Paper Group ANR 317
Domain Adaptation Using Adversarial Learning for Autonomous Navigation. Non-exchangeable random partition models for microclustering. Capacity, Fidelity, and Noise Tolerance of Associative Spatial-Temporal Memories Based on Memristive Neuromorphic Network. The Dependence of Machine Learning on Electronic Medical Record Quality. Real Multi-Sense or …
Domain Adaptation Using Adversarial Learning for Autonomous Navigation
| Title | Domain Adaptation Using Adversarial Learning for Autonomous Navigation |
| Authors | Jaeyoon Yoo, Yongjun Hong, YungKyun Noh, Sungroh Yoon |
| Abstract | Autonomous navigation has become an increasingly popular machine learning application. Recent advances in deep learning have also resulted in great improvements to autonomous navigation. However, prior outdoor autonomous navigation depends on various expensive sensors or large amounts of real labeled data which is difficult to acquire and sometimes erroneous. The objective of this study is to train an autonomous navigation model that uses a simulator (instead of real labeled data) and an inexpensive monocular camera. In order to exploit the simulator satisfactorily, our proposed method is based on domain adaptation with adversarial learning. Specifically, we propose our model with 1) a dilated residual block in the generator, 2) cycle loss, and 3) style loss to improve the adversarial learning performance for satisfactory domain adaptation. In addition, we perform a theoretical analysis that supports the justification of our proposed method. We present empirical results of navigation in outdoor courses with various intersections using a commercial radio controlled car. We observe that our proposed method allows us to learn a favorable navigation model by generating images with realistic textures. To the best of our knowledge, this is the first work to apply domain adaptation with adversarial learning to autonomous navigation in real outdoor environments. Our proposed method can also be applied to precise image generation or other robotic tasks. |
| Tasks | Autonomous Navigation, Domain Adaptation, Image Generation |
| Published | 2017-12-11 |
| URL | http://arxiv.org/abs/1712.03742v6 |
| http://arxiv.org/pdf/1712.03742v6.pdf | |
| PWC | https://paperswithcode.com/paper/domain-adaptation-using-adversarial-learning |
| Repo | |
| Framework | |
Non-exchangeable random partition models for microclustering
| Title | Non-exchangeable random partition models for microclustering |
| Authors | Giuseppe Di Benedetto, François Caron, Yee Whye Teh |
| Abstract | Many popular random partition models, such as the Chinese restaurant process and its two-parameter extension, fall in the class of exchangeable random partitions, and have found wide applicability in model-based clustering, population genetics, ecology or network analysis. While the exchangeability assumption is sensible in many cases, it has some strong implications. In particular, Kingman’s representation theorem implies that the size of the clusters necessarily grows linearly with the sample size; this feature may be undesirable for some applications, as recently pointed out by Miller et al. (2015). We present here a flexible class of non-exchangeable random partition models which are able to generate partitions whose cluster sizes grow sublinearly with the sample size, and where the growth rate is controlled by one parameter. Along with this result, we provide the asymptotic behaviour of the number of clusters of a given size, and show that the model can exhibit a power-law behavior, controlled by another parameter. The construction is based on completely random measures and a Poisson embedding of the random partition, and inference is performed using a Sequential Monte Carlo algorithm. Additionally, we show how the model can also be directly used to generate sparse multigraphs with power-law degree distributions and degree sequences with sublinear growth. Finally, experiments on real datasets emphasize the usefulness of the approach compared to a two-parameter Chinese restaurant process. |
| Tasks | |
| Published | 2017-11-20 |
| URL | http://arxiv.org/abs/1711.07287v1 |
| http://arxiv.org/pdf/1711.07287v1.pdf | |
| PWC | https://paperswithcode.com/paper/non-exchangeable-random-partition-models-for |
| Repo | |
| Framework | |
Capacity, Fidelity, and Noise Tolerance of Associative Spatial-Temporal Memories Based on Memristive Neuromorphic Network
| Title | Capacity, Fidelity, and Noise Tolerance of Associative Spatial-Temporal Memories Based on Memristive Neuromorphic Network |
| Authors | Dmitri Gavrilov, Dmitri Strukov, Konstantin K. Likharev |
| Abstract | We have calculated the key characteristics of associative (content-addressable) spatial-temporal memories based on neuromorphic networks with restricted connectivity - “CrossNets”. Such networks may be naturally implemented in nanoelectronic hardware using hybrid CMOS/memristor circuits, which may feature extremely high energy efficiency, approaching that of biological cortical circuits, at much higher operation speed. Our numerical simulations, in some cases confirmed by analytical calculations, have shown that the characteristics depend substantially on the method of information recording into the memory. Of the four methods we have explored, two look especially promising - one based on the quadratic programming, and the other one being a specific discrete version of the gradient descent. The latter method provides a slightly lower memory capacity (at the same fidelity) then the former one, but it allows local recording, which may be more readily implemented in nanoelectronic hardware. Most importantly, at the synchronous retrieval, both methods provide a capacity higher than that of the well-known Ternary Content-Addressable Memories with the same number of nonvolatile memory cells (e.g., memristors), though the input noise immunity of the CrossNet memories is somewhat lower. |
| Tasks | |
| Published | 2017-07-12 |
| URL | http://arxiv.org/abs/1707.03855v1 |
| http://arxiv.org/pdf/1707.03855v1.pdf | |
| PWC | https://paperswithcode.com/paper/capacity-fidelity-and-noise-tolerance-of |
| Repo | |
| Framework | |
The Dependence of Machine Learning on Electronic Medical Record Quality
| Title | The Dependence of Machine Learning on Electronic Medical Record Quality |
| Authors | Long Ho, David Ledbetter, Melissa Aczon, Randall Wetzel |
| Abstract | There is growing interest in applying machine learning methods to Electronic Medical Records (EMR). Across different institutions, however, EMR quality can vary widely. This work investigated the impact of this disparity on the performance of three advanced machine learning algorithms: logistic regression, multilayer perceptron, and recurrent neural network. The EMR disparity was emulated using different permutations of the EMR collected at Children’s Hospital Los Angeles (CHLA) Pediatric Intensive Care Unit (PICU) and Cardiothoracic Intensive Care Unit (CTICU). The algorithms were trained using patients from the PICU to predict in-ICU mortality for patients in a held out set of PICU and CTICU patients. The disparate patient populations between the PICU and CTICU provide an estimate of generalization errors across different ICUs. We quantified and evaluated the generalization of these algorithms on varying EMR size, input types, and fidelity of data. |
| Tasks | |
| Published | 2017-03-23 |
| URL | http://arxiv.org/abs/1703.08251v1 |
| http://arxiv.org/pdf/1703.08251v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-dependence-of-machine-learning-on |
| Repo | |
| Framework | |
Real Multi-Sense or Pseudo Multi-Sense: An Approach to Improve Word Representation
| Title | Real Multi-Sense or Pseudo Multi-Sense: An Approach to Improve Word Representation |
| Authors | Haoyue Shi, Caihua Li, Junfeng Hu |
| Abstract | Previous researches have shown that learning multiple representations for polysemous words can improve the performance of word embeddings on many tasks. However, this leads to another problem. Several vectors of a word may actually point to the same meaning, namely pseudo multi-sense. In this paper, we introduce the concept of pseudo multi-sense, and then propose an algorithm to detect such cases. With the consideration of the detected pseudo multi-sense cases, we try to refine the existing word embeddings to eliminate the influence of pseudo multi-sense. Moreover, we apply our algorithm on previous released multi-sense word embeddings and tested it on artificial word similarity tasks and the analogy task. The result of the experiments shows that diminishing pseudo multi-sense can improve the quality of word representations. Thus, our method is actually an efficient way to reduce linguistic complexity. |
| Tasks | Word Embeddings |
| Published | 2017-01-06 |
| URL | http://arxiv.org/abs/1701.01574v1 |
| http://arxiv.org/pdf/1701.01574v1.pdf | |
| PWC | https://paperswithcode.com/paper/real-multi-sense-or-pseudo-multi-sense-an |
| Repo | |
| Framework | |
Deep Learning for Skin Lesion Classification
| Title | Deep Learning for Skin Lesion Classification |
| Authors | P. Mirunalini, Aravindan Chandrabose, Vignesh Gokul, S. M. Jaisakthi |
| Abstract | Melanoma, a malignant form of skin cancer is very threatening to life. Diagnosis of melanoma at an earlier stage is highly needed as it has a very high cure rate. Benign and malignant forms of skin cancer can be detected by analyzing the lesions present on the surface of the skin using dermoscopic images. In this work, an automated skin lesion detection system has been developed which learns the representation of the image using Google’s pretrained CNN model known as Inception-v3 \cite{cnn}. After obtaining the representation vector for our input dermoscopic images we have trained two layer feed forward neural network to classify the images as malignant or benign. The system also classifies the images based on the cause of the cancer either due to melanocytic or non-melanocytic cells using a different neural network. These classification tasks are part of the challenge organized by International Skin Imaging Collaboration (ISIC) 2017. Our system learns to classify the images based on the model built using the training images given in the challenge and the experimental results were evaluated using validation and test sets. Our system has achieved an overall accuracy of 65.8% for the validation set. |
| Tasks | Skin Lesion Classification |
| Published | 2017-03-13 |
| URL | http://arxiv.org/abs/1703.04364v1 |
| http://arxiv.org/pdf/1703.04364v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-for-skin-lesion-classification |
| Repo | |
| Framework | |
Community Question Answering Platforms vs. Twitter for Predicting Characteristics of Urban Neighbourhoods
| Title | Community Question Answering Platforms vs. Twitter for Predicting Characteristics of Urban Neighbourhoods |
| Authors | Marzieh Saeidi, Alessandro Venerandi, Licia Capra, Sebastian Riedel |
| Abstract | In this paper, we investigate whether text from a Community Question Answering (QA) platform can be used to predict and describe real-world attributes. We experiment with predicting a wide range of 62 demographic attributes for neighbourhoods of London. We use the text from QA platform of Yahoo! Answers and compare our results to the ones obtained from Twitter microblogs. Outcomes show that the correlation between the predicted demographic attributes using text from Yahoo! Answers discussions and the observed demographic attributes can reach an average Pearson correlation coefficient of \r{ho} = 0.54, slightly higher than the predictions obtained using Twitter data. Our qualitative analysis indicates that there is semantic relatedness between the highest correlated terms extracted from both datasets and their relative demographic attributes. Furthermore, the correlations highlight the different natures of the information contained in Yahoo! Answers and Twitter. While the former seems to offer a more encyclopedic content, the latter provides information related to the current sociocultural aspects or phenomena. |
| Tasks | Community Question Answering, Question Answering |
| Published | 2017-01-17 |
| URL | http://arxiv.org/abs/1701.04653v1 |
| http://arxiv.org/pdf/1701.04653v1.pdf | |
| PWC | https://paperswithcode.com/paper/community-question-answering-platforms-vs |
| Repo | |
| Framework | |
Exchangeable modelling of relational data: checking sparsity, train-test splitting, and sparse exchangeable Poisson matrix factorization
| Title | Exchangeable modelling of relational data: checking sparsity, train-test splitting, and sparse exchangeable Poisson matrix factorization |
| Authors | Victor Veitch, Ekansh Sharma, Zacharie Naulet, Daniel M. Roy |
| Abstract | A variety of machine learning tasks—e.g., matrix factorization, topic modelling, and feature allocation—can be viewed as learning the parameters of a probability distribution over bipartite graphs. Recently, a new class of models for networks, the sparse exchangeable graphs, have been introduced to resolve some important pathologies of traditional approaches to statistical network modelling; most notably, the inability to model sparsity (in the asymptotic sense). The present paper explains some practical insights arising from this work. We first show how to check if sparsity is relevant for modelling a given (fixed size) dataset by using network subsampling to identify a simple signature of sparsity. We discuss the implications of the (sparse) exchangeable subsampling theory for test-train dataset splitting; we argue common approaches can lead to biased results, and we propose a principled alternative. Finally, we study sparse exchangeable Poisson matrix factorization as a worked example. In particular, we show how to adapt mean field variational inference to the sparse exchangeable setting, allowing us to scale inference to huge datasets. |
| Tasks | |
| Published | 2017-12-06 |
| URL | http://arxiv.org/abs/1712.02311v1 |
| http://arxiv.org/pdf/1712.02311v1.pdf | |
| PWC | https://paperswithcode.com/paper/exchangeable-modelling-of-relational-data |
| Repo | |
| Framework | |
Effective and Extensible Feature Extraction Method Using Genetic Algorithm-Based Frequency-Domain Feature Search for Epileptic EEG Multi-classification
| Title | Effective and Extensible Feature Extraction Method Using Genetic Algorithm-Based Frequency-Domain Feature Search for Epileptic EEG Multi-classification |
| Authors | Tingxi Wen, Zhongnan Zhang |
| Abstract | In this paper, a genetic algorithm-based frequency-domain feature search (GAFDS) method is proposed for the electroencephalogram (EEG) analysis of epilepsy. In this method, frequency-domain features are first searched and then combined with nonlinear features. Subsequently, these features are selected and optimized to classify EEG signals. The extracted features are analyzed experimentally. The features extracted by GAFDS show remarkable independence, and they are superior to the nonlinear features in terms of the ratio of inter-class distance and intra-class distance. Moreover, the proposed feature search method can additionally search for features of instantaneous frequency in a signal after Hilbert transformation. The classification results achieved using these features are reasonable, thus, GAFDS exhibits good extensibility. Multiple classic classifiers (i.e., $k$-nearest neighbor, linear discriminant analysis, decision tree, AdaBoost, multilayer perceptron, and Na"ive Bayes) achieve good results by using the features generated by GAFDS method and the optimized selection. Specifically, the accuracies for the two-classification and three-classification problems may reach up to 99% and 97%, respectively. Results of several cross-validation experiments illustrate that GAFDS is effective in feature extraction for EEG classification. Therefore, the proposed feature selection and optimization model can improve classification accuracy. |
| Tasks | EEG, Feature Selection |
| Published | 2017-01-22 |
| URL | http://arxiv.org/abs/1701.06120v1 |
| http://arxiv.org/pdf/1701.06120v1.pdf | |
| PWC | https://paperswithcode.com/paper/effective-and-extensible-feature-extraction |
| Repo | |
| Framework | |
A Mixture Model for Learning Multi-Sense Word Embeddings
| Title | A Mixture Model for Learning Multi-Sense Word Embeddings |
| Authors | Dai Quoc Nguyen, Dat Quoc Nguyen, Ashutosh Modi, Stefan Thater, Manfred Pinkal |
| Abstract | Word embeddings are now a standard technique for inducing meaning representations for words. For getting good representations, it is important to take into account different senses of a word. In this paper, we propose a mixture model for learning multi-sense word embeddings. Our model generalizes the previous works in that it allows to induce different weights of different senses of a word. The experimental results show that our model outperforms previous models on standard evaluation tasks. |
| Tasks | Word Embeddings |
| Published | 2017-06-15 |
| URL | http://arxiv.org/abs/1706.05111v1 |
| http://arxiv.org/pdf/1706.05111v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-mixture-model-for-learning-multi-sense-word |
| Repo | |
| Framework | |
Spatial Mapping with Gaussian Processes and Nonstationary Fourier Features
| Title | Spatial Mapping with Gaussian Processes and Nonstationary Fourier Features |
| Authors | Jean-Francois Ton, Seth Flaxman, Dino Sejdinovic, Samir Bhatt |
| Abstract | The use of covariance kernels is ubiquitous in the field of spatial statistics. Kernels allow data to be mapped into high-dimensional feature spaces and can thus extend simple linear additive methods to nonlinear methods with higher order interactions. However, until recently, there has been a strong reliance on a limited class of stationary kernels such as the Matern or squared exponential, limiting the expressiveness of these modelling approaches. Recent machine learning research has focused on spectral representations to model arbitrary stationary kernels and introduced more general representations that include classes of nonstationary kernels. In this paper, we exploit the connections between Fourier feature representations, Gaussian processes and neural networks to generalise previous approaches and develop a simple and efficient framework to learn arbitrarily complex nonstationary kernel functions directly from the data, while taking care to avoid overfitting using state-of-the-art methods from deep learning. We highlight the very broad array of kernel classes that could be created within this framework. We apply this to a time series dataset and a remote sensing problem involving land surface temperature in Eastern Africa. We show that without increasing the computational or storage complexity, nonstationary kernels can be used to improve generalisation performance and provide more interpretable results. |
| Tasks | Gaussian Processes, Time Series |
| Published | 2017-11-15 |
| URL | http://arxiv.org/abs/1711.05615v1 |
| http://arxiv.org/pdf/1711.05615v1.pdf | |
| PWC | https://paperswithcode.com/paper/spatial-mapping-with-gaussian-processes-and |
| Repo | |
| Framework | |
Bringing Background into the Foreground: Making All Classes Equal in Weakly-supervised Video Semantic Segmentation
| Title | Bringing Background into the Foreground: Making All Classes Equal in Weakly-supervised Video Semantic Segmentation |
| Authors | Fatemeh Sadat Saleh, Mohammad Sadegh Aliakbarian, Mathieu Salzmann, Lars Petersson, Jose M. Alvarez |
| Abstract | Pixel-level annotations are expensive and time-consuming to obtain. Hence, weak supervision using only image tags could have a significant impact in semantic segmentation. Recent years have seen great progress in weakly-supervised semantic segmentation, whether from a single image or from videos. However, most existing methods are designed to handle a single background class. In practical applications, such as autonomous navigation, it is often crucial to reason about multiple background classes. In this paper, we introduce an approach to doing so by making use of classifier heatmaps. We then develop a two-stream deep architecture that jointly leverages appearance and motion, and design a loss based on our heatmaps to train it. Our experiments demonstrate the benefits of our classifier heatmaps and of our two-stream architecture on challenging urban scene datasets and on the YouTube-Objects benchmark, where we obtain state-of-the-art results. |
| Tasks | Autonomous Navigation, Semantic Segmentation, Video Semantic Segmentation, Weakly-Supervised Semantic Segmentation |
| Published | 2017-08-15 |
| URL | http://arxiv.org/abs/1708.04400v1 |
| http://arxiv.org/pdf/1708.04400v1.pdf | |
| PWC | https://paperswithcode.com/paper/bringing-background-into-the-foreground |
| Repo | |
| Framework | |
Support Vector Machines and generalisation in HEP
| Title | Support Vector Machines and generalisation in HEP |
| Authors | Adrian Bevan, Rodrigo Gamboa Goñi, Jon Hays, Tom Stevenson |
| Abstract | We review the concept of Support Vector Machines (SVMs) and discuss examples of their use in a number of scenarios. Several SVM implementations have been used in HEP and we exemplify this algorithm using the Toolkit for Multivariate Analysis (TMVA) implementation. We discuss examples relevant to HEP including background suppression for $H\to\tau^+\tau^-$ at the LHC with several different kernel functions. Performance benchmarking leads to the issue of generalisation of hyper-parameter selection. The avoidance of fine tuning (over training or over fitting) in MVA hyper-parameter optimisation, i.e. the ability to ensure generalised performance of an MVA that is independent of the training, validation and test samples, is of utmost importance. We discuss this issue and compare and contrast performance of hold-out and k-fold cross-validation. We have extended the SVM functionality and introduced tools to facilitate cross validation in TMVA and present results based on these improvements. |
| Tasks | |
| Published | 2017-02-15 |
| URL | http://arxiv.org/abs/1702.04686v1 |
| http://arxiv.org/pdf/1702.04686v1.pdf | |
| PWC | https://paperswithcode.com/paper/support-vector-machines-and-generalisation-in |
| Repo | |
| Framework | |
Beating Atari with Natural Language Guided Reinforcement Learning
| Title | Beating Atari with Natural Language Guided Reinforcement Learning |
| Authors | Russell Kaplan, Christopher Sauer, Alexander Sosa |
| Abstract | We introduce the first deep reinforcement learning agent that learns to beat Atari games with the aid of natural language instructions. The agent uses a multimodal embedding between environment observations and natural language to self-monitor progress through a list of English instructions, granting itself reward for completing instructions in addition to increasing the game score. Our agent significantly outperforms Deep Q-Networks (DQNs), Asynchronous Advantage Actor-Critic (A3C) agents, and the best agents posted to OpenAI Gym on what is often considered the hardest Atari 2600 environment: Montezuma’s Revenge. |
| Tasks | Atari Games, Montezuma’s Revenge |
| Published | 2017-04-18 |
| URL | http://arxiv.org/abs/1704.05539v1 |
| http://arxiv.org/pdf/1704.05539v1.pdf | |
| PWC | https://paperswithcode.com/paper/beating-atari-with-natural-language-guided |
| Repo | |
| Framework | |
Micro-Objective Learning : Accelerating Deep Reinforcement Learning through the Discovery of Continuous Subgoals
| Title | Micro-Objective Learning : Accelerating Deep Reinforcement Learning through the Discovery of Continuous Subgoals |
| Authors | Sungtae Lee, Sang-Woo Lee, Jinyoung Choi, Dong-Hyun Kwak, Byoung-Tak Zhang |
| Abstract | Recently, reinforcement learning has been successfully applied to the logical game of Go, various Atari games, and even a 3D game, Labyrinth, though it continues to have problems in sparse reward settings. It is difficult to explore, but also difficult to exploit, a small number of successes when learning policy. To solve this issue, the subgoal and option framework have been proposed. However, discovering subgoals online is too expensive to be used to learn options in large state spaces. We propose Micro-objective learning (MOL) to solve this problem. The main idea is to estimate how important a state is while training and to give an additional reward proportional to its importance. We evaluated our algorithm in two Atari games: Montezuma’s Revenge and Seaquest. With three experiments to each game, MOL significantly improved the baseline scores. Especially in Montezuma’s Revenge, MOL achieved two times better results than the previous state-of-the-art model. |
| Tasks | Atari Games, Game of Go, Montezuma’s Revenge |
| Published | 2017-03-11 |
| URL | http://arxiv.org/abs/1703.03933v1 |
| http://arxiv.org/pdf/1703.03933v1.pdf | |
| PWC | https://paperswithcode.com/paper/micro-objective-learning-accelerating-deep |
| Repo | |
| Framework | |
