Paper Group ANR 34
Temperature-Based Deep Boltzmann Machines. “Flow Size Difference” Can Make a Difference: Detecting Malicious TCP Network Flows Based on Benford’s Law. MIST: Missing Person Intelligence Synthesis Toolkit. Adaptive Convolutional ELM For Concept Drift Handling in Online Stream Data. On the Robustness of Decision Tree Learning under Label Noise. Effect …
Temperature-Based Deep Boltzmann Machines
| Title | Temperature-Based Deep Boltzmann Machines |
| Authors | Leandro Aparecido Passos Junior, Joao Paulo Papa |
| Abstract | Deep learning techniques have been paramount in the last years, mainly due to their outstanding results in a number of applications, that range from speech recognition to face-based user identification. Despite other techniques employed for such purposes, Deep Boltzmann Machines are among the most used ones, which are composed of layers of Restricted Boltzmann Machines (RBMs) stacked on top of each other. In this work, we evaluate the concept of temperature in DBMs, which play a key role in Boltzmann-related distributions, but it has never been considered in this context up to date. Therefore, the main contribution of this paper is to take into account this information and to evaluate its influence in DBMs considering the task of binary image reconstruction. We expect this work can foster future research considering the usage of different temperatures during learning in DBMs. |
| Tasks | Image Reconstruction, Speech Recognition |
| Published | 2016-08-27 |
| URL | http://arxiv.org/abs/1608.07719v2 |
| http://arxiv.org/pdf/1608.07719v2.pdf | |
| PWC | https://paperswithcode.com/paper/temperature-based-deep-boltzmann-machines |
| Repo | |
| Framework | |
“Flow Size Difference” Can Make a Difference: Detecting Malicious TCP Network Flows Based on Benford’s Law
| Title | “Flow Size Difference” Can Make a Difference: Detecting Malicious TCP Network Flows Based on Benford’s Law |
| Authors | Aamo Iorliam, Santosh Tirunagari, Anthony T. S. Ho, Shujun Li, Adrian Waller, Norman Poh |
| Abstract | Statistical characteristics of network traffic have attracted a significant amount of research for automated network intrusion detection, some of which looked at applications of natural statistical laws such as Zipf’s law, Benford’s law and the Pareto distribution. In this paper, we present the application of Benford’s law to a new network flow metric “flow size difference”, which have not been studied before by other researchers, to build an unsupervised flow-based intrusion detection system (IDS). The method was inspired by our observation on a large number of TCP flow datasets where normal flows tend to follow Benford’s law closely but malicious flows tend to deviate significantly from it. The proposed IDS is unsupervised, so it can be easily deployed without any training. It has two simple operational parameters with a clear semantic meaning, allowing the IDS operator to set and adapt their values intuitively to adjust the overall performance of the IDS. We tested the proposed IDS on two (one closed and one public) datasets, and proved its efficiency in terms of AUC (area under the ROC curve). Our work showed the “flow size difference” has a great potential to improve the performance of any flow-based network IDSs. |
| Tasks | Intrusion Detection, Network Intrusion Detection |
| Published | 2016-09-14 |
| URL | http://arxiv.org/abs/1609.04214v2 |
| http://arxiv.org/pdf/1609.04214v2.pdf | |
| PWC | https://paperswithcode.com/paper/flow-size-difference-can-make-a-difference |
| Repo | |
| Framework | |
MIST: Missing Person Intelligence Synthesis Toolkit
| Title | MIST: Missing Person Intelligence Synthesis Toolkit |
| Authors | Elham Shaabani, Hamidreza Alvari, Paulo Shakarian, J. E. Kelly Snyder |
| Abstract | Each day, approximately 500 missing persons cases occur that go unsolved/unresolved in the United States. The non-profit organization known as the Find Me Group (FMG), led by former law enforcement professionals, is dedicated to solving or resolving these cases. This paper introduces the Missing Person Intelligence Synthesis Toolkit (MIST) which leverages a data-driven variant of geospatial abductive inference. This system takes search locations provided by a group of experts and rank-orders them based on the probability assigned to areas based on the prior performance of the experts taken as a group. We evaluate our approach compared to the current practices employed by the Find Me Group and found it significantly reduces the search area - leading to a reduction of 31 square miles over 24 cases we examined in our experiments. Currently, we are using MIST to aid the Find Me Group in an active missing person case. |
| Tasks | |
| Published | 2016-07-28 |
| URL | http://arxiv.org/abs/1607.08580v2 |
| http://arxiv.org/pdf/1607.08580v2.pdf | |
| PWC | https://paperswithcode.com/paper/mist-missing-person-intelligence-synthesis |
| Repo | |
| Framework | |
Adaptive Convolutional ELM For Concept Drift Handling in Online Stream Data
| Title | Adaptive Convolutional ELM For Concept Drift Handling in Online Stream Data |
| Authors | Arif Budiman, Mohamad Ivan Fanany, Chan Basaruddin |
| Abstract | In big data era, the data continuously generated and its distribution may keep changes overtime. These challenges in online stream of data are known as concept drift. In this paper, we proposed the Adaptive Convolutional ELM method (ACNNELM) as enhancement of Convolutional Neural Network (CNN) with a hybrid Extreme Learning Machine (ELM) model plus adaptive capability. This method is aimed for concept drift handling. We enhanced the CNN as convolutional hiererchical features representation learner combined with Elastic ELM (E$^2$LM) as a parallel supervised classifier. We propose an Adaptive OS-ELM (AOS-ELM) for concept drift adaptability in classifier level (named ACNNELM-1) and matrices concatenation ensembles for concept drift adaptability in ensemble level (named ACNNELM-2). Our proposed Adaptive CNNELM is flexible that works well in classifier level and ensemble level while most current methods only proposed to work on either one of the levels. We verified our method in extended MNIST data set and not MNIST data set. We set the experiment to simulate virtual drift, real drift, and hybrid drift event and we demonstrated how our CNNELM adaptability works. Our proposed method works well and gives better accuracy, computation scalability, and concept drifts adaptability compared to the regular ELM and CNN. Further researches are still required to study the optimum parameters and to use more varied image data set. |
| Tasks | |
| Published | 2016-10-07 |
| URL | http://arxiv.org/abs/1610.02348v1 |
| http://arxiv.org/pdf/1610.02348v1.pdf | |
| PWC | https://paperswithcode.com/paper/adaptive-convolutional-elm-for-concept-drift |
| Repo | |
| Framework | |
On the Robustness of Decision Tree Learning under Label Noise
| Title | On the Robustness of Decision Tree Learning under Label Noise |
| Authors | Aritra Ghosh, Naresh Manwani, P. S. Sastry |
| Abstract | In most practical problems of classifier learning, the training data suffers from the label noise. Hence, it is important to understand how robust is a learning algorithm to such label noise. This paper presents some theoretical analysis to show that many popular decision tree algorithms are robust to symmetric label noise under large sample size. We also present some sample complexity results which provide some bounds on the sample size for the robustness to hold with a high probability. Through extensive simulations we illustrate this robustness. |
| Tasks | |
| Published | 2016-05-20 |
| URL | http://arxiv.org/abs/1605.06296v2 |
| http://arxiv.org/pdf/1605.06296v2.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-robustness-of-decision-tree-learning |
| Repo | |
| Framework | |
Effective Data Mining Technique for Classification Cancers via Mutations in Gene using Neural Network
| Title | Effective Data Mining Technique for Classification Cancers via Mutations in Gene using Neural Network |
| Authors | Ayad Ghany Ismaeel, Dina Yousif Mikhail |
| Abstract | The prediction plays the important role in detecting efficient protection and therapy of cancer. The prediction of mutations in gene needs a diagnostic and classification, which is based on the whole database (big dataset), to reach sufficient accuracy results. Since the tumor suppressor P53 is approximately about fifty percentage of all human tumors because mutations that occur in the TP53 gene into the cells. So, this paper is applied on tumor p53, where the problem is there are several primitive databases (excel database) contain datasets of TP53 gene with its tumor protein p53, these databases are rich datasets that cover all mutations and cause diseases (cancers). But these Data Bases cannot reach to predict and diagnosis cancers, i.e. the big datasets have not efficient Data Mining method, which can predict, diagnosis the mutation, and classify the cancer of patient. The goal of this paper to reach a Data Mining technique, that employs neural network, which bases on the big datasets. Also, offers friendly predictions, flexible, and effective classified cancers, in order to overcome the previous techniques drawbacks. This proposed technique is done by using two approaches, first, bioinformatics techniques by using BLAST, CLUSTALW, etc, in order to know if there are malignant mutations or not. The second, data mining by using neural network; it is selected (12) out of (53) TP53 gene database fields. To clarify, one of these 12 fields (gene location field) did not exists in TP53 gene database; therefore, it is added to the database of TP53 gene in training and testing back propagation algorithm, in order to classify specifically the types of cancers. Feed Forward Back Propagation supports this Data Mining method with data training rate (1) and Mean Square Error (MSE) (0.00000000000001). This effective technique allows in a quick, accurate and easy way to classify the type of cancer. |
| Tasks | |
| Published | 2016-08-06 |
| URL | http://arxiv.org/abs/1608.02888v1 |
| http://arxiv.org/pdf/1608.02888v1.pdf | |
| PWC | https://paperswithcode.com/paper/effective-data-mining-technique-for |
| Repo | |
| Framework | |
On Deductive Systems of AC Semantics for Rough Sets
| Title | On Deductive Systems of AC Semantics for Rough Sets |
| Authors | A. Mani |
| Abstract | Antichain based semantics for general rough sets were introduced recently by the present author. In her paper two different semantics, one for general rough sets and another for general approximation spaces over quasi-equivalence relations, were developed. These semantics are improved and studied further from a lateral algebraic logic perspective in this research. The main results concern the structure of the algebras and deductive systems in the context. |
| Tasks | |
| Published | 2016-10-09 |
| URL | http://arxiv.org/abs/1610.02634v1 |
| http://arxiv.org/pdf/1610.02634v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-deductive-systems-of-ac-semantics-for |
| Repo | |
| Framework | |
Nonnegative Matrix Underapproximation for Robust Multiple Model Fitting
| Title | Nonnegative Matrix Underapproximation for Robust Multiple Model Fitting |
| Authors | Mariano Tepper, Guillermo Sapiro |
| Abstract | In this work, we introduce a highly efficient algorithm to address the nonnegative matrix underapproximation (NMU) problem, i.e., nonnegative matrix factorization (NMF) with an additional underapproximation constraint. NMU results are interesting as, compared to traditional NMF, they present additional sparsity and part-based behavior, explaining unique data features. To show these features in practice, we first present an application to the analysis of climate data. We then present an NMU-based algorithm to robustly fit multiple parametric models to a dataset. The proposed approach delivers state-of-the-art results for the estimation of multiple fundamental matrices and homographies, outperforming other alternatives in the literature and exemplifying the use of efficient NMU computations. |
| Tasks | |
| Published | 2016-11-04 |
| URL | http://arxiv.org/abs/1611.01408v5 |
| http://arxiv.org/pdf/1611.01408v5.pdf | |
| PWC | https://paperswithcode.com/paper/nonnegative-matrix-underapproximation-for |
| Repo | |
| Framework | |
Transfer Hashing with Privileged Information
| Title | Transfer Hashing with Privileged Information |
| Authors | Joey Tianyi Zhou, Xinxing Xu, Sinno Jialin Pan, Ivor W. Tsang, Zheng Qin, Rick Siow Mong Goh |
| Abstract | Most existing learning to hash methods assume that there are sufficient data, either labeled or unlabeled, on the domain of interest (i.e., the target domain) for training. However, this assumption cannot be satisfied in some real-world applications. To address this data sparsity issue in hashing, inspired by transfer learning, we propose a new framework named Transfer Hashing with Privileged Information (THPI). Specifically, we extend the standard learning to hash method, Iterative Quantization (ITQ), in a transfer learning manner, namely ITQ+. In ITQ+, a new slack function is learned from auxiliary data to approximate the quantization error in ITQ. We developed an alternating optimization approach to solve the resultant optimization problem for ITQ+. We further extend ITQ+ to LapITQ+ by utilizing the geometry structure among the auxiliary data for learning more precise binary codes in the target domain. Extensive experiments on several benchmark datasets verify the effectiveness of our proposed approaches through comparisons with several state-of-the-art baselines. |
| Tasks | Quantization, Transfer Learning |
| Published | 2016-05-13 |
| URL | http://arxiv.org/abs/1605.04034v1 |
| http://arxiv.org/pdf/1605.04034v1.pdf | |
| PWC | https://paperswithcode.com/paper/transfer-hashing-with-privileged-information |
| Repo | |
| Framework | |
Edge Detection Based Shape Identification
| Title | Edge Detection Based Shape Identification |
| Authors | Vivek Kumar, Sumit Pandey, Amrindra Pal, Sandeep Sharma |
| Abstract | Image recognition is the need of the hour. In order to be able to recognize an image, it is of immense importance that the image should be distinguishable from the background. In the present work, an approach is presented for automatic detection and recognition of regular 2D shapes in low noise environments. The work has a large number of direct applications in the real world. The algorithm proposed is based on locating the edges and thus, in turn calculating the area of the object helps in identification of a specified shape. The results were simulated using MATLAB tool are encouraging and validate the proposed algorithm. Index Terms: Edge Detection, Area Calculation, Shape Detection, Object Recognition |
| Tasks | Edge Detection, Object Recognition |
| Published | 2016-04-07 |
| URL | http://arxiv.org/abs/1604.02030v1 |
| http://arxiv.org/pdf/1604.02030v1.pdf | |
| PWC | https://paperswithcode.com/paper/edge-detection-based-shape-identification |
| Repo | |
| Framework | |
Deep Reinforcement Learning for Tensegrity Robot Locomotion
| Title | Deep Reinforcement Learning for Tensegrity Robot Locomotion |
| Authors | Marvin Zhang, Xinyang Geng, Jonathan Bruce, Ken Caluwaerts, Massimo Vespignani, Vytas SunSpiral, Pieter Abbeel, Sergey Levine |
| Abstract | Tensegrity robots, composed of rigid rods connected by elastic cables, have a number of unique properties that make them appealing for use as planetary exploration rovers. However, control of tensegrity robots remains a difficult problem due to their unusual structures and complex dynamics. In this work, we show how locomotion gaits can be learned automatically using a novel extension of mirror descent guided policy search (MDGPS) applied to periodic locomotion movements, and we demonstrate the effectiveness of our approach on tensegrity robot locomotion. We evaluate our method with real-world and simulated experiments on the SUPERball tensegrity robot, showing that the learned policies generalize to changes in system parameters, unreliable sensor measurements, and variation in environmental conditions, including varied terrains and a range of different gravities. Our experiments demonstrate that our method not only learns fast, power-efficient feedback policies for rolling gaits, but that these policies can succeed with only the limited onboard sensing provided by SUPERball’s accelerometers. We compare the learned feedback policies to learned open-loop policies and hand-engineered controllers, and demonstrate that the learned policy enables the first continuous, reliable locomotion gait for the real SUPERball robot. Our code and other supplementary materials are available from http://rll.berkeley.edu/drl_tensegrity |
| Tasks | |
| Published | 2016-09-28 |
| URL | http://arxiv.org/abs/1609.09049v3 |
| http://arxiv.org/pdf/1609.09049v3.pdf | |
| PWC | https://paperswithcode.com/paper/deep-reinforcement-learning-for-tensegrity |
| Repo | |
| Framework | |
Associative Adversarial Networks
| Title | Associative Adversarial Networks |
| Authors | Tarik Arici, Asli Celikyilmaz |
| Abstract | We propose a higher-level associative memory for learning adversarial networks. Generative adversarial network (GAN) framework has a discriminator and a generator network. The generator (G) maps white noise (z) to data samples while the discriminator (D) maps data samples to a single scalar. To do so, G learns how to map from high-level representation space to data space, and D learns to do the opposite. We argue that higher-level representation spaces need not necessarily follow a uniform probability distribution. In this work, we use Restricted Boltzmann Machines (RBMs) as a higher-level associative memory and learn the probability distribution for the high-level features generated by D. The associative memory samples its underlying probability distribution and G learns how to map these samples to data space. The proposed associative adversarial networks (AANs) are generative models in the higher-levels of the learning, and use adversarial non-stochastic models D and G for learning the mapping between data and higher-level representation spaces. Experiments show the potential of the proposed networks. |
| Tasks | |
| Published | 2016-11-18 |
| URL | http://arxiv.org/abs/1611.06953v1 |
| http://arxiv.org/pdf/1611.06953v1.pdf | |
| PWC | https://paperswithcode.com/paper/associative-adversarial-networks |
| Repo | |
| Framework | |
Search Improves Label for Active Learning
| Title | Search Improves Label for Active Learning |
| Authors | Alina Beygelzimer, Daniel Hsu, John Langford, Chicheng Zhang |
| Abstract | We investigate active learning with access to two distinct oracles: Label (which is standard) and Search (which is not). The Search oracle models the situation where a human searches a database to seed or counterexample an existing solution. Search is stronger than Label while being natural to implement in many situations. We show that an algorithm using both oracles can provide exponentially large problem-dependent improvements over Label alone. |
| Tasks | Active Learning |
| Published | 2016-02-23 |
| URL | http://arxiv.org/abs/1602.07265v2 |
| http://arxiv.org/pdf/1602.07265v2.pdf | |
| PWC | https://paperswithcode.com/paper/search-improves-label-for-active-learning |
| Repo | |
| Framework | |
Objective Micro-Facial Movement Detection Using FACS-Based Regions and Baseline Evaluation
| Title | Objective Micro-Facial Movement Detection Using FACS-Based Regions and Baseline Evaluation |
| Authors | Adrian K. Davison, Cliff Lansley, Choon Ching Ng, Kevin Tan, Moi Hoon Yap |
| Abstract | Micro-facial expressions are regarded as an important human behavioural event that can highlight emotional deception. Spotting these movements is difficult for humans and machines, however research into using computer vision to detect subtle facial expressions is growing in popularity. This paper proposes an individualised baseline micro-movement detection method using 3D Histogram of Oriented Gradients (3D HOG) temporal difference method. We define a face template consisting of 26 regions based on the Facial Action Coding System (FACS). We extract the temporal features of each region using 3D HOG. Then, we use Chi-square distance to find subtle facial motion in the local regions. Finally, an automatic peak detector is used to detect micro-movements above the newly proposed adaptive baseline threshold. The performance is validated on two FACS coded datasets: SAMM and CASME II. This objective method focuses on the movement of the 26 face regions. When comparing with the ground truth, the best result was an AUC of 0.7512 and 0.7261 on SAMM and CASME II, respectively. The results show that 3D HOG outperformed for micro-movement detection, compared to state-of-the-art feature representations: Local Binary Patterns in Three Orthogonal Planes and Histograms of Oriented Optical Flow. |
| Tasks | Optical Flow Estimation |
| Published | 2016-12-15 |
| URL | http://arxiv.org/abs/1612.05038v1 |
| http://arxiv.org/pdf/1612.05038v1.pdf | |
| PWC | https://paperswithcode.com/paper/objective-micro-facial-movement-detection |
| Repo | |
| Framework | |
Theoretical Evaluation of Feature Selection Methods based on Mutual Information
| Title | Theoretical Evaluation of Feature Selection Methods based on Mutual Information |
| Authors | Cláudia Pascoal, M. Rosário Oliveira, António Pacheco, Rui Valadas |
| Abstract | Feature selection methods are usually evaluated by wrapping specific classifiers and datasets in the evaluation process, resulting very often in unfair comparisons between methods. In this work, we develop a theoretical framework that allows obtaining the true feature ordering of two-dimensional sequential forward feature selection methods based on mutual information, which is independent of entropy or mutual information estimation methods, classifiers, or datasets, and leads to an undoubtful comparison of the methods. Moreover, the theoretical framework unveils problems intrinsic to some methods that are otherwise difficult to detect, namely inconsistencies in the construction of the objective function used to select the candidate features, due to various types of indeterminations and to the possibility of the entropy of continuous random variables taking null and negative values. |
| Tasks | Feature Selection |
| Published | 2016-09-21 |
| URL | http://arxiv.org/abs/1609.06575v2 |
| http://arxiv.org/pdf/1609.06575v2.pdf | |
| PWC | https://paperswithcode.com/paper/theoretical-evaluation-of-feature-selection |
| Repo | |
| Framework | |
