Paper Group ANR 227
Learning convolutional neural network to maximize Pos@Top performance measure. A Neural Autoregressive Approach to Collaborative Filtering. Dimensionality Reduction via Regression in Hyperspectral Imagery. Continuous occurrence theory. Gland Instance Segmentation by Deep Multichannel Neural Networks. Measuring the State of the Art of Automated Path …
Learning convolutional neural network to maximize Pos@Top performance measure
| Title | Learning convolutional neural network to maximize Pos@Top performance measure |
| Authors | Yanyan Geng, Ru-Ze Liang, Weizhi Li, Jingbin Wang, Gaoyuan Liang, Chenhao Xu, Jing-Yan Wang |
| Abstract | In the machine learning problems, the performance measure is used to evaluate the machine learning models. Recently, the number positive data points ranked at the top positions (Pos@Top) has been a popular performance measure in the machine learning community. In this paper, we propose to learn a convolutional neural network (CNN) model to maximize the Pos@Top performance measure. The CNN model is used to represent the multi-instance data point, and a classifier function is used to predict the label from the its CNN representation. We propose to minimize the loss function of Pos@Top over a training set to learn the filters of CNN and the classifier parameter. The classifier parameter vector is solved by the Lagrange multiplier method, and the filters are updated by the gradient descent method alternately in an iterative algorithm. Experiments over benchmark data sets show that the proposed method outperforms the state-of-the-art Pos@Top maximization methods. |
| Tasks | |
| Published | 2016-09-27 |
| URL | http://arxiv.org/abs/1609.08417v3 |
| http://arxiv.org/pdf/1609.08417v3.pdf | |
| PWC | https://paperswithcode.com/paper/learning-convolutional-neural-network-to |
| Repo | |
| Framework | |
A Neural Autoregressive Approach to Collaborative Filtering
| Title | A Neural Autoregressive Approach to Collaborative Filtering |
| Authors | Yin Zheng, Bangsheng Tang, Wenkui Ding, Hanning Zhou |
| Abstract | This paper proposes CF-NADE, a neural autoregressive architecture for collaborative filtering (CF) tasks, which is inspired by the Restricted Boltzmann Machine (RBM) based CF model and the Neural Autoregressive Distribution Estimator (NADE). We first describe the basic CF-NADE model for CF tasks. Then we propose to improve the model by sharing parameters between different ratings. A factored version of CF-NADE is also proposed for better scalability. Furthermore, we take the ordinal nature of the preferences into consideration and propose an ordinal cost to optimize CF-NADE, which shows superior performance. Finally, CF-NADE can be extended to a deep model, with only moderately increased computational complexity. Experimental results show that CF-NADE with a single hidden layer beats all previous state-of-the-art methods on MovieLens 1M, MovieLens 10M, and Netflix datasets, and adding more hidden layers can further improve the performance. |
| Tasks | |
| Published | 2016-05-31 |
| URL | http://arxiv.org/abs/1605.09477v1 |
| http://arxiv.org/pdf/1605.09477v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-neural-autoregressive-approach-to |
| Repo | |
| Framework | |
Dimensionality Reduction via Regression in Hyperspectral Imagery
| Title | Dimensionality Reduction via Regression in Hyperspectral Imagery |
| Authors | Valero Laparra, Jesus Malo, Gustau Camps-Valls |
| Abstract | This paper introduces a new unsupervised method for dimensionality reduction via regression (DRR). The algorithm belongs to the family of invertible transforms that generalize Principal Component Analysis (PCA) by using curvilinear instead of linear features. DRR identifies the nonlinear features through multivariate regression to ensure the reduction in redundancy between he PCA coefficients, the reduction of the variance of the scores, and the reduction in the reconstruction error. More importantly, unlike other nonlinear dimensionality reduction methods, the invertibility, volume-preservation, and straightforward out-of-sample extension, makes DRR interpretable and easy to apply. The properties of DRR enable learning a more broader class of data manifolds than the recently proposed Non-linear Principal Components Analysis (NLPCA) and Principal Polynomial Analysis (PPA). We illustrate the performance of the representation in reducing the dimensionality of remote sensing data. In particular, we tackle two common problems: processing very high dimensional spectral information such as in hyperspectral image sounding data, and dealing with spatial-spectral image patches of multispectral images. Both settings pose collinearity and ill-determination problems. Evaluation of the expressive power of the features is assessed in terms of truncation error, estimating atmospheric variables, and surface land cover classification error. Results show that DRR outperforms linear PCA and recently proposed invertible extensions based on neural networks (NLPCA) and univariate regressions (PPA). |
| Tasks | Dimensionality Reduction |
| Published | 2016-01-31 |
| URL | http://arxiv.org/abs/1602.00214v1 |
| http://arxiv.org/pdf/1602.00214v1.pdf | |
| PWC | https://paperswithcode.com/paper/dimensionality-reduction-via-regression-in |
| Repo | |
| Framework | |
Continuous occurrence theory
| Title | Continuous occurrence theory |
| Authors | Abdorrahman Haeri |
| Abstract | Usually gradual and continuous changes in entities will lead to appear events. But usually it is supposed that an event is occurred at once. In this research an integrated framework called continuous occurrence theory (COT) is presented to investigate respective path leading to occurrence of the events in the real world. For this purpose initially fundamental concepts are defined. Afterwards, the appropriate tools such as occurrence variables computations, occurrence dependency function and occurrence model are introduced and explained in a systematic manner. Indeed, COT provides the possibility to: (a) monitor occurrence of events during time; (b) study background of the events; (c) recognize the relevant issues of each event; and (d) understand how these issues affect on the considered event. The developed framework (COT) provides the necessary context to analyze accurately continual changes of the issues and the relevant events in the various branches of science and business. Finally, typical applications of COT and an applied modeling example of it have been explained and a mathematical programming example is modeled in the occurrence based environment. |
| Tasks | |
| Published | 2016-08-06 |
| URL | http://arxiv.org/abs/1609.05228v2 |
| http://arxiv.org/pdf/1609.05228v2.pdf | |
| PWC | https://paperswithcode.com/paper/continuous-occurrence-theory |
| Repo | |
| Framework | |
Gland Instance Segmentation by Deep Multichannel Neural Networks
| Title | Gland Instance Segmentation by Deep Multichannel Neural Networks |
| Authors | Yan Xu, Yang Li, Mingyuan Liu, Yipei Wang, Yubo Fan, Maode Lai, Eric I-Chao Chang |
| Abstract | In this paper, we propose a new image instance segmentation method that segments individual glands (instances) in colon histology images. This is a task called instance segmentation that has recently become increasingly important. The problem is challenging since not only do the glands need to be segmented from the complex background, they are also required to be individually identified. Here we leverage the idea of image-to-image prediction in recent deep learning by building a framework that automatically exploits and fuses complex multichannel information, regional, location and boundary patterns in gland histology images. Our proposed system, deep multichannel framework, alleviates heavy feature design due to the use of convolutional neural networks and is able to meet multifarious requirement by altering channels. Compared to methods reported in the 2015 MICCAI Gland Segmentation Challenge and other currently prevalent methods of instance segmentation, we observe state-of-the-art results based on a number of evaluation metrics. |
| Tasks | Instance Segmentation, Semantic Segmentation |
| Published | 2016-07-17 |
| URL | http://arxiv.org/abs/1607.04889v2 |
| http://arxiv.org/pdf/1607.04889v2.pdf | |
| PWC | https://paperswithcode.com/paper/gland-instance-segmentation-by-deep-1 |
| Repo | |
| Framework | |
Measuring the State of the Art of Automated Pathway Curation Using Graph Algorithms - A Case Study of the mTOR Pathway
| Title | Measuring the State of the Art of Automated Pathway Curation Using Graph Algorithms - A Case Study of the mTOR Pathway |
| Authors | Michael Spranger, Sucheendra K. Palaniappan, Samik Ghosh |
| Abstract | This paper evaluates the difference between human pathway curation and current NLP systems. We propose graph analysis methods for quantifying the gap between human curated pathway maps and the output of state-of-the-art automatic NLP systems. Evaluation is performed on the popular mTOR pathway. Based on analyzing where current systems perform well and where they fail, we identify possible avenues for progress. |
| Tasks | |
| Published | 2016-08-12 |
| URL | http://arxiv.org/abs/1608.03767v1 |
| http://arxiv.org/pdf/1608.03767v1.pdf | |
| PWC | https://paperswithcode.com/paper/measuring-the-state-of-the-art-of-automated |
| Repo | |
| Framework | |
Grounding Dynamic Spatial Relations for Embodied (Robot) Interaction
| Title | Grounding Dynamic Spatial Relations for Embodied (Robot) Interaction |
| Authors | Michael Spranger, Jakob Suchan, Mehul Bhatt, Manfred Eppe |
| Abstract | This paper presents a computational model of the processing of dynamic spatial relations occurring in an embodied robotic interaction setup. A complete system is introduced that allows autonomous robots to produce and interpret dynamic spatial phrases (in English) given an environment of moving objects. The model unites two separate research strands: computational cognitive semantics and on commonsense spatial representation and reasoning. The model for the first time demonstrates an integration of these different strands. |
| Tasks | |
| Published | 2016-07-26 |
| URL | http://arxiv.org/abs/1607.07565v1 |
| http://arxiv.org/pdf/1607.07565v1.pdf | |
| PWC | https://paperswithcode.com/paper/grounding-dynamic-spatial-relations-for |
| Repo | |
| Framework | |
Phase Retrieval via Incremental Truncated Wirtinger Flow
| Title | Phase Retrieval via Incremental Truncated Wirtinger Flow |
| Authors | Ritesh Kolte, Ayfer Özgür |
| Abstract | In the phase retrieval problem, an unknown vector is to be recovered given quadratic measurements. This problem has received considerable attention in recent times. In this paper, we present an algorithm to solve a nonconvex formulation of the phase retrieval problem, that we call $\textit{Incremental Truncated Wirtinger Flow}$. Given random Gaussian sensing vectors, we prove that it converges linearly to the solution, with an optimal sample complexity. We also provide stability guarantees of the algorithm under noisy measurements. Performance and comparisons with existing algorithms are illustrated via numerical experiments on simulated and real data, with both random and structured sensing vectors. |
| Tasks | |
| Published | 2016-06-10 |
| URL | http://arxiv.org/abs/1606.03196v1 |
| http://arxiv.org/pdf/1606.03196v1.pdf | |
| PWC | https://paperswithcode.com/paper/phase-retrieval-via-incremental-truncated |
| Repo | |
| Framework | |
Fast and Robust Hand Tracking Using Detection-Guided Optimization
| Title | Fast and Robust Hand Tracking Using Detection-Guided Optimization |
| Authors | Srinath Sridhar, Franziska Mueller, Antti Oulasvirta, Christian Theobalt |
| Abstract | Markerless tracking of hands and fingers is a promising enabler for human-computer interaction. However, adoption has been limited because of tracking inaccuracies, incomplete coverage of motions, low framerate, complex camera setups, and high computational requirements. In this paper, we present a fast method for accurately tracking rapid and complex articulations of the hand using a single depth camera. Our algorithm uses a novel detection-guided optimization strategy that increases the robustness and speed of pose estimation. In the detection step, a randomized decision forest classifies pixels into parts of the hand. In the optimization step, a novel objective function combines the detected part labels and a Gaussian mixture representation of the depth to estimate a pose that best fits the depth. Our approach needs comparably less computational resources which makes it extremely fast (50 fps without GPU support). The approach also supports varying static, or moving, camera-to-scene arrangements. We show the benefits of our method by evaluating on public datasets and comparing against previous work. |
| Tasks | Pose Estimation |
| Published | 2016-02-12 |
| URL | http://arxiv.org/abs/1602.04124v1 |
| http://arxiv.org/pdf/1602.04124v1.pdf | |
| PWC | https://paperswithcode.com/paper/fast-and-robust-hand-tracking-using-detection |
| Repo | |
| Framework | |
Consistently Estimating Markov Chains with Noisy Aggregate Data
| Title | Consistently Estimating Markov Chains with Noisy Aggregate Data |
| Authors | Garrett Bernstein, Daniel Sheldon |
| Abstract | We address the problem of estimating the parameters of a time-homogeneous Markov chain given only noisy, aggregate data. This arises when a population of individuals behave independently according to a Markov chain, but individual sample paths cannot be observed due to limitations of the observation process or the need to protect privacy. Instead, only population-level counts of the number of individuals in each state at each time step are available. When these counts are exact, a conditional least squares (CLS) estimator is known to be consistent and asymptotically normal. We initiate the study of method of moments estimators for this problem to handle the more realistic case when observations are additionally corrupted by noise. We show that CLS can be interpreted as a simple “plug-in” method of moments estimator. However, when observations are noisy, it is not consistent because it fails to account for additional variance introduced by the noise. We develop a new, simpler method of moments estimator that bypasses this problem and is consistent under noisy observations. |
| Tasks | |
| Published | 2016-04-14 |
| URL | http://arxiv.org/abs/1604.04182v1 |
| http://arxiv.org/pdf/1604.04182v1.pdf | |
| PWC | https://paperswithcode.com/paper/consistently-estimating-markov-chains-with |
| Repo | |
| Framework | |
Semantic Regularisation for Recurrent Image Annotation
| Title | Semantic Regularisation for Recurrent Image Annotation |
| Authors | Feng Liu, Tao Xiang, Timothy M. Hospedales, Wankou Yang, Changyin Sun |
| Abstract | The “CNN-RNN” design pattern is increasingly widely applied in a variety of image annotation tasks including multi-label classification and captioning. Existing models use the weakly semantic CNN hidden layer or its transform as the image embedding that provides the interface between the CNN and RNN. This leaves the RNN overstretched with two jobs: predicting the visual concepts and modelling their correlations for generating structured annotation output. Importantly this makes the end-to-end training of the CNN and RNN slow and ineffective due to the difficulty of back propagating gradients through the RNN to train the CNN. We propose a simple modification to the design pattern that makes learning more effective and efficient. Specifically, we propose to use a semantically regularised embedding layer as the interface between the CNN and RNN. Regularising the interface can partially or completely decouple the learning problems, allowing each to be more effectively trained and jointly training much more efficient. Extensive experiments show that state-of-the art performance is achieved on multi-label classification as well as image captioning. |
| Tasks | Image Captioning, Multi-Label Classification |
| Published | 2016-11-16 |
| URL | http://arxiv.org/abs/1611.05490v1 |
| http://arxiv.org/pdf/1611.05490v1.pdf | |
| PWC | https://paperswithcode.com/paper/semantic-regularisation-for-recurrent-image |
| Repo | |
| Framework | |
Evaluating the Performance of ANN Prediction System at Shanghai Stock Market in the Period 21-Sep-2016 to 11-Oct-2016
| Title | Evaluating the Performance of ANN Prediction System at Shanghai Stock Market in the Period 21-Sep-2016 to 11-Oct-2016 |
| Authors | Barack Wamkaya Wanjawa |
| Abstract | This research evaluates the performance of an Artificial Neural Network based prediction system that was employed on the Shanghai Stock Exchange for the period 21-Sep-2016 to 11-Oct-2016. It is a follow-up to a previous paper in which the prices were predicted and published before September 21. Stock market price prediction remains an important quest for investors and researchers. This research used an Artificial Intelligence system, being an Artificial Neural Network that is feedforward multi-layer perceptron with error backpropagation for prediction, unlike other methods such as technical, fundamental or time series analysis. While these alternative methods tend to guide on trends and not the exact likely prices, neural networks on the other hand have the ability to predict the real value prices, as was done on this research. Nonetheless, determination of suitable network parameters remains a challenge in neural network design, with this research settling on a configuration of 5:21:21:1 with 80% training data or 4-year of training data as a good enough model for stock prediction, as already determined in a previous research by the author. The comparative results indicate that neural network can predict typical stock market prices with mean absolute percentage errors that are as low as 1.95% over the ten prediction instances that was studied in this research. |
| Tasks | Stock Prediction, Time Series, Time Series Analysis |
| Published | 2016-12-05 |
| URL | http://arxiv.org/abs/1612.02666v1 |
| http://arxiv.org/pdf/1612.02666v1.pdf | |
| PWC | https://paperswithcode.com/paper/evaluating-the-performance-of-ann-prediction |
| Repo | |
| Framework | |
Predicting Future Shanghai Stock Market Price using ANN in the Period 21-Sep-2016 to 11-Oct-2016
| Title | Predicting Future Shanghai Stock Market Price using ANN in the Period 21-Sep-2016 to 11-Oct-2016 |
| Authors | Barack Wamkaya Wanjawa |
| Abstract | Predicting the prices of stocks at any stock market remains a quest for many investors and researchers. Those who trade at the stock market tend to use technical, fundamental or time series analysis in their predictions. These methods usually guide on trends and not the exact likely prices. It is for this reason that Artificial Intelligence systems, such as Artificial Neural Network, that is feedforward multi-layer perceptron with error backpropagation, can be used for such predictions. A difficulty in neural network application is the determination of suitable network parameters. A previous research by the author already determined the network parameters as 5:21:21:1 with 80% training data or 4-year of training data as a good enough model for stock prediction. This model has been put to the test in predicting selected Shanghai Stock Exchange stocks in the future period of 21-Sep-2016 to 11-Oct-2016, about one week after the publication of these predictions. The research aims at confirming that simple neural network systems can be quite powerful in typical stock market predictions. |
| Tasks | Stock Prediction, Time Series, Time Series Analysis |
| Published | 2016-09-17 |
| URL | http://arxiv.org/abs/1609.05394v1 |
| http://arxiv.org/pdf/1609.05394v1.pdf | |
| PWC | https://paperswithcode.com/paper/predicting-future-shanghai-stock-market-price |
| Repo | |
| Framework | |
Joint Learning Templates and Slots for Event Schema Induction
| Title | Joint Learning Templates and Slots for Event Schema Induction |
| Authors | Lei Sha, Sujian Li, Baobao Chang, Zhifang Sui |
| Abstract | Automatic event schema induction (AESI) means to extract meta-event from raw text, in other words, to find out what types (templates) of event may exist in the raw text and what roles (slots) may exist in each event type. In this paper, we propose a joint entity-driven model to learn templates and slots simultaneously based on the constraints of templates and slots in the same sentence. In addition, the entities’ semantic information is also considered for the inner connectivity of the entities. We borrow the normalized cut criteria in image segmentation to divide the entities into more accurate template clusters and slot clusters. The experiment shows that our model gains a relatively higher result than previous work. |
| Tasks | Semantic Segmentation |
| Published | 2016-03-04 |
| URL | http://arxiv.org/abs/1603.01333v1 |
| http://arxiv.org/pdf/1603.01333v1.pdf | |
| PWC | https://paperswithcode.com/paper/joint-learning-templates-and-slots-for-event |
| Repo | |
| Framework | |
Learning Latent Local Conversation Modes for Predicting Community Endorsement in Online Discussions
| Title | Learning Latent Local Conversation Modes for Predicting Community Endorsement in Online Discussions |
| Authors | Hao Fang, Hao Cheng, Mari Ostendorf |
| Abstract | Many social media platforms offer a mechanism for readers to react to comments, both positively and negatively, which in aggregate can be thought of as community endorsement. This paper addresses the problem of predicting community endorsement in online discussions, leveraging both the participant response structure and the text of the comment. The different types of features are integrated in a neural network that uses a novel architecture to learn latent modes of discussion structure that perform as well as deep neural networks but are more interpretable. In addition, the latent modes can be used to weight text features thereby improving prediction accuracy. |
| Tasks | |
| Published | 2016-08-16 |
| URL | http://arxiv.org/abs/1608.04808v2 |
| http://arxiv.org/pdf/1608.04808v2.pdf | |
| PWC | https://paperswithcode.com/paper/learning-latent-local-conversation-modes-for |
| Repo | |
| Framework | |
