Paper Group ANR 131
Kernel Distillation for Fast Gaussian Processes Prediction. Sparse Gaussian ICA. Comparison of Classification Algorithms Used Medical Documents Categorization. Accurate Weakly Supervised Deep Lesion Segmentation on CT Scans: Self-Paced 3D Mask Generation from RECIST. Deep Learning Angiography (DLA): Three-dimensional C-arm Cone Beam CT Angiography …
Kernel Distillation for Fast Gaussian Processes Prediction
Title | Kernel Distillation for Fast Gaussian Processes Prediction |
Authors | Congzheng Song, Yiming Sun |
Abstract | Gaussian processes (GPs) are flexible models that can capture complex structure in large-scale dataset due to their non-parametric nature. However, the usage of GPs in real-world application is limited due to their high computational cost at inference time. In this paper, we introduce a new framework, \textit{kernel distillation}, to approximate a fully trained teacher GP model with kernel matrix of size $n\times n$ for $n$ training points. We combine inducing points method with sparse low-rank approximation in the distillation procedure. The distilled student GP model only costs $O(m^2)$ storage for $m$ inducing points where $m \ll n$ and improves the inference time complexity. We demonstrate empirically that kernel distillation provides better trade-off between the prediction time and the test performance compared to the alternatives. |
Tasks | Gaussian Processes |
Published | 2018-01-31 |
URL | http://arxiv.org/abs/1801.10273v2 |
http://arxiv.org/pdf/1801.10273v2.pdf | |
PWC | https://paperswithcode.com/paper/kernel-distillation-for-fast-gaussian |
Repo | |
Framework | |
Sparse Gaussian ICA
Title | Sparse Gaussian ICA |
Authors | Nilin Abrahamsen, Philippe Rigollet |
Abstract | Independent component analysis (ICA) is a cornerstone of modern data analysis. Its goal is to recover a latent random vector S with independent components from samples of X=AS where A is an unknown mixing matrix. Critically, all existing methods for ICA rely on and exploit strongly the assumption that S is not Gaussian as otherwise A becomes unidentifiable. In this paper, we show that in fact one can handle the case of Gaussian components by imposing structure on the matrix A. Specifically, we assume that A is sparse and generic in the sense that it is generated from a sparse Bernoulli-Gaussian ensemble. Under this condition, we give an efficient algorithm to recover the columns of A given only the covariance matrix of X as input even when S has several Gaussian components. |
Tasks | |
Published | 2018-04-02 |
URL | http://arxiv.org/abs/1804.00408v2 |
http://arxiv.org/pdf/1804.00408v2.pdf | |
PWC | https://paperswithcode.com/paper/sparse-gaussian-ica |
Repo | |
Framework | |
Comparison of Classification Algorithms Used Medical Documents Categorization
Title | Comparison of Classification Algorithms Used Medical Documents Categorization |
Authors | Durmus Ozkan Sahin, Erdal Kilic |
Abstract | Volume of text based documents have been increasing day by day. Medical documents are located within this growing text documents. In this study, the techniques used for text classification applied on medical documents and evaluated classification performance. Used data sets are multi class and multi labelled. Chi Square (CHI) technique was used for feature selection also SMO, NB, C4.5, RF and KNN algorithms was used for classification. The aim of this study, success of various classifiers is evaluated on multi class and multi label data sets consisting of medical documents. The first 400 features, while the most successful in the KNN classifier, feature number 400 and after the SMO has become the most successful classifier. |
Tasks | Feature Selection, Text Classification |
Published | 2018-11-02 |
URL | http://arxiv.org/abs/1811.00869v1 |
http://arxiv.org/pdf/1811.00869v1.pdf | |
PWC | https://paperswithcode.com/paper/comparison-of-classification-algorithms-used |
Repo | |
Framework | |
Accurate Weakly Supervised Deep Lesion Segmentation on CT Scans: Self-Paced 3D Mask Generation from RECIST
Title | Accurate Weakly Supervised Deep Lesion Segmentation on CT Scans: Self-Paced 3D Mask Generation from RECIST |
Authors | Jinzheng Cai, Youbao Tang, Le Lu, Adam P. Harrison, Ke Yan, Jing Xiao, Lin Yang, Ronald M. Summers |
Abstract | Volumetric lesion segmentation via medical imaging is a powerful means to precisely assess multiple time-point lesion/tumor changes. Because manual 3D segmentation is prohibitively time consuming and requires radiological experience, current practices rely on an imprecise surrogate called response evaluation criteria in solid tumors (RECIST). Despite their coarseness, RECIST marks are commonly found in current hospital picture and archiving systems (PACS), meaning they can provide a potentially powerful, yet extraordinarily challenging, source of weak supervision for full 3D segmentation. Toward this end, we introduce a convolutional neural network based weakly supervised self-paced segmentation (WSSS) method to 1) generate the initial lesion segmentation on the axial RECIST-slice; 2) learn the data distribution on RECIST-slices; 3) adapt to segment the whole volume slice by slice to finally obtain a volumetric segmentation. In addition, we explore how super-resolution images (2~5 times beyond the physical CT imaging), generated from a proposed stacked generative adversarial network, can aid the WSSS performance. We employ the DeepLesion dataset, a comprehensive CT-image lesion dataset of 32,735 PACS-bookmarked findings, which include lesions, tumors, and lymph nodes of varying sizes, categories, body regions and surrounding contexts. These are drawn from 10,594 studies of 4,459 patients. We also validate on a lymph-node dataset, where 3D ground truth masks are available for all images. For the DeepLesion dataset, we report mean Dice coefficients of 93% on RECIST-slices and 76% in 3D lesion volumes. We further validate using a subjective user study, where an experienced radiologist accepted our WSSS-generated lesion segmentation results with a high probability of 92.4%. |
Tasks | Lesion Segmentation, Super-Resolution |
Published | 2018-01-25 |
URL | http://arxiv.org/abs/1801.08614v1 |
http://arxiv.org/pdf/1801.08614v1.pdf | |
PWC | https://paperswithcode.com/paper/accurate-weakly-supervised-deep-lesion |
Repo | |
Framework | |
Deep Learning Angiography (DLA): Three-dimensional C-arm Cone Beam CT Angiography Using Deep Learning
Title | Deep Learning Angiography (DLA): Three-dimensional C-arm Cone Beam CT Angiography Using Deep Learning |
Authors | Juan C. Montoya, Yinsheng Li, Charles Strother, Guang-Hong Chen |
Abstract | Background and Purpose: Our purpose was to develop a deep learning angiography (DLA) method to generate 3D cerebral angiograms from a single contrast-enhanced acquisition. Material and Methods: Under an approved IRB protocol 105 3D-DSA exams were randomly selected from an internal database. All were acquired using a clinical system (Axiom Artis zee, Siemens Healthineers) in conjunction with a standard injection protocol. More than 150 million labeled voxels from 35 subjects were used for training. A deep convolutional neural network was trained to classify each image voxel into three tissue types (vasculature, bone and soft tissue). The trained DLA model was then applied for tissue classification in a validation cohort of 8 subjects and a final testing cohort consisting of the remaining 62 subjects. The final vasculature tissue class was used to generate the 3D-DLA images. To quantify the generalization error of the trained model, accuracy, sensitivity, precision and F1-scores were calculated for vasculature classification in relevant anatomy. The 3D-DLA and clinical 3D-DSA images were subject to a qualitative assessment for the presence of inter-sweep motion artifacts. Results: Vasculature classification accuracy and 95% CI in the testing dataset was 98.7% ([98.3, 99.1] %). No residual signal from osseous structures was observed for all 3D-DLA testing cases except for small regions in the otic capsule and nasal cavity compared to 37% (23/62) of the 3D-DSAs. Conclusion: DLA accurately recreated the vascular anatomy of the 3D-DSA reconstructions without mask. DLA reduced mis-registration artifacts induced by inter-sweep motion. DLA reduces radiation exposure required to obtain clinically useful 3D-DSA |
Tasks | |
Published | 2018-01-26 |
URL | http://arxiv.org/abs/1801.09520v1 |
http://arxiv.org/pdf/1801.09520v1.pdf | |
PWC | https://paperswithcode.com/paper/deep-learning-angiography-dla-three |
Repo | |
Framework | |
Combining Multi-level Contexts of Superpixel using Convolutional Neural Networks to perform Natural Scene Labeling
Title | Combining Multi-level Contexts of Superpixel using Convolutional Neural Networks to perform Natural Scene Labeling |
Authors | Aritra Das, Swarnendu Ghosh, Ritesh Sarkhel, Sandipan Choudhuri, Nibaran Das, Mita Nasipuri |
Abstract | Modern deep learning algorithms have triggered various image segmentation approaches. However most of them deal with pixel based segmentation. However, superpixels provide a certain degree of contextual information while reducing computation cost. In our approach, we have performed superpixel level semantic segmentation considering 3 various levels as neighbours for semantic contexts. Furthermore, we have enlisted a number of ensemble approaches like max-voting and weighted-average. We have also used the Dempster-Shafer theory of uncertainty to analyze confusion among various classes. Our method has proved to be superior to a number of different modern approaches on the same dataset. |
Tasks | Scene Labeling, Semantic Segmentation |
Published | 2018-03-14 |
URL | http://arxiv.org/abs/1803.05200v1 |
http://arxiv.org/pdf/1803.05200v1.pdf | |
PWC | https://paperswithcode.com/paper/combining-multi-level-contexts-of-superpixel |
Repo | |
Framework | |
The State of the Art in Developing Fuzzy Ontologies: A Survey
Title | The State of the Art in Developing Fuzzy Ontologies: A Survey |
Authors | Zahra Riahi Samani, Mehrnoush Shamsfard |
Abstract | Conceptual formalism supported by typical ontologies may not be sufficient to represent uncertainty information which is caused due to the lack of clear cut boundaries between concepts of a domain. Fuzzy ontologies are proposed to offer a way to deal with this uncertainty. This paper describes the state of the art in developing fuzzy ontologies. The survey is produced by studying about 35 works on developing fuzzy ontologies from a batch of 100 articles in the field of fuzzy ontologies. |
Tasks | |
Published | 2018-05-06 |
URL | http://arxiv.org/abs/1805.02290v1 |
http://arxiv.org/pdf/1805.02290v1.pdf | |
PWC | https://paperswithcode.com/paper/the-state-of-the-art-in-developing-fuzzy |
Repo | |
Framework | |
Towards Compositional Distributional Discourse Analysis
Title | Towards Compositional Distributional Discourse Analysis |
Authors | Bob Coecke, Giovanni de Felice, Dan Marsden, Alexis Toumi |
Abstract | Categorical compositional distributional semantics provide a method to derive the meaning of a sentence from the meaning of its individual words: the grammatical reduction of a sentence automatically induces a linear map for composing the word vectors obtained from distributional semantics. In this paper, we extend this passage from word-to-sentence to sentence-to-discourse composition. To achieve this we introduce a notion of basic anaphoric discourses as a mid-level representation between natural language discourse formalised in terms of basic discourse representation structures (DRS); and knowledge base queries over the Semantic Web as described by basic graph patterns in the Resource Description Framework (RDF). This provides a high-level specification for compositional algorithms for question answering and anaphora resolution, and allows us to give a picture of natural language understanding as a process involving both statistical and logical resources. |
Tasks | Question Answering |
Published | 2018-11-08 |
URL | http://arxiv.org/abs/1811.03277v1 |
http://arxiv.org/pdf/1811.03277v1.pdf | |
PWC | https://paperswithcode.com/paper/towards-compositional-distributional |
Repo | |
Framework | |
An introduction to domain adaptation and transfer learning
Title | An introduction to domain adaptation and transfer learning |
Authors | Wouter M. Kouw, Marco Loog |
Abstract | In machine learning, if the training data is an unbiased sample of an underlying distribution, then the learned classification function will make accurate predictions for new samples. However, if the training data is not an unbiased sample, then there will be differences between how the training data is distributed and how the test data is distributed. Standard classifiers cannot cope with changes in data distributions between training and test phases, and will not perform well. Domain adaptation and transfer learning are sub-fields within machine learning that are concerned with accounting for these types of changes. Here, we present an introduction to these fields, guided by the question: when and how can a classifier generalize from a source to a target domain? We will start with a brief introduction into risk minimization, and how transfer learning and domain adaptation expand upon this framework. Following that, we discuss three special cases of data set shift, namely prior, covariate and concept shift. For more complex domain shifts, there are a wide variety of approaches. These are categorized into: importance-weighting, subspace mapping, domain-invariant spaces, feature augmentation, minimax estimators and robust algorithms. A number of points will arise, which we will discuss in the last section. We conclude with the remark that many open questions will have to be addressed before transfer learners and domain-adaptive classifiers become practical. |
Tasks | Domain Adaptation, Transfer Learning |
Published | 2018-12-31 |
URL | http://arxiv.org/abs/1812.11806v2 |
http://arxiv.org/pdf/1812.11806v2.pdf | |
PWC | https://paperswithcode.com/paper/an-introduction-to-domain-adaptation-and |
Repo | |
Framework | |
End-to-End Learning via a Convolutional Neural Network for Cancer Cell Line Classification
Title | End-to-End Learning via a Convolutional Neural Network for Cancer Cell Line Classification |
Authors | Darlington Ahiale Akogo, Xavier-Lewis Palmer |
Abstract | Computer Vision for automated analysis of cells and tissues usually include extracting features from images before analyzing such features via various Machine Learning and Machine Vision algorithms. We developed a Convolutional Neural Network model that classifies MDA-MB-468 and MCF7 breast cancer cells via brightfield microscopy images without the need of any prior feature extraction. Our 6-layer Convolutional Neural Network is directly trained, validated and tested on 1,241 images of MDA-MB-468 and MCF7 breast cancer cell line in an end-to-end fashion, allowing a system to distinguish between different cancer cell types. The model takes in as input imaged breast cancer cell line and then outputs the cell line type (MDA-MB-468 or MCF7) as predicted probabilities between the two classes. Our model scored a 99% Accuracy. |
Tasks | |
Published | 2018-07-25 |
URL | http://arxiv.org/abs/1807.10638v1 |
http://arxiv.org/pdf/1807.10638v1.pdf | |
PWC | https://paperswithcode.com/paper/end-to-end-learning-via-a-convolutional |
Repo | |
Framework | |
Optimizing Agent Behavior over Long Time Scales by Transporting Value
Title | Optimizing Agent Behavior over Long Time Scales by Transporting Value |
Authors | Chia-Chun Hung, Timothy Lillicrap, Josh Abramson, Yan Wu, Mehdi Mirza, Federico Carnevale, Arun Ahuja, Greg Wayne |
Abstract | Humans spend a remarkable fraction of waking life engaged in acts of “mental time travel”. We dwell on our actions in the past and experience satisfaction or regret. More than merely autobiographical storytelling, we use these event recollections to change how we will act in similar scenarios in the future. This process endows us with a computationally important ability to link actions and consequences across long spans of time, which figures prominently in addressing the problem of long-term temporal credit assignment; in artificial intelligence (AI) this is the question of how to evaluate the utility of the actions within a long-duration behavioral sequence leading to success or failure in a task. Existing approaches to shorter-term credit assignment in AI cannot solve tasks with long delays between actions and consequences. Here, we introduce a new paradigm for reinforcement learning where agents use recall of specific memories to credit actions from the past, allowing them to solve problems that are intractable for existing algorithms. This paradigm broadens the scope of problems that can be investigated in AI and offers a mechanistic account of behaviors that may inspire computational models in neuroscience, psychology, and behavioral economics. |
Tasks | |
Published | 2018-10-15 |
URL | http://arxiv.org/abs/1810.06721v2 |
http://arxiv.org/pdf/1810.06721v2.pdf | |
PWC | https://paperswithcode.com/paper/optimizing-agent-behavior-over-long-time |
Repo | |
Framework | |
Assessing the effect of advertising expenditures upon sales: a Bayesian structural time series model
Title | Assessing the effect of advertising expenditures upon sales: a Bayesian structural time series model |
Authors | Víctor Gallego, Pablo Suárez-García, Pablo Angulo, David Gómez-Ullate |
Abstract | We propose a robust implementation of the Nerlove–Arrow model using a Bayesian structural time series model to explain the relationship between advertising expenditures of a country-wide fast-food franchise network with its weekly sales. Thanks to the flexibility and modularity of the model, it is well suited to generalization to other markets or situations. Its Bayesian nature facilitates incorporating \emph{a priori} information (the manager’s views), which can be updated with relevant data. This aspect of the model will be used to present a strategy of budget scheduling across time and channels. |
Tasks | Time Series |
Published | 2018-01-09 |
URL | https://arxiv.org/abs/1801.03050v3 |
https://arxiv.org/pdf/1801.03050v3.pdf | |
PWC | https://paperswithcode.com/paper/assessing-the-effect-of-advertising |
Repo | |
Framework | |
ASR-free CNN-DTW keyword spotting using multilingual bottleneck features for almost zero-resource languages
Title | ASR-free CNN-DTW keyword spotting using multilingual bottleneck features for almost zero-resource languages |
Authors | Raghav Menon, Herman Kamper, Emre Yilmaz, John Quinn, Thomas Niesler |
Abstract | We consider multilingual bottleneck features (BNFs) for nearly zero-resource keyword spotting. This forms part of a United Nations effort using keyword spotting to support humanitarian relief programmes in parts of Africa where languages are severely under-resourced. We use 1920 isolated keywords (40 types, 34 minutes) as exemplars for dynamic time warping (DTW) template matching, which is performed on a much larger body of untranscribed speech. These DTW costs are used as targets for a convolutional neural network (CNN) keyword spotter, giving a much faster system than direct DTW. Here we consider how available data from well-resourced languages can improve this CNN-DTW approach. We show that multilingual BNFs trained on ten languages improve the area under the ROC curve of a CNN-DTW system by 10.9% absolute relative to the MFCC baseline. By combining low-resource DTW-based supervision with information from well-resourced languages, CNN-DTW is a competitive option for low-resource keyword spotting. |
Tasks | Keyword Spotting |
Published | 2018-07-23 |
URL | http://arxiv.org/abs/1807.08666v1 |
http://arxiv.org/pdf/1807.08666v1.pdf | |
PWC | https://paperswithcode.com/paper/asr-free-cnn-dtw-keyword-spotting-using |
Repo | |
Framework | |
Face Recognition Techniques: A Survey
Title | Face Recognition Techniques: A Survey |
Authors | Raunak Dave, Ankit Vyas, Nikita P Desai |
Abstract | Nowadays research has expanded to extracting auxiliary information from various biometric techniques like fingerprints, face, iris, palm and voice . This information contains some major features like gender, age, beard, mustache, scars, height, hair, skin color, glasses, weight, facial marks and tattoos. All this information contributes strongly to identification of human. The major challenges that come across face recognition are to find age & gender of the person. This paper contributes a survey of various face recognition techniques for finding the age and gender. The existing techniques are discussed based on their performances. This paper also provides future directions for further research. |
Tasks | Face Recognition |
Published | 2018-03-20 |
URL | http://arxiv.org/abs/1803.07288v5 |
http://arxiv.org/pdf/1803.07288v5.pdf | |
PWC | https://paperswithcode.com/paper/face-recognition-techniques-a-survey |
Repo | |
Framework | |
Improving Sentiment Analysis in Arabic Using Word Representation
Title | Improving Sentiment Analysis in Arabic Using Word Representation |
Authors | Abdulaziz M. Alayba, Vasile Palade, Matthew England, Rahat Iqbal |
Abstract | The complexities of Arabic language in morphology, orthography and dialects makes sentiment analysis for Arabic more challenging. Also, text feature extraction from short messages like tweets, in order to gauge the sentiment, makes this task even more difficult. In recent years, deep neural networks were often employed and showed very good results in sentiment classification and natural language processing applications. Word embedding, or word distributing approach, is a current and powerful tool to capture together the closest words from a contextual text. In this paper, we describe how we construct Word2Vec models from a large Arabic corpus obtained from ten newspapers in different Arab countries. By applying different machine learning algorithms and convolutional neural networks with different text feature selections, we report improved accuracy of sentiment classification (91%-95%) on our publicly available Arabic language health sentiment dataset [1] |
Tasks | Sentiment Analysis |
Published | 2018-02-28 |
URL | http://arxiv.org/abs/1803.00124v2 |
http://arxiv.org/pdf/1803.00124v2.pdf | |
PWC | https://paperswithcode.com/paper/improving-sentiment-analysis-in-arabic-using |
Repo | |
Framework | |