October 19, 2019

3009 words 15 mins read

Paper Group ANR 362

EasyConvPooling: Random Pooling with Easy Convolution for Accelerating Training and Testing. Conditions for Major Transitions in Biological and Cultural Evolution. Building a language evolution tree based on word vector combination model. A Likelihood-Free Inference Framework for Population Genetic Data using Exchangeable Neural Networks. An effici …

EasyConvPooling: Random Pooling with Easy Convolution for Accelerating Training and Testing


Title	EasyConvPooling: Random Pooling with Easy Convolution for Accelerating Training and Testing
Authors	Jianzhong Sheng, Chuanbo Chen, Chenchen Fu, Chun Jason Xue
Abstract	Convolution operations dominate the overall execution time of Convolutional Neural Networks (CNNs). This paper proposes an easy yet efficient technique for both Convolutional Neural Network training and testing. The conventional convolution and pooling operations are replaced by Easy Convolution and Random Pooling (ECP). In ECP, we randomly select one pixel out of four and only conduct convolution operations of the selected pixel. As a result, only a quarter of the conventional convolution computations are needed. Experiments demonstrate that the proposed EasyConvPooling can achieve 1.45x speedup on training time and 1.64x on testing time. What’s more, a speedup of 5.09x on pure Easy Convolution operations is obtained compared to conventional convolution operations.
Tasks
Published	2018-06-05
URL	http://arxiv.org/abs/1806.01729v1
PDF	http://arxiv.org/pdf/1806.01729v1.pdf
PWC	https://paperswithcode.com/paper/easyconvpooling-random-pooling-with-easy
Repo
Framework

Conditions for Major Transitions in Biological and Cultural Evolution


Title	Conditions for Major Transitions in Biological and Cultural Evolution
Authors	Peter D. Turney
Abstract	Evolution by natural selection can be seen an algorithm for generating creative solutions to difficult problems. More precisely, evolution by natural selection is a class of algorithms that share a set of properties. The question we address here is, what are the conditions that define this class of algorithms? There is a standard answer to this question: Briefly, the conditions are variation, heredity, and selection. We agree that these three conditions are sufficient for a limited type of evolution, but they are not sufficient for open-ended evolution. By open-ended evolution, we mean evolution that generates a continuous stream of creative solutions, without stagnating. We propose a set of conditions for open-ended evolution. The new conditions build on the standard conditions by adding fission, fusion, and cooperation. We test the proposed conditions by applying them to major transitions in the evolution of life and culture. We find that the proposed conditions are able to account for the major transitions.
Tasks
Published	2018-06-20
URL	http://arxiv.org/abs/1806.07941v1
PDF	http://arxiv.org/pdf/1806.07941v1.pdf
PWC	https://paperswithcode.com/paper/conditions-for-major-transitions-in
Repo
Framework

Building a language evolution tree based on word vector combination model


Title	Building a language evolution tree based on word vector combination model
Authors	Zhu Gao, Yanhui Jiang, Junhui Gao
Abstract	In this paper, we try to explore the evolution of language through case calculations. First, we chose the novels of eleven British writers from 1400 to 2005 and found the corresponding works; Then, we use the natural language processing tool to construct the corresponding eleven corpora, and calculate the respective word vectors of 100 high-frequency words in eleven corpora; Next, for each corpus, we concatenate the 100 word vectors from beginning to end into one; Finally, we use the similarity comparison and hierarchical clustering method to generate the relationship tree between the combined eleven word vectors. This tree represents the relationship between eleven corpora. We found that in the tree generated by clustering, the distance between the corpus and the year corresponding to the corpus are basically the same. This means that we have discovered a specific language evolution tree. To verify the stability and versatility of this method, we add three other themes: Dickens’s eight works, the 19th century poets’ works, and art criticism of recent 60 years. For these four themes, we tested different parameters such as the time span of the corpus, the time interval between the corpora, the dimension of the word vector, and the number of high-frequency public words. The results show that this is fairly stable and versatile.
Tasks
Published	2018-10-04
URL	http://arxiv.org/abs/1810.03445v1
PDF	http://arxiv.org/pdf/1810.03445v1.pdf
PWC	https://paperswithcode.com/paper/building-a-language-evolution-tree-based-on
Repo
Framework

A Likelihood-Free Inference Framework for Population Genetic Data using Exchangeable Neural Networks


Title	A Likelihood-Free Inference Framework for Population Genetic Data using Exchangeable Neural Networks
Authors	Jeffrey Chan, Valerio Perrone, Jeffrey P. Spence, Paul A. Jenkins, Sara Mathieson, Yun S. Song
Abstract	An explosion of high-throughput DNA sequencing in the past decade has led to a surge of interest in population-scale inference with whole-genome data. Recent work in population genetics has centered on designing inference methods for relatively simple model classes, and few scalable general-purpose inference techniques exist for more realistic, complex models. To achieve this, two inferential challenges need to be addressed: (1) population data are exchangeable, calling for methods that efficiently exploit the symmetries of the data, and (2) computing likelihoods is intractable as it requires integrating over a set of correlated, extremely high-dimensional latent variables. These challenges are traditionally tackled by likelihood-free methods that use scientific simulators to generate datasets and reduce them to hand-designed, permutation-invariant summary statistics, often leading to inaccurate inference. In this work, we develop an exchangeable neural network that performs summary statistic-free, likelihood-free inference. Our framework can be applied in a black-box fashion across a variety of simulation-based tasks, both within and outside biology. We demonstrate the power of our approach on the recombination hotspot testing problem, outperforming the state-of-the-art.
Tasks
Published	2018-02-16
URL	http://arxiv.org/abs/1802.06153v2
PDF	http://arxiv.org/pdf/1802.06153v2.pdf
PWC	https://paperswithcode.com/paper/a-likelihood-free-inference-framework-for
Repo
Framework

An efficient deep convolutional laplacian pyramid architecture for CS reconstruction at low sampling ratios


Title	An efficient deep convolutional laplacian pyramid architecture for CS reconstruction at low sampling ratios
Authors	Wenxue Cui, Heyao Xu, Xinwei Gao, Shengping Zhang, Feng Jiang, Debin Zhao
Abstract	The compressed sensing (CS) has been successfully applied to image compression in the past few years as most image signals are sparse in a certain domain. Several CS reconstruction models have been proposed and obtained superior performance. However, these methods suffer from blocking artifacts or ringing effects at low sampling ratios in most cases. To address this problem, we propose a deep convolutional Laplacian Pyramid Compressed Sensing Network (LapCSNet) for CS, which consists of a sampling sub-network and a reconstruction sub-network. In the sampling sub-network, we utilize a convolutional layer to mimic the sampling operator. In contrast to the fixed sampling matrices used in traditional CS methods, the filters used in our convolutional layer are jointly optimized with the reconstruction sub-network. In the reconstruction sub-network, two branches are designed to reconstruct multi-scale residual images and muti-scale target images progressively using a Laplacian pyramid architecture. The proposed LapCSNet not only integrates multi-scale information to achieve better performance but also reduces computational cost dramatically. Experimental results on benchmark datasets demonstrate that the proposed method is capable of reconstructing more details and sharper edges against the state-of-the-arts methods.
Tasks	Image Compression
Published	2018-04-13
URL	http://arxiv.org/abs/1804.04970v1
PDF	http://arxiv.org/pdf/1804.04970v1.pdf
PWC	https://paperswithcode.com/paper/an-efficient-deep-convolutional-laplacian
Repo
Framework

Generative Adversarial Networks for Extreme Learned Image Compression


Title	Generative Adversarial Networks for Extreme Learned Image Compression
Authors	Eirikur Agustsson, Michael Tschannen, Fabian Mentzer, Radu Timofte, Luc Van Gool
Abstract	We present a learned image compression system based on GANs, operating at extremely low bitrates. Our proposed framework combines an encoder, decoder/generator and a multi-scale discriminator, which we train jointly for a generative learned compression objective. The model synthesizes details it cannot afford to store, obtaining visually pleasing results at bitrates where previous methods fail and show strong artifacts. Furthermore, if a semantic label map of the original image is available, our method can fully synthesize unimportant regions in the decoded image such as streets and trees from the label map, proportionally reducing the storage cost. A user study confirms that for low bitrates, our approach is preferred to state-of-the-art methods, even when they use more than double the bits.
Tasks	Image Compression
Published	2018-04-09
URL	https://arxiv.org/abs/1804.02958v3
PDF	https://arxiv.org/pdf/1804.02958v3.pdf
PWC	https://paperswithcode.com/paper/generative-adversarial-networks-for-extreme
Repo
Framework

Deep Feature Factorization For Concept Discovery


Title	Deep Feature Factorization For Concept Discovery
Authors	Edo Collins, Radhakrishna Achanta, Sabine Süsstrunk
Abstract	We propose Deep Feature Factorization (DFF), a method capable of localizing similar semantic concepts within an image or a set of images. We use DFF to gain insight into a deep convolutional neural network’s learned features, where we detect hierarchical cluster structures in feature space. This is visualized as heat maps, which highlight semantically matching regions across a set of images, revealing what the network `perceives’ as similar. DFF can also be used to perform co-segmentation and co-localization, and we report state-of-the-art results on these tasks. \|
Tasks
Published	2018-06-26
URL	http://arxiv.org/abs/1806.10206v5
PDF	http://arxiv.org/pdf/1806.10206v5.pdf
PWC	https://paperswithcode.com/paper/deep-feature-factorization-for-concept
Repo
Framework

Fast-converging Conditional Generative Adversarial Networks for Image Synthesis


Title	Fast-converging Conditional Generative Adversarial Networks for Image Synthesis
Authors	Chengcheng Li, Zi Wang, Hairong Qi
Abstract	Building on top of the success of generative adversarial networks (GANs), conditional GANs attempt to better direct the data generation process by conditioning with certain additional information. Inspired by the most recent AC-GAN, in this paper we propose a fast-converging conditional GAN (FC-GAN). In addition to the real/fake classifier used in vanilla GANs, our discriminator has an advanced auxiliary classifier which distinguishes each real class from an extra `fake' class. The` fake’ class avoids mixing generated data with real data, which can potentially confuse the classification of real data as AC-GAN does, and makes the advanced auxiliary classifier behave as another real/fake classifier. As a result, FC-GAN can accelerate the process of differentiation of all classes, thus boost the convergence speed. Experimental results on image synthesis demonstrate our model is competitive in the quality of images generated while achieving a faster convergence rate.
Tasks	Image Generation
Published	2018-05-05
URL	http://arxiv.org/abs/1805.01972v1
PDF	http://arxiv.org/pdf/1805.01972v1.pdf
PWC	https://paperswithcode.com/paper/fast-converging-conditional-generative
Repo
Framework

IONet: Learning to Cure the Curse of Drift in Inertial Odometry


Title	IONet: Learning to Cure the Curse of Drift in Inertial Odometry
Authors	Changhao Chen, Xiaoxuan Lu, Andrew Markham, Niki Trigoni
Abstract	Inertial sensors play a pivotal role in indoor localization, which in turn lays the foundation for pervasive personal applications. However, low-cost inertial sensors, as commonly found in smartphones, are plagued by bias and noise, which leads to unbounded growth in error when accelerations are double integrated to obtain displacement. Small errors in state estimation propagate to make odometry virtually unusable in a matter of seconds. We propose to break the cycle of continuous integration, and instead segment inertial data into independent windows. The challenge becomes estimating the latent states of each window, such as velocity and orientation, as these are not directly observable from sensor data. We demonstrate how to formulate this as an optimization problem, and show how deep recurrent neural networks can yield highly accurate trajectories, outperforming state-of-the-art shallow techniques, on a wide range of tests and attachments. In particular, we demonstrate that IONet can generalize to estimate odometry for non-periodic motion, such as a shopping trolley or baby-stroller, an extremely challenging task for existing techniques.
Tasks
Published	2018-01-30
URL	http://arxiv.org/abs/1802.02209v1
PDF	http://arxiv.org/pdf/1802.02209v1.pdf
PWC	https://paperswithcode.com/paper/ionet-learning-to-cure-the-curse-of-drift-in
Repo
Framework

Optimal Stochastic Package Delivery Planning with Deadline: A Cardinality Minimization in Routing


Title	Optimal Stochastic Package Delivery Planning with Deadline: A Cardinality Minimization in Routing
Authors	Suttinee Sawadsitang, Siwei Jiang, Dusit Niyato, Ping Wang
Abstract	Vehicle Routing Problem with Private fleet and common Carrier (VRPPC) has been proposed to help a supplier manage package delivery services from a single depot to multiple customers. Most of the existing VRPPC works consider deterministic parameters which may not be practical and uncertainty has to be taken into account. In this paper, we propose the Optimal Stochastic Delivery Planning with Deadline (ODPD) to help a supplier plan and optimize the package delivery. The aim of ODPD is to service all customers within a given deadline while considering the randomness in customer demands and traveling time. We formulate the ODPD as a stochastic integer programming, and use the cardinality minimization approach for calculating the deadline violation probability. To accelerate computation, the L-shaped decomposition method is adopted. We conduct extensive performance evaluation based on real customer locations and traveling time from Google Map.
Tasks
Published	2018-02-28
URL	http://arxiv.org/abs/1803.02232v1
PDF	http://arxiv.org/pdf/1803.02232v1.pdf
PWC	https://paperswithcode.com/paper/optimal-stochastic-package-delivery-planning
Repo
Framework

Bio-Measurements Estimation and Support in Knee Recovery through Machine Learning


Title	Bio-Measurements Estimation and Support in Knee Recovery through Machine Learning
Authors	João Bernardino, Luís Filipe Teixeira, Hugo Sereno Ferreira
Abstract	Knee injuries are frequent, varied and often require the patient to undergo intensive rehabilitation for several months. Treatment protocols usually contemplate some recurrent measurements in order to assess progress, such as goniometry. The need for specific equipment or the complexity and duration of these tasks cause them to often be neglected. A novel deep learning based solution is presented, supported by the generation of a synthetic image dataset. A 3D human-body model was used for this purpose, simulating a recovering patient. For each image, the coordinates of three key points were registered: the centers of the thigh, the knee and the lower leg. These values are sufficient to estimate the flexion angle. Convolutional neural networks were then trained for predicting these six coordinates. Transfer learning was used with the VGG16 and InceptionV3 models pre-trained on the ImageNet dataset, being an additional custom model trained from scratch. All models were tested with different combinations of data augmentation techniques applied on the training sets. InceptionV3 achieved the best overall results, producing considerably good predictions even on real unedited pictures.
Tasks	Data Augmentation, Transfer Learning
Published	2018-07-19
URL	http://arxiv.org/abs/1807.07521v1
PDF	http://arxiv.org/pdf/1807.07521v1.pdf
PWC	https://paperswithcode.com/paper/bio-measurements-estimation-and-support-in
Repo
Framework

Domain Aware Markov Logic Networks


Title	Domain Aware Markov Logic Networks
Authors	Happy Mittal, Ayush Bhardwaj, Vibhav Gogate, Parag Singla
Abstract	Combining logic and probability has been a long stand- ing goal of AI research. Markov Logic Networks (MLNs) achieve this by attaching weights to formulas in first-order logic, and can be seen as templates for constructing features for ground Markov networks. Most techniques for learning weights of MLNs are domain-size agnostic, i.e., the size of the domain is not explicitly taken into account while learn- ing the parameters of the model. This often results in ex- treme probabilities when testing on domain sizes different from those seen during training. In this paper, we propose Domain Aware Markov logic Networks (DA-MLNs) which present a principled solution to this problem. While defin- ing the ground network distribution, DA-MLNs divide the ground feature weight by a scaling factor which is a function of the number of connections the ground atoms appearing in the feature are involved in. We show that standard MLNs fall out as a special case of our formalism when this func- tion evaluates to a constant equal to 1. Experiments on the benchmark Friends & Smokers domain show that our ap- proach results in significantly higher accuracies compared to existing methods when testing on domains whose sizes different from those seen during training.
Tasks
Published	2018-07-03
URL	http://arxiv.org/abs/1807.01082v3
PDF	http://arxiv.org/pdf/1807.01082v3.pdf
PWC	https://paperswithcode.com/paper/domain-aware-markov-logic-networks
Repo
Framework

Relational Constraints for Metric Learning on Relational Data


Title	Relational Constraints for Metric Learning on Relational Data
Authors	Jiajun Pan, Hoel Le Capitaine, Philippe Leray
Abstract	Most of metric learning approaches are dedicated to be applied on data described by feature vectors, with some notable exceptions such as times series, trees or graphs. The objective of this paper is to propose a metric learning algorithm that specifically considers relational data. The proposed approach can take benefit from both the topological structure of the data and supervised labels. For selecting relative constraints representing the relational information, we introduce a link-strength function that measures the strength of relationship links between entities by the side-information of their common parents. We show the performance of the proposed method with two different classical metric learning algorithms, which are ITML (Information Theoretic Metric Learning) and LSML (Least Squares Metric Learning), and test on several real-world datasets. Experimental results show that using relational information improves the quality of the learned metric.
Tasks	Metric Learning
Published	2018-07-02
URL	http://arxiv.org/abs/1807.00558v1
PDF	http://arxiv.org/pdf/1807.00558v1.pdf
PWC	https://paperswithcode.com/paper/relational-constraints-for-metric-learning-on
Repo
Framework

Memristive LSTM network hardware architecture for time-series predictive modeling problem


Title	Memristive LSTM network hardware architecture for time-series predictive modeling problem
Authors	Kazybek Adam, Kamilya Smagulova, Alex Pappachen James
Abstract	Analysis of time-series data allows to identify long-term trends and make predictions that can help to improve our lives. With the rapid development of artificial neural networks, long short-term memory (LSTM) recurrent neural network (RNN) configuration is found to be capable in dealing with time-series forecasting problems where data points are time-dependent and possess seasonality trends. Gated structure of LSTM cell and flexibility in network topology (one-to-many, many-to-one, etc.) allows to model systems with multiple input variables and control several parameters such as the size of the look-back window to make a prediction and number of time steps to be predicted. These make LSTM attractive tool over conventional methods such as autoregression models, the simple average, moving average, naive approach, ARIMA, Holt’s linear trend method, Holt’s Winter seasonal method, and others. In this paper, we propose a hardware implementation of LSTM network architecture for time-series forecasting problem. All simulations were performed using TSMC 0.18um CMOS technology and HP memristor model.
Tasks	Time Series, Time Series Forecasting
Published	2018-09-10
URL	http://arxiv.org/abs/1809.03119v1
PDF	http://arxiv.org/pdf/1809.03119v1.pdf
PWC	https://paperswithcode.com/paper/memristive-lstm-network-hardware-architecture
Repo
Framework

Dimensional emotion recognition using visual and textual cues


Title	Dimensional emotion recognition using visual and textual cues
Authors	Pedro M. Ferreira, Diogo Pernes, Kelwin Fernandes, Ana Rebelo, Jaime S. Cardoso
Abstract	This paper addresses the problem of automatic emotion recognition in the scope of the One-Minute Gradual-Emotional Behavior challenge (OMG-Emotion challenge). The underlying objective of the challenge is the automatic estimation of emotion expressions in the two-dimensional emotion representation space (i.e., arousal and valence). The adopted methodology is a weighted ensemble of several models from both video and text modalities. For video-based recognition, two different types of visual cues (i.e., face and facial landmarks) were considered to feed a multi-input deep neural network. Regarding the text modality, a sequential model based on a simple recurrent architecture was implemented. In addition, we also introduce a model based on high-level features in order to embed domain knowledge in the learning process. Experimental results on the OMG-Emotion validation set demonstrate the effectiveness of the implemented ensemble model as it clearly outperforms the current baseline methods.
Tasks	Emotion Recognition
Published	2018-05-03
URL	http://arxiv.org/abs/1805.01416v1
PDF	http://arxiv.org/pdf/1805.01416v1.pdf
PWC	https://paperswithcode.com/paper/dimensional-emotion-recognition-using-visual
Repo
Framework