Paper Group ANR 452
Semantic Term “Blurring” and Stochastic “Barcoding” for Improved Unsupervised Text Classification. On Exploration, Exploitation and Learning in Adaptive Importance Sampling. OhioState at SemEval-2018 Task 7: Exploiting Data Augmentation for Relation Classification in Scientific Papers using Piecewise Convolutional Neural Networks. Intelligent Physi …
Semantic Term “Blurring” and Stochastic “Barcoding” for Improved Unsupervised Text Classification
| Title | Semantic Term “Blurring” and Stochastic “Barcoding” for Improved Unsupervised Text Classification |
| Authors | Robert Frank Martorano III |
| Abstract | The abundance of text data being produced in the modern age makes it increasingly important to intuitively group, categorize, or classify text data by theme for efficient retrieval and search. Yet, the high dimensionality and imprecision of text data, or more generally language as a whole, prove to be challenging when attempting to perform unsupervised document clustering. In this thesis, we present two novel methods for improving unsupervised document clustering/classification by theme. The first is to improve document representations. We look to exploit “term neighborhoods” and “blur” semantic weight across neighboring terms. These neighborhoods are located in the semantic space afforded by “word embeddings.” The second method is for cluster revision, based on what we deem as “stochastic barcoding”, or “S- Barcode” patterns. Text data is inherently high dimensional, yet clustering typically takes place in a low dimensional representation space. Our method utilizes lower dimension clustering results as initial cluster configurations, and iteratively revises the configuration in the high dimensional space. We show with experimental results how both of the two methods improve the quality of document clustering. While this thesis elaborates on the two new conceptual contributions, a joint thesis by David Yan details the feature transformation and software architecture we developed for unsupervised document classification. |
| Tasks | Document Classification, Text Classification, Word Embeddings |
| Published | 2018-11-06 |
| URL | http://arxiv.org/abs/1811.02456v1 |
| http://arxiv.org/pdf/1811.02456v1.pdf | |
| PWC | https://paperswithcode.com/paper/semantic-term-blurring-and-stochastic |
| Repo | |
| Framework | |
On Exploration, Exploitation and Learning in Adaptive Importance Sampling
| Title | On Exploration, Exploitation and Learning in Adaptive Importance Sampling |
| Authors | Xiaoyu Lu, Tom Rainforth, Yuan Zhou, Jan-Willem van de Meent, Yee Whye Teh |
| Abstract | We study adaptive importance sampling (AIS) as an online learning problem and argue for the importance of the trade-off between exploration and exploitation in this adaptation. Borrowing ideas from the bandits literature, we propose Daisee, a partition-based AIS algorithm. We further introduce a notion of regret for AIS and show that Daisee has $\mathcal{O}(\sqrt{T}(\log T)^{\frac{3}{4}})$ cumulative pseudo-regret, where $T$ is the number of iterations. We then extend Daisee to adaptively learn a hierarchical partitioning of the sample space for more efficient sampling and confirm the performance of both algorithms empirically. |
| Tasks | |
| Published | 2018-10-31 |
| URL | http://arxiv.org/abs/1810.13296v1 |
| http://arxiv.org/pdf/1810.13296v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-exploration-exploitation-and-learning-in |
| Repo | |
| Framework | |
OhioState at SemEval-2018 Task 7: Exploiting Data Augmentation for Relation Classification in Scientific Papers using Piecewise Convolutional Neural Networks
| Title | OhioState at SemEval-2018 Task 7: Exploiting Data Augmentation for Relation Classification in Scientific Papers using Piecewise Convolutional Neural Networks |
| Authors | Dushyanta Dhyani |
| Abstract | We describe our system for SemEval-2018 Shared Task on Semantic Relation Extraction and Classification in Scientific Papers where we focus on the Classification task. Our simple piecewise convolution neural encoder performs decently in an end to end manner. A simple inter-task data augmentation signifi- cantly boosts the performance of the model. Our best-performing systems stood 8th out of 20 teams on the classification task on noisy data and 12th out of 28 teams on the classification task on clean data. |
| Tasks | Data Augmentation, Relation Classification, Relation Extraction |
| Published | 2018-02-25 |
| URL | http://arxiv.org/abs/1802.08949v2 |
| http://arxiv.org/pdf/1802.08949v2.pdf | |
| PWC | https://paperswithcode.com/paper/ohiostate-at-semeval-2018-task-7-exploiting |
| Repo | |
| Framework | |
Intelligent Physiotherapy Through Procedural Content Generation
| Title | Intelligent Physiotherapy Through Procedural Content Generation |
| Authors | Shabnam Sadeghi Esfahlani, Tommy Thompson |
| Abstract | This paper describes an avenue for artificial and computational intelligence techniques applied within games research to be deployed for purposes of physical therapy. We provide an overview of prototypical research focussed on the application of motion sensor input devices and virtual reality equipment for rehabilitation of motor impairment an issue typical of patient’s of traumatic brain injuries. We highlight how advances in procedural content generation and player modelling can stimulate development in this area by improving quality of rehabilitation programmes and measuring patient performance. |
| Tasks | |
| Published | 2018-04-25 |
| URL | http://arxiv.org/abs/1804.09465v1 |
| http://arxiv.org/pdf/1804.09465v1.pdf | |
| PWC | https://paperswithcode.com/paper/intelligent-physiotherapy-through-procedural |
| Repo | |
| Framework | |
AI Reasoning Systems: PAC and Applied Methods
| Title | AI Reasoning Systems: PAC and Applied Methods |
| Authors | Jeffrey Cheng |
| Abstract | Learning and logic are distinct and remarkable approaches to prediction. Machine learning has experienced a surge in popularity because it is robust to noise and achieves high performance; however, ML experiences many issues with knowledge transfer and extrapolation. In contrast, logic is easily intepreted, and logical rules are easy to chain and transfer between systems; however, inductive logic is brittle to noise. We then explore the premise of combining learning with inductive logic into AI Reasoning Systems. Specifically, we summarize findings from PAC learning (conceptual graphs, robust logics, knowledge infusion) and deep learning (DSRL, $\partial$ILP, DeepLogic) by reproducing proofs of tractability, presenting algorithms in pseudocode, highlighting results, and synthesizing between fields. We conclude with suggestions for integrated models by combining the modules listed above and with a list of unsolved (likely intractable) problems. |
| Tasks | Transfer Learning |
| Published | 2018-07-09 |
| URL | http://arxiv.org/abs/1807.05054v1 |
| http://arxiv.org/pdf/1807.05054v1.pdf | |
| PWC | https://paperswithcode.com/paper/ai-reasoning-systems-pac-and-applied-methods |
| Repo | |
| Framework | |
Nearest neighbor density functional estimation based on inverse Laplace transform
| Title | Nearest neighbor density functional estimation based on inverse Laplace transform |
| Authors | Shouvik Ganguly, Jongha Ryu, Young-Han Kim, Yung-Kyun Noh, Daniel D. Lee |
| Abstract | A general approach to $L_2$-consistent estimation of various density functionals using $k$-nearest neighbor distances is proposed, along with the analysis of convergence rates in mean squared error. The construction of the estimator is based on inverse Laplace transforms related to the target density functional, which arises naturally from the convergence of a normalized volume of $k$-nearest neighbor ball to a Gamma distribution in the sample limit. Some instantiations of the proposed estimator rediscover existing $k$-nearest neighbor based estimators of Shannon and Renyi entropies and Kullback–Leibler and Renyi divergences, and discover new consistent estimators for many other functionals, such as Jensen–Shannon divergence and generalized entropies and divergences. A unified finite-sample analysis of the proposed estimator is presented that builds on a recent result by Gao, Oh, and Viswanath (2017) on the finite sample behavior of the Kozachenko–Leoneko estimator of entropy. |
| Tasks | |
| Published | 2018-05-22 |
| URL | http://arxiv.org/abs/1805.08342v1 |
| http://arxiv.org/pdf/1805.08342v1.pdf | |
| PWC | https://paperswithcode.com/paper/nearest-neighbor-density-functional |
| Repo | |
| Framework | |
On the Benefit of Width for Neural Networks: Disappearance of Bad Basins
| Title | On the Benefit of Width for Neural Networks: Disappearance of Bad Basins |
| Authors | Dawei Li, Tian Ding, Ruoyu Sun |
| Abstract | Wide neural networks are often believed to have nice optimization landscape, but what rigorous results can we prove? To understand the benefit of width, it is important to identify the difference between wide and narrow networks. In this work, we prove that from narrow to wide networks, there is a phase transition from having sub-optimal basins to no sub-optimal basins. Specifically, we prove that for any continuous activation functions, the loss surface of wide networks has no sub-optimal basin, where “basin” is defined as the setwise strict local minimum. Furthermore, for a class of networks with width below a threshold, we construct sub-optimal strict local minima. These two results together suggest that one benefit of width is the disappearance of bad basins. Although a classical result [64] claimed that a large width can eliminate sub-optimal local minima in 1-hidden-layer networks, we point out a subtle cavity in its proof. |
| Tasks | |
| Published | 2018-12-28 |
| URL | https://arxiv.org/abs/1812.11039v2 |
| https://arxiv.org/pdf/1812.11039v2.pdf | |
| PWC | https://paperswithcode.com/paper/over-parameterized-deep-neural-networks-have |
| Repo | |
| Framework | |
Analysis of Irregular Spatial Data with Machine Learning: Classification of Building Patterns with a Graph Convolutional Neural Network
| Title | Analysis of Irregular Spatial Data with Machine Learning: Classification of Building Patterns with a Graph Convolutional Neural Network |
| Authors | Xiongfeng Yan, Tinghua Ai |
| Abstract | Machine learning methods such as convolutional neural networks (CNNs) are becoming an integral part of scientific research in many disciplines, spatial vector data often fail to be analyzed using these powerful learning methods because of its irregularities. With the aid of graph Fourier transform and convolution theorem, it is possible to convert the convolution as a point-wise product in Fourier domain and construct a learning architecture of CNN on graph for the analysis task of irregular spatial data. In this study, we used the classification task of building patterns as a case study to test this method, and experiments showed that this method has achieved outstanding results in identifying regular and irregular patterns, and has significantly improved in comparing with other methods. |
| Tasks | |
| Published | 2018-09-21 |
| URL | http://arxiv.org/abs/1809.08196v1 |
| http://arxiv.org/pdf/1809.08196v1.pdf | |
| PWC | https://paperswithcode.com/paper/analysis-of-irregular-spatial-data-with |
| Repo | |
| Framework | |
On Filter Size in Graph Convolutional Networks
| Title | On Filter Size in Graph Convolutional Networks |
| Authors | Dinh Van Tran, Nicolò Navarin, Alessandro Sperduti |
| Abstract | Recently, many researchers have been focusing on the definition of neural networks for graphs. The basic component for many of these approaches remains the graph convolution idea proposed almost a decade ago. In this paper, we extend this basic component, following an intuition derived from the well-known convolutional filters over multi-dimensional tensors. In particular, we derive a simple, efficient and effective way to introduce a hyper-parameter on graph convolutions that influences the filter size, i.e. its receptive field over the considered graph. We show with experimental results on real-world graph datasets that the proposed graph convolutional filter improves the predictive performance of Deep Graph Convolutional Networks. |
| Tasks | |
| Published | 2018-11-23 |
| URL | http://arxiv.org/abs/1811.10435v1 |
| http://arxiv.org/pdf/1811.10435v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-filter-size-in-graph-convolutional |
| Repo | |
| Framework | |
Web-Based Implementation of Travelling Salesperson Problem Using Genetic Algorithm
| Title | Web-Based Implementation of Travelling Salesperson Problem Using Genetic Algorithm |
| Authors | Aryo Pinandito, Novanto Yudistira, Fajar Pradana |
| Abstract | The world is connected through the Internet. As the abundance of Internet users connected into the Web and the popularity of cloud computing research, the need of Artificial Intelligence (AI) is demanding. In this research, Genetic Algorithm (GA) as AI optimization method through natural selection and genetic evolution is utilized. There are many applications of GA such as web mining, load balancing, routing, and scheduling or web service selection. Hence, it is a challenging task to discover whether the code mainly server side and web based language technology affects the performance of GA. Travelling Salesperson Problem (TSP) as Non Polynomial-hard (NP-hard) problem is provided to be a problem domain to be solved by GA. While many scientists prefer Python in GA implementation, another popular high-level interpreter programming language such as PHP (PHP Hypertext Preprocessor) and Ruby were benchmarked. Line of codes, file sizes, and performances based on GA implementation and runtime were found varies among these programming languages. Based on the result, the use of Ruby in GA implementation is recommended. |
| Tasks | |
| Published | 2018-02-09 |
| URL | http://arxiv.org/abs/1802.03155v1 |
| http://arxiv.org/pdf/1802.03155v1.pdf | |
| PWC | https://paperswithcode.com/paper/web-based-implementation-of-travelling |
| Repo | |
| Framework | |
Convolutional Neural Networks for Aircraft Noise Monitoring
| Title | Convolutional Neural Networks for Aircraft Noise Monitoring |
| Authors | Nicholas Heller, Derek Anderson, Matt Baker, Brad Juffer, Nikolaos Papanikolopoulos |
| Abstract | Air travel is one of the fastest growing modes of transportation, however, the effects of aircraft noise on populations surrounding airports is hindering its growth. In an effort to study and ultimately mitigate the impact that this noise has, many airports continuously monitor the aircraft noise in their surrounding communities. Noise monitoring and analysis is complicated by the fact that aircraft are not the only source of noise. In this work, we show that a Convolutional Neural Network is well-suited for the task of identifying noise events which are not caused by aircraft. Our system achieves an accuracy of 0.970 when trained on 900 manually labeled noise events. Our training data and a TensorFlow implementation of our model are available at https://github.com/neheller/aircraftnoise. |
| Tasks | |
| Published | 2018-06-12 |
| URL | http://arxiv.org/abs/1806.04779v1 |
| http://arxiv.org/pdf/1806.04779v1.pdf | |
| PWC | https://paperswithcode.com/paper/convolutional-neural-networks-for-aircraft |
| Repo | |
| Framework | |
Efficient logic architecture in training gradient boosting decision tree for high-performance and edge computing
| Title | Efficient logic architecture in training gradient boosting decision tree for high-performance and edge computing |
| Authors | Takuya Tanaka, Ryosuke Kasahara, Daishiro Kobayashi |
| Abstract | This study proposes a logic architecture for the high-speed and power efficiently training of a gradient boosting decision tree model of binary classification. We implemented the proposed logic architecture on an FPGA and compared training time and power efficiency with three general GBDT software libraries using CPU and GPU. The training speed of the logic architecture on the FPGA was 26-259 times faster than the software libraries. The power efficiency of the logic architecture was 90-1,104 times higher than the software libraries. The results show that the logic architecture suits for high-performance and edge computing. |
| Tasks | |
| Published | 2018-12-20 |
| URL | http://arxiv.org/abs/1812.08295v1 |
| http://arxiv.org/pdf/1812.08295v1.pdf | |
| PWC | https://paperswithcode.com/paper/efficient-logic-architecture-in-training |
| Repo | |
| Framework | |
End-to-End Text Classification via Image-based Embedding using Character-level Networks
| Title | End-to-End Text Classification via Image-based Embedding using Character-level Networks |
| Authors | Shunsuke Kitada, Ryunosuke Kotani, Hitoshi Iyatomi |
| Abstract | For analysing and/or understanding languages having no word boundaries based on morphological analysis such as Japanese, Chinese, and Thai, it is desirable to perform appropriate word segmentation before word embeddings. But it is inherently difficult in these languages. In recent years, various language models based on deep learning have made remarkable progress, and some of these methodologies utilizing character-level features have successfully avoided such a difficult problem. However, when a model is fed character-level features of the above languages, it often causes overfitting due to a large number of character types. In this paper, we propose a CE-CLCNN, character-level convolutional neural networks using a character encoder to tackle these problems. The proposed CE-CLCNN is an end-to-end learning model and has an image-based character encoder, i.e. the CE-CLCNN handles each character in the target document as an image. Through various experiments, we found and confirmed that our CE-CLCNN captured closely embedded features for visually and semantically similar characters and achieves state-of-the-art results on several open document classification tasks. In this paper we report the performance of our CE-CLCNN with the Wikipedia title estimation task and analyse the internal behaviour. |
| Tasks | Document Classification, Morphological Analysis, Text Classification, Word Embeddings |
| Published | 2018-10-08 |
| URL | http://arxiv.org/abs/1810.03595v2 |
| http://arxiv.org/pdf/1810.03595v2.pdf | |
| PWC | https://paperswithcode.com/paper/end-to-end-text-classification-via-image |
| Repo | |
| Framework | |
Semi-supervised learning with Bidirectional GANs
| Title | Semi-supervised learning with Bidirectional GANs |
| Authors | Maciej Zamorski, Maciej Zięba |
| Abstract | In this work we introduce a novel approach to train Bidirectional Generative Adversarial Model (BiGAN) in a semi-supervised manner. The presented method utilizes triplet loss function as an additional component of the objective function used to train discriminative data representation in the latent space of the BiGAN model. This representation can be further used as a seed for generating artificial images, but also as a good feature embedding for classification and image retrieval tasks. We evaluate the quality of the proposed method in the two mentioned challenging tasks using two benchmark datasets: CIFAR10 and SVHN. |
| Tasks | Image Retrieval |
| Published | 2018-11-28 |
| URL | http://arxiv.org/abs/1811.11426v1 |
| http://arxiv.org/pdf/1811.11426v1.pdf | |
| PWC | https://paperswithcode.com/paper/semi-supervised-learning-with-bidirectional |
| Repo | |
| Framework | |
Edge-Host Partitioning of Deep Neural Networks with Feature Space Encoding for Resource-Constrained Internet-of-Things Platforms
| Title | Edge-Host Partitioning of Deep Neural Networks with Feature Space Encoding for Resource-Constrained Internet-of-Things Platforms |
| Authors | Jong Hwan Ko, Taesik Na, Mohammad Faisal Amir, Saibal Mukhopadhyay |
| Abstract | This paper introduces partitioning an inference task of a deep neural network between an edge and a host platform in the IoT environment. We present a DNN as an encoding pipeline, and propose to transmit the output feature space of an intermediate layer to the host. The lossless or lossy encoding of the feature space is proposed to enhance the maximum input rate supported by the edge platform and/or reduce the energy of the edge platform. Simulation results show that partitioning a DNN at the end of convolutional (feature extraction) layers coupled with feature space encoding enables significant improvement in the energy-efficiency and throughput over the baseline configurations that perform the entire inference at the edge or at the host. |
| Tasks | |
| Published | 2018-02-11 |
| URL | http://arxiv.org/abs/1802.03835v1 |
| http://arxiv.org/pdf/1802.03835v1.pdf | |
| PWC | https://paperswithcode.com/paper/edge-host-partitioning-of-deep-neural |
| Repo | |
| Framework | |
