Paper Group ANR 48
Feature Incay for Representation Regularization. A Harmony Search Based Wrapper Feature Selection Method for Holistic Bangla word Recognition. Toward the Starting Line: A Systems Engineering Approach to Strong AI. Machine learning methods for multimedia information retrieval. 3D Pathfinding and Collision Avoidance Using Uneven Search-space Quantiza …
Feature Incay for Representation Regularization
| Title | Feature Incay for Representation Regularization |
| Authors | Yuhui Yuan, Kuiyuan Yang, Chao Zhang |
| Abstract | Softmax loss is widely used in deep neural networks for multi-class classification, where each class is represented by a weight vector, a sample is represented as a feature vector, and the feature vector has the largest projection on the weight vector of the correct category when the model correctly classifies a sample. To ensure generalization, weight decay that shrinks the weight norm is often used as regularizer. Different from traditional learning algorithms where features are fixed and only weights are tunable, features are also tunable as representation learning in deep learning. Thus, we propose feature incay to also regularize representation learning, which favors feature vectors with large norm when the samples can be correctly classified. With the feature incay, feature vectors are further pushed away from the origin along the direction of their corresponding weight vectors, which achieves better inter-class separability. In addition, the proposed feature incay encourages intra-class compactness along the directions of weight vectors by increasing the small feature norm faster than the large ones. Empirical results on MNIST, CIFAR10 and CIFAR100 demonstrate feature incay can improve the generalization ability. |
| Tasks | Representation Learning |
| Published | 2017-05-29 |
| URL | http://arxiv.org/abs/1705.10284v1 |
| http://arxiv.org/pdf/1705.10284v1.pdf | |
| PWC | https://paperswithcode.com/paper/feature-incay-for-representation |
| Repo | |
| Framework | |
A Harmony Search Based Wrapper Feature Selection Method for Holistic Bangla word Recognition
| Title | A Harmony Search Based Wrapper Feature Selection Method for Holistic Bangla word Recognition |
| Authors | Supratim Das, Pawan Kumar Singh, Showmik Bhowmik, Ram Sarkar, Mita Nasipuri |
| Abstract | A lot of search approaches have been explored for the selection of features in pattern classification domain in order to discover significant subset of the features which produces better accuracy. In this paper, we introduced a Harmony Search (HS) algorithm based feature selection method for feature dimensionality reduction in handwritten Bangla word recognition problem. This algorithm has been implemented to reduce the feature dimensionality of a technique described in one of our previous papers by S. Bhowmik et al.[1]. In the said paper, a set of 65 elliptical features were computed for handwritten Bangla word recognition purpose and a recognition accuracy of 81.37% was achieved using Multi Layer Perceptron (MLP) classifier. In the present work, a subset containing 48 features (approximately 75% of said feature vector) has been selected by HS based wrapper feature selection method which produces an accuracy rate of 90.29%. Reasonable outcomes also validates that the introduced algorithm utilizes optimal number of features while showing higher classification accuracies when compared to two standard evolutionary algorithms like Genetic Algorithm (GA), Particle Swarm Optimization (PSO) and statistical feature dimensionality reduction technique like Principal Component Analysis (PCA). This confirms the suitability of HS algorithm to the holistic handwritten word recognition problem. |
| Tasks | Dimensionality Reduction, Feature Selection |
| Published | 2017-07-26 |
| URL | http://arxiv.org/abs/1707.08398v1 |
| http://arxiv.org/pdf/1707.08398v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-harmony-search-based-wrapper-feature |
| Repo | |
| Framework | |
Toward the Starting Line: A Systems Engineering Approach to Strong AI
| Title | Toward the Starting Line: A Systems Engineering Approach to Strong AI |
| Authors | Tansu Alpcan, Sarah M. Erfani, Christopher Leckie |
| Abstract | Artificial General Intelligence (AGI) or Strong AI aims to create machines with human-like or human-level intelligence, which is still a very ambitious goal when compared to the existing computing and AI systems. After many hype cycles and lessons from AI history, it is clear that a big conceptual leap is needed for crossing the starting line to kick-start mainstream AGI research. This position paper aims to make a small conceptual contribution toward reaching that starting line. After a broad analysis of the AGI problem from different perspectives, a system-theoretic and engineering-based research approach is introduced, which builds upon the existing mainstream AI and systems foundations. Several promising cross-fertilization opportunities between systems disciplines and AI research are identified. Specific potential research directions are discussed. |
| Tasks | |
| Published | 2017-07-28 |
| URL | http://arxiv.org/abs/1707.09095v2 |
| http://arxiv.org/pdf/1707.09095v2.pdf | |
| PWC | https://paperswithcode.com/paper/toward-the-starting-line-a-systems |
| Repo | |
| Framework | |
Machine learning methods for multimedia information retrieval
| Title | Machine learning methods for multimedia information retrieval |
| Authors | Bálint Zoltán Daróczy |
| Abstract | In this thesis we examined several multimodal feature extraction and learning methods for retrieval and classification purposes. We reread briefly some theoretical results of learning in Section 2 and reviewed several generative and discriminative models in Section 3 while we described the similarity kernel in Section 4. We examined different aspects of the multimodal image retrieval and classification in Section 5 and suggested methods for identifying quality assessments of Web documents in Section 6. In our last problem we proposed similarity kernel for time-series based classification. The experiments were carried over publicly available datasets and source codes for the most essential parts are either open source or released. Since the used similarity graphs (Section 4.2) are greatly constrained for computational purposes, we would like to continue work with more complex, evolving and capable graphs and apply for different problems such as capturing the rapid change in the distribution (e.g. session based recommendation) or complex graphs of the literature work. The similarity kernel with the proper metrics reaches and in many cases improves over the state-of-the-art. Hence we may conclude generative models based on instance similarities with multiple modes is a generally applicable model for classification and regression tasks ranging over various domains, including but not limited to the ones presented in this thesis. More generally, the Fisher kernel is not only unique in many ways but one of the most powerful kernel functions. Therefore we may exploit the Fisher kernel in the future over widely used generative models, such as Boltzmann Machines [Hinton et al., 1984], a particular subset, the Restricted Boltzmann Machines and Deep Belief Networks [Hinton et al., 2006]), Latent Dirichlet Allocation [Blei et al., 2003] or Hidden Markov Models [Baum and Petrie, 1966] to name a few. |
| Tasks | Image Retrieval, Information Retrieval, Session-Based Recommendations, Time Series |
| Published | 2017-05-14 |
| URL | http://arxiv.org/abs/1705.04964v1 |
| http://arxiv.org/pdf/1705.04964v1.pdf | |
| PWC | https://paperswithcode.com/paper/machine-learning-methods-for-multimedia |
| Repo | |
| Framework | |
3D Pathfinding and Collision Avoidance Using Uneven Search-space Quantization and Visual Cone Search
| Title | 3D Pathfinding and Collision Avoidance Using Uneven Search-space Quantization and Visual Cone Search |
| Authors | Diptangshu Pandit |
| Abstract | Pathfinding is a very popular area in computer game development. While two-dimensional (2D) pathfinding is widely applied in most of the popular game engines, little implementation of real three-dimensional (3D) pathfinding can be found. This research presents a dynamic search space optimization algorithm which can be applied to tessellate 3D search space unevenly, significantly reducing the total number of resulting nodes. The algorithm can be used with popular pathfinding algorithms in 3D game engines. Furthermore, a simplified standalone 3D pathfinding algorithm is proposed in this paper. The proposed algorithm relies on ray-casting or line vision to generate a feasible path during runtime without requiring division of the search space into a 3D grid. Both of the proposed algorithms are simulated on Unreal Engine to show innerworkings and resultant path comparison with A*. The advantages and shortcomings of the proposed algorithms are also discussed along with future directions. |
| Tasks | Quantization |
| Published | 2017-06-05 |
| URL | http://arxiv.org/abs/1706.01320v3 |
| http://arxiv.org/pdf/1706.01320v3.pdf | |
| PWC | https://paperswithcode.com/paper/3d-pathfinding-and-collision-avoidance-using |
| Repo | |
| Framework | |
Neuroevolution on the Edge of Chaos
| Title | Neuroevolution on the Edge of Chaos |
| Authors | Filip Matzner |
| Abstract | Echo state networks represent a special type of recurrent neural networks. Recent papers stated that the echo state networks maximize their computational performance on the transition between order and chaos, the so-called edge of chaos. This work confirms this statement in a comprehensive set of experiments. Furthermore, the echo state networks are compared to networks evolved via neuroevolution. The evolved networks outperform the echo state networks, however, the evolution consumes significant computational resources. It is demonstrated that echo state networks with local connections combine the best of both worlds, the simplicity of random echo state networks and the performance of evolved networks. Finally, it is shown that evolution tends to stay close to the ordered side of the edge of chaos. |
| Tasks | |
| Published | 2017-06-05 |
| URL | http://arxiv.org/abs/1706.01330v1 |
| http://arxiv.org/pdf/1706.01330v1.pdf | |
| PWC | https://paperswithcode.com/paper/neuroevolution-on-the-edge-of-chaos |
| Repo | |
| Framework | |
PupilNet v2.0: Convolutional Neural Networks for CPU based real time Robust Pupil Detection
| Title | PupilNet v2.0: Convolutional Neural Networks for CPU based real time Robust Pupil Detection |
| Authors | Wolfgang Fuhl, Thiago Santini, Gjergji Kasneci, Wolfgang Rosenstiel, Enkelejda Kasneci |
| Abstract | Real-time, accurate, and robust pupil detection is an essential prerequisite for pervasive video-based eye-tracking. However, automated pupil detection in realworld scenarios has proven to be an intricate challenge due to fast illumination changes, pupil occlusion, non-centered and off-axis eye recording, as well as physiological eye characteristics. In this paper, we approach this challenge through: I) a convolutional neural network (CNN) running in real time on a single core, II) a novel computational intensive two stage CNN for accuracy improvement, and III) a fast propability distribution based refinement method as a practical alternative to II. We evaluate the proposed approaches against the state-of-the-art pupil detection algorithms, improving the detection rate up to ~9% percent points on average over all data sets (~7% on one CPU core 7ms). This evaluation was performed on over 135,000 images: 94,000 images from the literature, and 41,000 new hand-labeled and challenging images contributed by this work (v1.0). |
| Tasks | Eye Tracking |
| Published | 2017-10-30 |
| URL | http://arxiv.org/abs/1711.00112v1 |
| http://arxiv.org/pdf/1711.00112v1.pdf | |
| PWC | https://paperswithcode.com/paper/pupilnet-v20-convolutional-neural-networks |
| Repo | |
| Framework | |
What is the Machine Learning?
| Title | What is the Machine Learning? |
| Authors | Spencer Chang, Timothy Cohen, Bryan Ostdiek |
| Abstract | Applications of machine learning tools to problems of physical interest are often criticized for producing sensitivity at the expense of transparency. To address this concern, we explore a data planing procedure for identifying combinations of variables – aided by physical intuition – that can discriminate signal from background. Weights are introduced to smooth away the features in a given variable(s). New networks are then trained on this modified data. Observed decreases in sensitivity diagnose the variable’s discriminating power. Planing also allows the investigation of the linear versus non-linear nature of the boundaries between signal and background. We demonstrate the efficacy of this approach using a toy example, followed by an application to an idealized heavy resonance scenario at the Large Hadron Collider. By unpacking the information being utilized by these algorithms, this method puts in context what it means for a machine to learn. |
| Tasks | |
| Published | 2017-09-28 |
| URL | http://arxiv.org/abs/1709.10106v2 |
| http://arxiv.org/pdf/1709.10106v2.pdf | |
| PWC | https://paperswithcode.com/paper/what-is-the-machine-learning |
| Repo | |
| Framework | |
Event Representations for Automated Story Generation with Deep Neural Nets
| Title | Event Representations for Automated Story Generation with Deep Neural Nets |
| Authors | Lara J. Martin, Prithviraj Ammanabrolu, Xinyu Wang, William Hancock, Shruti Singh, Brent Harrison, Mark O. Riedl |
| Abstract | Automated story generation is the problem of automatically selecting a sequence of events, actions, or words that can be told as a story. We seek to develop a system that can generate stories by learning everything it needs to know from textual story corpora. To date, recurrent neural networks that learn language models at character, word, or sentence levels have had little success generating coherent stories. We explore the question of event representations that provide a mid-level of abstraction between words and sentences in order to retain the semantic information of the original data while minimizing event sparsity. We present a technique for preprocessing textual story data into event sequences. We then present a technique for automated story generation whereby we decompose the problem into the generation of successive events (event2event) and the generation of natural language sentences from events (event2sentence). We give empirical results comparing different event representations and their effects on event successor generation and the translation of events to natural language. |
| Tasks | |
| Published | 2017-06-05 |
| URL | http://arxiv.org/abs/1706.01331v3 |
| http://arxiv.org/pdf/1706.01331v3.pdf | |
| PWC | https://paperswithcode.com/paper/event-representations-for-automated-story |
| Repo | |
| Framework | |
FashionBrain Project: A Vision for Understanding Europe’s Fashion Data Universe
| Title | FashionBrain Project: A Vision for Understanding Europe’s Fashion Data Universe |
| Authors | Alessandro Checco, Gianluca Demartini, Alexander Loeser, Ines Arous, Mourad Khayati, Matthias Dantone, Richard Koopmanschap, Svetlin Stalinov, Martin Kersten, Ying Zhang |
| Abstract | A core business in the fashion industry is the understanding and prediction of customer needs and trends. Search engines and social networks are at the same time a fundamental bridge and a costly middleman between the customer’s purchase intention and the retailer. To better exploit Europe’s distinctive characteristics e.g., multiple languages, fashion and cultural differences, it is pivotal to reduce retailers’ dependence to search engines. This goal can be achieved by harnessing various data channels (manufacturers and distribution networks, online shops, large retailers, social media, market observers, call centers, press/magazines etc.) that retailers can leverage in order to gain more insight about potential buyers, and on the industry trends as a whole. This can enable the creation of novel on-line shopping experiences, the detection of influencers, and the prediction of upcoming fashion trends. In this paper, we provide an overview of the main research challenges and an analysis of the most promising technological solutions that we are investigating in the FashionBrain project. |
| Tasks | |
| Published | 2017-10-26 |
| URL | http://arxiv.org/abs/1710.09788v1 |
| http://arxiv.org/pdf/1710.09788v1.pdf | |
| PWC | https://paperswithcode.com/paper/fashionbrain-project-a-vision-for |
| Repo | |
| Framework | |
Local Search for Minimum Weight Dominating Set with Two-Level Configuration Checking and Frequency Based Scoring Function
| Title | Local Search for Minimum Weight Dominating Set with Two-Level Configuration Checking and Frequency Based Scoring Function |
| Authors | Yiyuan Wang, Shaowei Cai, Minghao Yin |
| Abstract | The Minimum Weight Dominating Set (MWDS) problem is an important generalization of the Minimum Dominating Set (MDS) problem with extensive applications. This paper proposes a new local search algorithm for the MWDS problem, which is based on two new ideas. The first idea is a heuristic called two-level configuration checking (CC2), which is a new variant of a recent powerful configuration checking strategy (CC) for effectively avoiding the recent search paths. The second idea is a novel scoring function based on the frequency of being uncovered of vertices. Our algorithm is called CC2FS, according to the names of the two ideas. The experimental results show that, CC2FS performs much better than some state-of-the-art algorithms in terms of solution quality on a broad range of MWDS benchmarks. |
| Tasks | |
| Published | 2017-02-15 |
| URL | http://arxiv.org/abs/1702.04594v1 |
| http://arxiv.org/pdf/1702.04594v1.pdf | |
| PWC | https://paperswithcode.com/paper/local-search-for-minimum-weight-dominating |
| Repo | |
| Framework | |
Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning
| Title | Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning |
| Authors | Stefan Elfwing, Eiji Uchibe, Kenji Doya |
| Abstract | In recent years, neural networks have enjoyed a renaissance as function approximators in reinforcement learning. Two decades after Tesauro’s TD-Gammon achieved near top-level human performance in backgammon, the deep reinforcement learning algorithm DQN achieved human-level performance in many Atari 2600 games. The purpose of this study is twofold. First, we propose two activation functions for neural network function approximation in reinforcement learning: the sigmoid-weighted linear unit (SiLU) and its derivative function (dSiLU). The activation of the SiLU is computed by the sigmoid function multiplied by its input. Second, we suggest that the more traditional approach of using on-policy learning with eligibility traces, instead of experience replay, and softmax action selection with simple annealing can be competitive with DQN, without the need for a separate target network. We validate our proposed approach by, first, achieving new state-of-the-art results in both stochastic SZ-Tetris and Tetris with a small 10$\times$10 board, using TD($\lambda$) learning and shallow dSiLU network agents, and, then, by outperforming DQN in the Atari 2600 domain by using a deep Sarsa($\lambda$) agent with SiLU and dSiLU hidden units. |
| Tasks | Atari Games |
| Published | 2017-02-10 |
| URL | http://arxiv.org/abs/1702.03118v3 |
| http://arxiv.org/pdf/1702.03118v3.pdf | |
| PWC | https://paperswithcode.com/paper/sigmoid-weighted-linear-units-for-neural |
| Repo | |
| Framework | |
Evaluation of Semantic Web Technologies for Storing Computable Definitions of Electronic Health Records Phenotyping Algorithms
| Title | Evaluation of Semantic Web Technologies for Storing Computable Definitions of Electronic Health Records Phenotyping Algorithms |
| Authors | Vaclav Papez, Spiros Denaxas, Harry Hemingway |
| Abstract | Electronic Health Records are electronic data generated during or as a byproduct of routine patient care. Structured, semi-structured and unstructured EHR offer researchers unprecedented phenotypic breadth and depth and have the potential to accelerate the development of precision medicine approaches at scale. A main EHR use-case is defining phenotyping algorithms that identify disease status, onset and severity. Phenotyping algorithms utilize diagnoses, prescriptions, laboratory tests, symptoms and other elements in order to identify patients with or without a specific trait. No common standardized, structured, computable format exists for storing phenotyping algorithms. The majority of algorithms are stored as human-readable descriptive text documents making their translation to code challenging due to their inherent complexity and hinders their sharing and re-use across the community. In this paper, we evaluate the two key Semantic Web Technologies, the Web Ontology Language and the Resource Description Framework, for enabling computable representations of EHR-driven phenotyping algorithms. |
| Tasks | |
| Published | 2017-07-24 |
| URL | http://arxiv.org/abs/1707.07673v1 |
| http://arxiv.org/pdf/1707.07673v1.pdf | |
| PWC | https://paperswithcode.com/paper/evaluation-of-semantic-web-technologies-for |
| Repo | |
| Framework | |
Anomaly Detection on Graph Time Series
| Title | Anomaly Detection on Graph Time Series |
| Authors | Daniel Hsu |
| Abstract | In this paper, we use variational recurrent neural network to investigate the anomaly detection problem on graph time series. The temporal correlation is modeled by the combination of recurrent neural network (RNN) and variational inference (VI), while the spatial information is captured by the graph convolutional network. In order to incorporate external factors, we use feature extractor to augment the transition of latent variables, which can learn the influence of external factors. With the target function as accumulative ELBO, it is easy to extend this model to on-line method. The experimental study on traffic flow data shows the detection capability of the proposed method. |
| Tasks | Anomaly Detection, Time Series |
| Published | 2017-08-09 |
| URL | http://arxiv.org/abs/1708.02975v2 |
| http://arxiv.org/pdf/1708.02975v2.pdf | |
| PWC | https://paperswithcode.com/paper/anomaly-detection-on-graph-time-series |
| Repo | |
| Framework | |
Performance Evaluation of Deep Learning Tools in Docker Containers
| Title | Performance Evaluation of Deep Learning Tools in Docker Containers |
| Authors | Pengfei Xu, Shaohuai Shi, Xiaowen Chu |
| Abstract | With the success of deep learning techniques in a broad range of application domains, many deep learning software frameworks have been developed and are being updated frequently to adapt to new hardware features and software libraries, which bring a big challenge for end users and system administrators. To address this problem, container techniques are widely used to simplify the deployment and management of deep learning software. However, it remains unknown whether container techniques bring any performance penalty to deep learning applications. The purpose of this work is to systematically evaluate the impact of docker container on the performance of deep learning applications. We first benchmark the performance of system components (IO, CPU and GPU) in a docker container and the host system and compare the results to see if there’s any difference. According to our results, we find that computational intensive jobs, either running on CPU or GPU, have small overhead indicating docker containers can be applied to deep learning programs. Then we evaluate the performance of some popular deep learning tools deployed in a docker container and the host system. It turns out that the docker container will not cause noticeable drawbacks while running those deep learning tools. So encapsulating deep learning tool in a container is a feasible solution. |
| Tasks | |
| Published | 2017-11-09 |
| URL | http://arxiv.org/abs/1711.03386v1 |
| http://arxiv.org/pdf/1711.03386v1.pdf | |
| PWC | https://paperswithcode.com/paper/performance-evaluation-of-deep-learning-tools |
| Repo | |
| Framework | |
