October 19, 2019

3076 words 15 mins read

Paper Group ANR 235

Paper Group ANR 235

A neuro-inspired architecture for unsupervised continual learning based on online clustering and hierarchical predictive coding. Integrating Multiplicative Features into Supervised Distributional Methods for Lexical Entailment. A multi-level convolutional LSTM model for the segmentation of left ventricle myocardium in infarcted porcine cine MR imag …

A neuro-inspired architecture for unsupervised continual learning based on online clustering and hierarchical predictive coding

Title A neuro-inspired architecture for unsupervised continual learning based on online clustering and hierarchical predictive coding
Authors Constantine Dovrolis
Abstract We propose that the Continual Learning desiderata can be achieved through a neuro-inspired architecture, grounded on Mountcastle’s cortical column hypothesis. The proposed architecture involves a single module, called Self-Taught Associative Memory (STAM), which models the function of a cortical column. STAMs are repeated in multi-level hierarchies involving feedforward, lateral and feedback connections. STAM networks learn in an unsupervised manner, based on a combination of online clustering and hierarchical predictive coding. This short paper only presents the architecture and its connections with neuroscience. A mathematical formulation and experimental results will be presented in an extended version of this paper.
Tasks Continual Learning
Published 2018-10-22
URL http://arxiv.org/abs/1810.09391v1
PDF http://arxiv.org/pdf/1810.09391v1.pdf
PWC https://paperswithcode.com/paper/a-neuro-inspired-architecture-for
Repo
Framework

Integrating Multiplicative Features into Supervised Distributional Methods for Lexical Entailment

Title Integrating Multiplicative Features into Supervised Distributional Methods for Lexical Entailment
Authors Tu Vu, Vered Shwartz
Abstract Supervised distributional methods are applied successfully in lexical entailment, but recent work questioned whether these methods actually learn a relation between two words. Specifically, Levy et al. (2015) claimed that linear classifiers learn only separate properties of each word. We suggest a cheap and easy way to boost the performance of these methods by integrating multiplicative features into commonly used representations. We provide an extensive evaluation with different classifiers and evaluation setups, and suggest a suitable evaluation setup for the task, eliminating biases existing in previous ones.
Tasks
Published 2018-04-24
URL http://arxiv.org/abs/1804.08845v1
PDF http://arxiv.org/pdf/1804.08845v1.pdf
PWC https://paperswithcode.com/paper/integrating-multiplicative-features-into
Repo
Framework

A multi-level convolutional LSTM model for the segmentation of left ventricle myocardium in infarcted porcine cine MR images

Title A multi-level convolutional LSTM model for the segmentation of left ventricle myocardium in infarcted porcine cine MR images
Authors Dongqing Zhang, Ilknur Icke, Belma Dogdas, Sarayu Parimal, Smita Sampath, Joseph Forbes, Ansuman Bagchi, Chih-Liang Chin, Antong Chen
Abstract Automatic segmentation of left ventricle (LV) myocardium in cardiac short-axis cine MR images acquired on subjects with myocardial infarction is a challenging task, mainly because of the various types of image inhomogeneity caused by the infarctions. Among the approaches proposed to automate the LV myocardium segmentation task, methods based upon deep convolutional neural networks (CNN) have demonstrated their exceptional accuracy and robustness in recent years. However, most of the CNN-based approaches treat the frames in a cardiac cycle independently, which fails to capture the valuable dynamics of heart motion. Herein, an approach based on recurrent neural network (RNN), specifically a multi-level convolutional long short-term memory (ConvLSTM) model, is proposed to take the motion of the heart into consideration. Based on a ResNet-56 CNN, LV-related image features in consecutive frames of a cardiac cycle are extracted at both the low- and high-resolution levels, which are processed by the corresponding multi-level ConvLSTM models to generate the myocardium segmentations. A leave-one-out experiment was carried out on a set of 3,600 cardiac cine MR slices collected in-house for 8 porcine subjects with surgically induced myocardial infarction. Compared with a solely CNN-based approach, the proposed approach demonstrated its superior robustness against image inhomogeneity by incorporating information from adjacent frames. It also outperformed a one-level ConvLSTM approach thanks to its capabilities to take advantage of image features at multiple resolution levels.
Tasks
Published 2018-11-14
URL http://arxiv.org/abs/1811.06051v1
PDF http://arxiv.org/pdf/1811.06051v1.pdf
PWC https://paperswithcode.com/paper/a-multi-level-convolutional-lstm-model-for
Repo
Framework

Flexible Deep Neural Network Processing

Title Flexible Deep Neural Network Processing
Authors Hokchhay Tann, Soheil Hashemi, Sherief Reda
Abstract The recent success of Deep Neural Networks (DNNs) has drastically improved the state of the art for many application domains. While achieving high accuracy performance, deploying state-of-the-art DNNs is a challenge since they typically require billions of expensive arithmetic computations. In addition, DNNs are typically deployed in ensemble to boost accuracy performance, which further exacerbates the system requirements. This computational overhead is an issue for many platforms, e.g. data centers and embedded systems, with tight latency and energy budgets. In this article, we introduce flexible DNNs ensemble processing technique, which achieves large reduction in average inference latency while incurring small to negligible accuracy drop. Our technique is flexible in that it allows for dynamic adaptation between quality of results (QoR) and execution runtime. We demonstrate the effectiveness of the technique on AlexNet and ResNet-50 using the ImageNet dataset. This technique can also easily handle other types of networks.
Tasks
Published 2018-01-23
URL http://arxiv.org/abs/1801.07353v1
PDF http://arxiv.org/pdf/1801.07353v1.pdf
PWC https://paperswithcode.com/paper/flexible-deep-neural-network-processing
Repo
Framework

Simplifying the minimax disparity model for determining OWA weights in large-scale problems

Title Simplifying the minimax disparity model for determining OWA weights in large-scale problems
Authors Thuy Hong Nguyen
Abstract In the context of multicriteria decision making, the ordered weighted averaging (OWA) functions play a crucial role in aggregating multiple criteria evaluations into an overall assessment supporting the decision makers’ choice. Determining OWA weights, therefore, is an essential part of this process. Available methods for determining OWA weights, however, often require heavy computational loads in real-life large-scale optimization problems. In this paper, we propose a new approach to simplify the well-known minimax disparity model for determining OWA weights. For this purpose, we use to the binomial decomposition framework in which natural constraints can be imposed on the level of complexity of the weight distribution. The original problem of determining OWA weights is thereby transformed into a smaller scale optimization problem, formulated in terms of the coefficients in the binomial decomposition. Our preliminary results show that a small set of these coefficients can encode for an appropriate full-dimensional set of OWA weights.
Tasks Decision Making
Published 2018-04-17
URL http://arxiv.org/abs/1804.06331v1
PDF http://arxiv.org/pdf/1804.06331v1.pdf
PWC https://paperswithcode.com/paper/simplifying-the-minimax-disparity-model-for
Repo
Framework

A Flexible Convolutional Solver with Application to Photorealistic Style Transfer

Title A Flexible Convolutional Solver with Application to Photorealistic Style Transfer
Authors Gilles Puy, Patrick Pérez
Abstract We propose a new flexible deep convolutional neural network (convnet) to perform fast visual style transfer. In contrast to existing convnets that address the same task, our architecture derives directly from the structure of the gradient descent originally used to solve the style transfer problem [Gatys et al., 2016]. Like existing convnets, ours approximately solves the original problem much faster than the gradient descent. However, our network is uniquely flexible by design: it can be manipulated at runtime to enforce new constraints on the final solution. In particular, we show how to modify it to obtain a photorealistic result with no retraining. We study the modifications made by [Luan et al., 2017] to the original cost function of [Gatys et al., 2016] to achieve photorealistic style transfer. These modifications affect directly the gradient descent and can be reported on-the-fly in our network. These modifications are possible as the proposed architecture stems from unrolling the gradient descent.
Tasks Style Transfer
Published 2018-06-13
URL http://arxiv.org/abs/1806.05285v1
PDF http://arxiv.org/pdf/1806.05285v1.pdf
PWC https://paperswithcode.com/paper/a-flexible-convolutional-solver-with
Repo
Framework

Parallel Computation of PDFs on Big Spatial Data Using Spark

Title Parallel Computation of PDFs on Big Spatial Data Using Spark
Authors Ji Liu, Noel Moreno Lemus, Esther Pacitti, Fabio Porto, Patrick Valduriez
Abstract We consider big spatial data, which is typically produced in scientific areas such as geological or seismic interpretation. The spatial data can be produced by observation (e.g. using sensors or soil instrument) or numerical simulation programs and correspond to points that represent a 3D soil cube area. However, errors in signal processing and modeling create some uncertainty, and thus a lack of accuracy in identifying geological or seismic phenomenons. Such uncertainty must be carefully analyzed. To analyze uncertainty, the main solution is to compute a Probability Density Function (PDF) of each point in the spatial cube area. However, computing PDFs on big spatial data can be very time consuming (from several hours to even months on a parallel computer). In this paper, we propose a new solution to efficiently compute such PDFs in parallel using Spark, with three methods: data grouping, machine learning prediction and sampling. We evaluate our solution by extensive experiments on different computer clusters using big data ranging from hundreds of GB to several TB. The experimental results show that our solution scales up very well and can reduce the execution time by a factor of 33 (in the order of seconds or minutes) compared with a baseline method.
Tasks Seismic Interpretation
Published 2018-05-08
URL http://arxiv.org/abs/1805.03141v1
PDF http://arxiv.org/pdf/1805.03141v1.pdf
PWC https://paperswithcode.com/paper/parallel-computation-of-pdfs-on-big-spatial
Repo
Framework

Demystifying Neural Network Filter Pruning

Title Demystifying Neural Network Filter Pruning
Authors Zhuwei Qin, Fuxun Yu, ChenChen Liu, Xiang Chen
Abstract Based on filter magnitude ranking (e.g. L1 norm), conventional filter pruning methods for Convolutional Neural Networks (CNNs) have been proved with great effectiveness in computation load reduction. Although effective, these methods are rarely analyzed in a perspective of filter functionality. In this work, we explore the filter pruning and the retraining through qualitative filter functionality interpretation. We find that the filter magnitude based method fails to eliminate the filters with repetitive functionality. And the retraining phase is actually used to reconstruct the remained filters for functionality compensation for the wrongly-pruned critical filters. With a proposed functionality-oriented pruning method, we further testify that, by precisely addressing the filter functionality redundancy, a CNN can be pruned without considerable accuracy drop, and the retraining phase is unnecessary.
Tasks
Published 2018-10-29
URL https://arxiv.org/abs/1811.02639v1
PDF https://arxiv.org/pdf/1811.02639v1.pdf
PWC https://paperswithcode.com/paper/demystifying-neural-network-filter-pruning
Repo
Framework

A Method For Dynamic Ensemble Selection Based on a Filter and an Adaptive Distance to Improve the Quality of the Regions of Competence

Title A Method For Dynamic Ensemble Selection Based on a Filter and an Adaptive Distance to Improve the Quality of the Regions of Competence
Authors Rafael M. O. Cruz, George D. C. Cavalcanti, Tsang Ing Ren
Abstract Dynamic classifier selection systems aim to select a group of classifiers that is most adequate for a specific query pattern. This is done by defining a region around the query pattern and analyzing the competence of the classifiers in this region. However, the regions are often surrounded by noise which can difficult the classifier selection. This fact makes the performance of most dynamic selection systems no better than static selections. In this paper, we demonstrate that the performance dynamic selection systems end up limited by the quality of the regions extracted. Thereafter, we propose a new dynamic classifier selection that improves the regions of competence in order to achieve higher recognition rates. obtained from several classification databases show the proposed method not only increase the recognition performance but also decreases the computational cost.
Tasks
Published 2018-11-01
URL http://arxiv.org/abs/1811.00669v1
PDF http://arxiv.org/pdf/1811.00669v1.pdf
PWC https://paperswithcode.com/paper/a-method-for-dynamic-ensemble-selection-based
Repo
Framework

A Semi-Supervised and Inductive Embedding Model for Churn Prediction of Large-Scale Mobile Games

Title A Semi-Supervised and Inductive Embedding Model for Churn Prediction of Large-Scale Mobile Games
Authors Xi Liu, Muhe Xie, Xidao Wen, Rui Chen, Yong Ge, Nick Duffield, Na Wang
Abstract Mobile gaming has emerged as a promising market with billion-dollar revenues. A variety of mobile game platforms and services have been developed around the world. One critical challenge for these platforms and services is to understand user churn behavior in mobile games. Accurate churn prediction will benefit many stakeholders such as game developers, advertisers, and platform operators. In this paper, we present the first large-scale churn prediction solution for mobile games. In view of the common limitations of the state-of-the-art methods built upon traditional machine learning models, we devise a novel semi-supervised and inductive embedding model that jointly learns the prediction function and the embedding function for user-app relationships. We model these two functions by deep neural networks with a unique edge embedding technique that is able to capture both contextual information and relationship dynamics. We also design a novel attributed random walk technique that takes into consideration both topological adjacency and attribute similarities. To evaluate the performance of our solution, we collect real-world data from the Samsung Game Launcher platform that includes tens of thousands of games and hundreds of millions of user-app interactions. The experimental results with this data demonstrate the superiority of our proposed model against existing state-of-the-art methods.
Tasks
Published 2018-08-20
URL http://arxiv.org/abs/1808.06573v3
PDF http://arxiv.org/pdf/1808.06573v3.pdf
PWC https://paperswithcode.com/paper/a-semi-supervised-and-inductive-embedding
Repo
Framework

Gnowee: A Hybrid Metaheuristic Optimization Algorithm for Constrained, Black Box, Combinatorial Mixed-Integer Design

Title Gnowee: A Hybrid Metaheuristic Optimization Algorithm for Constrained, Black Box, Combinatorial Mixed-Integer Design
Authors James Bevins, Rachel Slaybaugh
Abstract This paper introduces Gnowee, a modular, Python-based, open-source hybrid metaheuristic optimization algorithm (Available from https://github.com/SlaybaughLab/Gnowee). Gnowee is designed for rapid convergence to nearly globally optimum solutions for complex, constrained nuclear engineering problems with mixed-integer and combinatorial design vectors and high-cost, noisy, discontinuous, black box objective function evaluations. Gnowee’s hybrid metaheuristic framework is a new combination of a set of diverse, robust heuristics that appropriately balance diversification and intensification strategies across a wide range of optimization problems. This novel algorithm was specifically developed to optimize complex nuclear design problems; the motivating research problem was the design of material stack-ups to modify neutron energy spectra to specific targeted spectra for applications in nuclear medicine, technical nuclear forensics, nuclear physics, etc. However, there are a wider range of potential applications for this algorithm both within the nuclear community and beyond. To demonstrate Gnowee’s behavior for a variety of problem types, comparisons between Gnowee and several well-established metaheuristic algorithms are made for a set of eighteen continuous, mixed-integer, and combinatorial benchmarks. These results demonstrate Gnoweee to have superior flexibility and convergence characteristics over a wide range of design spaces. We anticipate this wide range of applicability will make this algorithm desirable for many complex engineering applications.
Tasks
Published 2018-04-15
URL http://arxiv.org/abs/1804.05429v1
PDF http://arxiv.org/pdf/1804.05429v1.pdf
PWC https://paperswithcode.com/paper/gnowee-a-hybrid-metaheuristic-optimization
Repo
Framework

Deploy Large-Scale Deep Neural Networks in Resource Constrained IoT Devices with Local Quantization Region

Title Deploy Large-Scale Deep Neural Networks in Resource Constrained IoT Devices with Local Quantization Region
Authors Yi Yang, Andy Chen, Xiaoming Chen, Jiang Ji, Zhenyang Chen, Yan Dai
Abstract Implementing large-scale deep neural networks with high computational complexity on low-cost IoT devices may inevitably be constrained by limited computation resource, making the devices hard to respond in real-time. This disjunction makes the state-of-art deep learning algorithms, i.e. CNN (Convolutional Neural Networks), incompatible with IoT world. We present a low-bit (range from 8-bit to 1-bit) scheme with our local quantization region algorithm. We use models in Caffe model zoo as our example tasks to evaluate the effect of our low precision data representation scheme. With the available of local quantization region, we find implementations on top of those schemes could greatly retain the model accuracy, besides the reduction of computational complexity. For example, our 8-bit scheme has no drops on top-1 and top-5 accuracy with 2x speedup on Intel Edison IoT platform. Implementations based on our 4-bit, 2-bit or 1-bit scheme are also applicable to IoT devices with advances of low computational complexity. For example, the drop on our task is only 0.7% when using 2-bit scheme, a scheme which could largely save transistors. Making low-bit scheme usable here opens a new door for further optimization on commodity IoT controller, i.e. extra speed-up could be achieved by replacing multiply-accumulate operations with the proposed table look-up operations. The whole study offers a new approach to relief the challenge of bring advanced deep learning algorithm to resource constrained low-cost IoT device.
Tasks Quantization
Published 2018-05-24
URL http://arxiv.org/abs/1805.09473v1
PDF http://arxiv.org/pdf/1805.09473v1.pdf
PWC https://paperswithcode.com/paper/deploy-large-scale-deep-neural-networks-in
Repo
Framework

A Machine Learning Driven IoT Solution for Noise Classification in Smart Cities

Title A Machine Learning Driven IoT Solution for Noise Classification in Smart Cities
Authors Yasser Alsouda, Sabri Pllana, Arianit Kurti
Abstract We present a machine learning based method for noise classification using a low-power and inexpensive IoT unit. We use Mel-frequency cepstral coefficients for audio feature extraction and supervised classification algorithms (that is, support vector machine and k-nearest neighbors) for noise classification. We evaluate our approach experimentally with a dataset of about 3000 sound samples grouped in eight sound classes (such as, car horn, jackhammer, or street music). We explore the parameter space of support vector machine and k-nearest neighbors algorithms to estimate the optimal parameter values for classification of sound samples in the dataset under study. We achieve a noise classification accuracy in the range 85% – 100%. Training and testing of our k-nearest neighbors (k = 1) implementation on Raspberry Pi Zero W is less than a second for a dataset with features of more than 3000 sound samples.
Tasks
Published 2018-09-01
URL http://arxiv.org/abs/1809.00238v1
PDF http://arxiv.org/pdf/1809.00238v1.pdf
PWC https://paperswithcode.com/paper/a-machine-learning-driven-iot-solution-for
Repo
Framework

Regularized Loss Minimizers with Local Data Perturbation: Consistency and Data Irrecoverability

Title Regularized Loss Minimizers with Local Data Perturbation: Consistency and Data Irrecoverability
Authors Zitao Li, Jean Honorio
Abstract We introduce a new concept, data irrecoverability, and show that the well-studied concept of data privacy implies data irrecoverability. We show that there are several regularized loss minimization problems that can use locally perturbed data with theoretical guarantees of generalization, i.e., loss consistency. Our results quantitatively connect the convergence rates of the learning problems to the impossibility for any adversary for recovering the original data from perturbed observations. In addition, we show several examples where the convergence rates with perturbed data only increase the convergence rates with original data within a constant factor related to the amount of perturbation, i.e., noise.
Tasks
Published 2018-05-19
URL http://arxiv.org/abs/1805.07645v5
PDF http://arxiv.org/pdf/1805.07645v5.pdf
PWC https://paperswithcode.com/paper/regularized-loss-minimizers-with-local-data
Repo
Framework

Semi-Supervised Clustering with Neural Networks

Title Semi-Supervised Clustering with Neural Networks
Authors Ankita Shukla, Gullal Singh Cheema, Saket Anand
Abstract Clustering using neural networks has recently demonstrated promising performance in machine learning and computer vision applications. However, the performance of current approaches is limited either by unsupervised learning or their dependence on large set of labeled data samples. In this paper, we propose ClusterNet that uses pairwise semantic constraints from very few labeled data samples (<5% of total data) and exploits the abundant unlabeled data to drive the clustering approach. We define a new loss function that uses pairwise semantic similarity between objects combined with constrained k-means clustering to efficiently utilize both labeled and unlabeled data in the same framework. The proposed network uses convolution autoencoder to learn a latent representation that groups data into k specified clusters, while also learning the cluster centers simultaneously. We evaluate and compare the performance of ClusterNet on several datasets and state of the art deep clustering approaches.
Tasks Semantic Similarity, Semantic Textual Similarity
Published 2018-06-05
URL http://arxiv.org/abs/1806.01547v2
PDF http://arxiv.org/pdf/1806.01547v2.pdf
PWC https://paperswithcode.com/paper/semi-supervised-clustering-with-neural
Repo
Framework
comments powered by Disqus