: A Fast Re-constructive Method to Generate Multimodal Embeddings
Authors	Guillem Collell, Teddy Zhang, Marie-Francine Moens
Abstract	Integrating visual and linguistic information into a single multimodal representation is an unsolved problem with wide-reaching applications to both natural language processing and computer vision. In this paper, we present a simple method to build multimodal representations by learning a language-to-vision mapping and using its output to build multimodal embeddings. In this sense, our method provides a cognitively plausible way of building representations, consistent with the inherently re-constructive and associative nature of human memory. Using seven benchmark concept similarity tests we show that the mapped vectors not only implicitly encode multimodal information, but also outperform strong unimodal baselines and state-of-the-art multimodal methods, thus exhibiting more “human-like” judgments—particularly in zero-shot settings.
Tasks
Published	2017-03-25
URL	http://arxiv.org/abs/1703.08737v1
PDF	http://arxiv.org/pdf/1703.08737v1.pdf
PWC	https://paperswithcode.com/paper/learning-to-predict-a-fast-re-constructive
Repo
Framework

Functional connectivity patterns of autism spectrum disorder identified by deep feature learning


Title	Functional connectivity patterns of autism spectrum disorder identified by deep feature learning
Authors	Hongyoon Choi
Abstract	Autism spectrum disorder (ASD) is regarded as a brain disease with globally disrupted neuronal networks. Even though fMRI studies have revealed abnormal functional connectivity in ASD, they have not reached a consensus of the disrupted patterns. Here, a deep learning-based feature extraction method identifies multivariate and nonlinear functional connectivity patterns of ASD. Resting-state fMRI data of 972 subjects (465 ASD 507 normal controls) acquired from the Autism Brain Imaging Data Exchange were used. A functional connectivity matrix of each subject was generated using 90 predefined brain regions. As a data-driven feature extraction method without prior knowledge such as subjects diagnosis, variational autoencoder (VAE) summarized the functional connectivity matrix into 2 features. Those feature values of ASD patients were statistically compared with those of controls. A feature was significantly different between ASD and normal controls. The extracted features were visualized by VAE-based generator which can produce virtual functional connectivity matrices. The ASD-related feature was associated with frontoparietal connections, interconnections of the dorsal medial frontal cortex and corticostriatal connections. It also showed a trend of negative correlation with full-scale IQ. A data-driven feature extraction based on deep learning could identify complex patterns of functional connectivity of ASD. This approach will help discover complex patterns of abnormalities in brain connectivity in various brain disorders.
Tasks
Published	2017-07-25
URL	http://arxiv.org/abs/1707.07932v1
PDF	http://arxiv.org/pdf/1707.07932v1.pdf
PWC	https://paperswithcode.com/paper/functional-connectivity-patterns-of-autism
Repo
Framework

SOT for MOT


Title	SOT for MOT
Authors	Qizheng He, Jianan Wu, Gang Yu, Chi Zhang
Abstract	In this paper we present a robust tracker to solve the multiple object tracking (MOT) problem, under the framework of tracking-by-detection. As the first contribution, we innovatively combine single object tracking (SOT) algorithms with multiple object tracking algorithms, and our results show that SOT is a general way to strongly reduce the number of false negatives, regardless of the quality of detection. Another contribution is that we show with a deep learning based appearance model, it is easy to associate detections of the same object efficiently and also with high accuracy. This appearance model plays an important role in our MOT algorithm to correctly associate detections into long trajectories, and also in our SOT algorithm to discover new detections mistakenly missed by the detector. The deep neural network based model ensures the robustness of our tracking algorithm, which can perform data association in a wide variety of scenes. We ran comprehensive experiments on a large-scale and challenging dataset, the MOT16 benchmark, and results showed that our tracker achieved state-of-the-art performance based on both public and private detections.
Tasks	Multiple Object Tracking, Object Tracking
Published	2017-12-04
URL	http://arxiv.org/abs/1712.01059v1
PDF	http://arxiv.org/pdf/1712.01059v1.pdf
PWC	https://paperswithcode.com/paper/sot-for-mot
Repo
Framework

Fitting Jump Models


Title	Fitting Jump Models
Authors	A. Bemporad, V. Breschi, D. Piga, S. Boyd
Abstract	We describe a new framework for fitting jump models to a sequence of data. The key idea is to alternate between minimizing a loss function to fit multiple model parameters, and minimizing a discrete loss function to determine which set of model parameters is active at each data point. The framework is quite general and encompasses popular classes of models, such as hidden Markov models and piecewise affine models. The shape of the chosen loss functions to minimize determine the shape of the resulting jump model.
Tasks
Published	2017-11-25
URL	http://arxiv.org/abs/1711.09220v2
PDF	http://arxiv.org/pdf/1711.09220v2.pdf
PWC	https://paperswithcode.com/paper/fitting-jump-models
Repo
Framework

Iterative Deep Convolutional Encoder-Decoder Network for Medical Image Segmentation


Title	Iterative Deep Convolutional Encoder-Decoder Network for Medical Image Segmentation
Authors	Jung Uk Kim, Hak Gu Kim, Yong Man Ro
Abstract	In this paper, we propose a novel medical image segmentation using iterative deep learning framework. We have combined an iterative learning approach and an encoder-decoder network to improve segmentation results, which enables to precisely localize the regions of interest (ROIs) including complex shapes or detailed textures of medical images in an iterative manner. The proposed iterative deep convolutional encoder-decoder network consists of two main paths: convolutional encoder path and convolutional decoder path with iterative learning. Experimental results show that the proposed iterative deep learning framework is able to yield excellent medical image segmentation performances for various medical images. The effectiveness of the proposed method has been proved by comparing with other state-of-the-art medical image segmentation methods.
Tasks	Medical Image Segmentation, Semantic Segmentation
Published	2017-08-11
URL	http://arxiv.org/abs/1708.03431v1
PDF	http://arxiv.org/pdf/1708.03431v1.pdf
PWC	https://paperswithcode.com/paper/iterative-deep-convolutional-encoder-decoder
Repo
Framework

Quantum ensembles of quantum classifiers


Title	Quantum ensembles of quantum classifiers
Authors	Maria Schuld, Francesco Petruccione
Abstract	Quantum machine learning witnesses an increasing amount of quantum algorithms for data-driven decision making, a problem with potential applications ranging from automated image recognition to medical diagnosis. Many of those algorithms are implementations of quantum classifiers, or models for the classification of data inputs with a quantum computer. Following the success of collective decision making with ensembles in classical machine learning, this paper introduces the concept of quantum ensembles of quantum classifiers. Creating the ensemble corresponds to a state preparation routine, after which the quantum classifiers are evaluated in parallel and their combined decision is accessed by a single-qubit measurement. This framework naturally allows for exponentially large ensembles in which – similar to Bayesian learning – the individual classifiers do not have to be trained. As an example, we analyse an exponentially large quantum ensemble in which each classifier is weighed according to its performance in classifying the training data, leading to new results for quantum as well as classical machine learning.
Tasks	Decision Making, Medical Diagnosis, Quantum Machine Learning
Published	2017-04-07
URL	http://arxiv.org/abs/1704.02146v1
PDF	http://arxiv.org/pdf/1704.02146v1.pdf
PWC	https://paperswithcode.com/paper/quantum-ensembles-of-quantum-classifiers
Repo
Framework

Estimation of Tissue Microstructure Using a Deep Network Inspired by a Sparse Reconstruction Framework


Title	Estimation of Tissue Microstructure Using a Deep Network Inspired by a Sparse Reconstruction Framework
Authors	Chuyang Ye
Abstract	Diffusion magnetic resonance imaging (dMRI) provides a unique tool for noninvasively probing the microstructure of the neuronal tissue. The NODDI model has been a popular approach to the estimation of tissue microstructure in many neuroscience studies. It represents the diffusion signals with three types of diffusion in tissue: intra-cellular, extra-cellular, and cerebrospinal fluid compartments. However, the original NODDI method uses a computationally expensive procedure to fit the model and could require a large number of diffusion gradients for accurate microstructure estimation, which may be impractical for clinical use. Therefore, efforts have been devoted to efficient and accurate NODDI microstructure estimation with a reduced number of diffusion gradients. In this work, we propose a deep network based approach to the NODDI microstructure estimation, which is named Microstructure Estimation using a Deep Network (MEDN). Motivated by the AMICO algorithm which accelerates the computation of NODDI parameters, we formulate the microstructure estimation problem in a dictionary-based framework. The proposed network comprises two cascaded stages. The first stage resembles the solution to a dictionary-based sparse reconstruction problem and the second stage computes the final microstructure using the output of the first stage. The weights in the two stages are jointly learned from training data, which is obtained from training dMRI scans with diffusion gradients that densely sample the q-space. The proposed method was applied to brain dMRI scans, where two shells each with 30 gradient directions (60 diffusion gradients in total) were used. Estimation accuracy with respect to the gold standard was measured and the results demonstrate that MEDN outperforms the competing algorithms.
Tasks
Published	2017-04-05
URL	http://arxiv.org/abs/1704.01246v1
PDF	http://arxiv.org/pdf/1704.01246v1.pdf
PWC	https://paperswithcode.com/paper/estimation-of-tissue-microstructure-using-a
Repo
Framework

CleanNet: Transfer Learning for Scalable Image Classifier Training with Label Noise


Title	CleanNet: Transfer Learning for Scalable Image Classifier Training with Label Noise
Authors	Kuang-Huei Lee, Xiaodong He, Lei Zhang, Linjun Yang
Abstract	In this paper, we study the problem of learning image classification models with label noise. Existing approaches depending on human supervision are generally not scalable as manually identifying correct or incorrect labels is time-consuming, whereas approaches not relying on human supervision are scalable but less effective. To reduce the amount of human supervision for label noise cleaning, we introduce CleanNet, a joint neural embedding network, which only requires a fraction of the classes being manually verified to provide the knowledge of label noise that can be transferred to other classes. We further integrate CleanNet and conventional convolutional neural network classifier into one framework for image classification learning. We demonstrate the effectiveness of the proposed algorithm on both of the label noise detection task and the image classification on noisy data task on several large-scale datasets. Experimental results show that CleanNet can reduce label noise detection error rate on held-out classes where no human supervision available by 41.5% compared to current weakly supervised methods. It also achieves 47% of the performance gain of verifying all images with only 3.2% images verified on an image classification task. Source code and dataset will be available at kuanghuei.github.io/CleanNetProject.
Tasks	Image Classification, Transfer Learning
Published	2017-11-20
URL	http://arxiv.org/abs/1711.07131v2
PDF	http://arxiv.org/pdf/1711.07131v2.pdf
PWC	https://paperswithcode.com/paper/cleannet-transfer-learning-for-scalable-image
Repo
Framework

A multi-method simulation of a high-frequency bus line using AnyLogic


Title	A multi-method simulation of a high-frequency bus line using AnyLogic
Authors	Thierry van der Spek
Abstract	In this work a mixed agent-based and discrete event simulation model is developed for a high frequency bus route in the Netherlands. With this model, different passenger growth scenarios can be easily evaluated. This simulation model helps policy makers to predict changes that have to be made to bus routes and planned travel times before problems occur. The model is validated using several performance indicators, showing that under some model assumptions, it can realistically simulate real-life situations. The simulation’s workings are illustrated by two use cases.
Tasks
Published	2017-04-19
URL	http://arxiv.org/abs/1704.05692v1
PDF	http://arxiv.org/pdf/1704.05692v1.pdf
PWC	https://paperswithcode.com/paper/a-multi-method-simulation-of-a-high-frequency
Repo
Framework

Brain Tumor Detection and Classification with Feed Forward Back-Prop Neural Network


Title	Brain Tumor Detection and Classification with Feed Forward Back-Prop Neural Network
Authors	Neha Rani, Sharda Vashisth
Abstract	Brain is an organ that controls activities of all the parts of the body. Recognition of automated brain tumor in Magnetic resonance imaging (MRI) is a difficult task due to complexity of size and location variability. This automatic method detects all the type of cancer present in the body. Previous methods for tumor are time consuming and less accurate. In the present work, statistical analysis morphological and thresholding techniques are used to process the images obtained by MRI. Feed-forward back-prop neural network is used to classify the performance of tumors part of the image. This method results high accuracy and less iterations detection which further reduces the consumption time.
Tasks
Published	2017-05-31
URL	http://arxiv.org/abs/1706.06411v1
PDF	http://arxiv.org/pdf/1706.06411v1.pdf
PWC	https://paperswithcode.com/paper/brain-tumor-detection-and-classification-with
Repo
Framework

An asymptotic analysis of distributed nonparametric methods


Title	An asymptotic analysis of distributed nonparametric methods
Authors	Botond Szabo, Harry van Zanten
Abstract	We investigate and compare the fundamental performance of several distributed learning methods that have been proposed recently. We do this in the context of a distributed version of the classical signal-in-Gaussian-white-noise model, which serves as a benchmark model for studying performance in this setting. The results show how the design and tuning of a distributed method can have great impact on convergence rates and validity of uncertainty quantification. Moreover, we highlight the difficulty of designing nonparametric distributed procedures that automatically adapt to smoothness.
Tasks
Published	2017-11-08
URL	http://arxiv.org/abs/1711.03149v1
PDF	http://arxiv.org/pdf/1711.03149v1.pdf
PWC	https://paperswithcode.com/paper/an-asymptotic-analysis-of-distributed
Repo
Framework

The difference between memory and prediction in linear recurrent networks


Title	The difference between memory and prediction in linear recurrent networks
Authors	Sarah Marzen
Abstract	Recurrent networks are trained to memorize their input better, often in the hopes that such training will increase the ability of the network to predict. We show that networks designed to memorize input can be arbitrarily bad at prediction. We also find, for several types of inputs, that one-node networks optimized for prediction are nearly at upper bounds on predictive capacity given by Wiener filters, and are roughly equivalent in performance to randomly generated five-node networks. Our results suggest that maximizing memory capacity leads to very different networks than maximizing predictive capacity, and that optimizing recurrent weights can decrease reservoir size by half an order of magnitude.
Tasks
Published	2017-06-26
URL	http://arxiv.org/abs/1706.09382v2
PDF	http://arxiv.org/pdf/1706.09382v2.pdf
PWC	https://paperswithcode.com/paper/the-difference-between-memory-and-prediction
Repo
Framework

Recursive Neural Networks in Quark/Gluon Tagging


Title	Recursive Neural Networks in Quark/Gluon Tagging
Authors	Taoli Cheng
Abstract	Since the machine learning techniques are improving rapidly, it has been shown that the image recognition techniques in deep neural networks can be used to detect jet substructure. And it turns out that deep neural networks can match or outperform traditional approach of expert features. However, there are disadvantages such as sparseness of jet images. Based on the natural tree-like structure of jet sequential clustering, the recursive neural networks (RecNNs), which embed jet clustering history recursively as in natural language processing, have a better behavior when confronted with these problems. We thus try to explore the performance of RecNNs in quark/gluon discrimination. The results show that RecNNs work better than the baseline boosted decision tree (BDT) by a few percent in gluon rejection rate. However, extra implementation of particle flow identification only increases the performance slightly. We also experimented on some relevant aspects which might influence the performance of the networks. It shows that even taking only particle flow identification as input feature without any extra information on momentum or angular position is already giving a fairly good result, which indicates that the most of the information for quark/gluon discrimination is already included in the tree-structure itself. As a bonus, a rough up/down quark jets discrimination is also explored.
Tasks
Published	2017-11-07
URL	http://arxiv.org/abs/1711.02633v2
PDF	http://arxiv.org/pdf/1711.02633v2.pdf
PWC	https://paperswithcode.com/paper/recursive-neural-networks-in-quarkgluon
Repo
Framework