A novel monotonic fixed-point algorithm for l1-regularized least square vector and matrix problem

Least square problem with l₁ regularization has been proposed as a promising method for sparse signal reconstruction (e.g., basis pursuit de-noising and compressed sensing) and feature selection (e.g., the Lasso algorithm) in signal processing, statistics, and related fields. These problems can be cast as l₁-regularized least-square program (LSP). In this paper, we propose a novel monotonic fixed point method to solve large-scale l₁-regularized LSP. And we also prove the stability and convergence of the proposed method. Furthermore we generalize this method to least square matrix problem and apply it in nonnegative matrix factorization (NMF). The method is illustrated on sparse signal reconstruction, partner recognition and blind source separation problems, and the method tends to convergent faster and sparser than other l₁-regularized algorithms.

Learning an L1-regularized Gaussian Bayesian Network in the Equivalence Class Space

Learning the structure of a graphical model from data is a common task in a wide range of practical applications. In this paper, we focus on Gaussian Bayesian networks, i.e., on continuous data and directed acyclic graphs with a joint probability density of all variables given by a Gaussian. We propose to work in an equivalence class search space, specifically using the k-greedy equivalence search algorithm. This, combined with regularization techniques to guide the structure search, can learn sparse networks close to the one that generated the data. We provide results on some synthetic networks and on modeling the gene network of the two biological pathways regulating the biosynthesis of isoprenoids for the Arabidopsis thaliana plant

Regularized Online Mixture of Gaussians for Background Subtraction

Mixture of Gaussians (MoG) modelling [13] is a popular approach to background subtraction in video sequences. Although the algorithm shows good empirical performance, it lacks theoretical justification. In this paper, we give a justification for it from an online stochastic expectation maximization (EM) viewpoint and extend it to a general framework of regularized online classification EM for MoG with guaranteed convergence. By choosing a special regularization function, l1 norm, we derived a new set of updating equations for l1 regularized online MoG. It is shown empirically that l1 regularized online MoG converge faster than the original online MoG .

Sequential alternating proximal method for scalable sparse structural SVMs

Structural Support Vector Machines (SSVMs) have recently gained wide prominence in classifying structured and complex objects like parse-trees, image segments and Part-of-Speech (POS) tags. Typical learning algorithms used in training SSVMs result in model parameters which are vectors residing in a large-dimensional feature space. Such a high-dimensional model parameter vector contains many non-zero components which often lead to slow prediction and storage issues. Hence there is a need for sparse parameter vectors which contain a very small number of non-zero components. L1-regularizer and elastic net regularizer have been traditionally used to get sparse model parameters. Though L1-regularized structural SVMs have been studied in the past, the use of elastic net regularizer for structural SVMs has not been explored yet. In this work, we formulate the elastic net SSVM and propose a sequential alternating proximal algorithm to solve the dual formulation. We compare the proposed method with existing methods for L1-regularized Structural SVMs. Experiments on large-scale benchmark datasets show that the proposed dual elastic net SSVM trained using the sequential alternating proximal algorithm scales well and results in highly sparse model parameters while achieving a comparable generalization performance. Hence the proposed sequential alternating proximal algorithm is a competitive method to achieve sparse model parameters and a comparable generalization performance when elastic net regularized Structural SVMs are used on very large datasets.

An Interval-based Multiobjective Approach to Feature Subset Selection Using Joint Modeling of Objectives and Variables

This paper studies feature subset selection in classification using a multiobjective estimation of distribution algorithm. We consider six functions, namely area under ROC curve, sensitivity, specificity, precision, F1 measure and Brier score, for evaluation of feature subsets and as the objectives of the problem. One of the characteristics of these objective functions is the existence of noise in their values that should be appropriately handled during optimization. Our proposed algorithm consists of two major techniques which are specially designed for the feature subset selection problem. The first one is a solution ranking method based on interval values to handle the noise in the objectives of this problem. The second one is a model estimation method for learning a joint probabilistic model of objectives and variables which is used to generate new solutions and advance through the search space. To simplify model estimation, l1 regularized regression is used to select a subset of problem variables before model learning. The proposed algorithm is compared with a well-known ranking method for interval-valued objectives and a standard multiobjective genetic algorithm. Particularly, the effects of the two new techniques are experimentally investigated. The experimental results show that the proposed algorithm is able to obtain comparable or better performance on the tested datasets.

The effects of L1 orthography on processing an artificial logographic script

To date, studies have focused on the acquisition of alphabetic second languages (L2s) in alphabetic first language (L1) users, demonstrating significant transfer effects. The present study examined the process from a reverse perspective, comparing logographic (Mandarin-Chinese) and alphabetic (English) L1 users in the acquisition of an artificial logographic script, in order to determine whether similar language-specific advantageous transfer effects occurred. English monolinguals, English-French bilinguals and Chinese-English bilinguals learned a small set of symbols in an artificial logographic script and were subsequently tested on their ability to process this script in regard to three main perspectives: L2 reading, L2 working memory (WM), and inner processing strategies. In terms of L2 reading, a lexical decision task on the artificial symbols revealed markedly faster response times in the Chinese-English bilinguals, indicating a logographic transfer effect suggestive of a visual processing advantage. A syntactic decision task evaluated the degree to which the new language was mastered beyond the single word level. No L1-specific transfer effects were found for artificial language strings. In order to investigate visual processing of the artificial logographs further, a series of WM experiments were conducted. Artificial logographs were recalled under concurrent auditory and visuo-spatial suppression conditions to disrupt phonological and visual processing, respectively. No L1-specific transfer effects were found, indicating no visual processing advantage of the Chinese-English bilinguals. However, a bilingual processing advantage was found indicative of a superior ability to control executive functions. In terms of L1 WM, the Chinese-English bilinguals outperformed the alphabetic L1 users when processing L1 words, indicating a language experience-specific advantage. Questionnaire data on the cognitive strategies that were deployed during the acquisition and processing of the artificial logographic script revealed that the Chinese-English bilinguals rated their inner speech as lower than the alphabetic L1 users, suggesting that they were transferring their phonological processing skill set to the acquisition and use of an artificial script. Overall, evidence was found to indicate that language learners transfer specific L1 orthographic processing skills to L2 logographic processing. Additionally, evidence was also found indicating that a bilingual history enhances cognitive performance in L2.

A novel corepressor, BCoR-L1, represses transcription through an interaction with CtBP

Corepressors play a crucial role in negative gene regulation and are defective in several diseases. BCoR is a corepressor for the BCL6 repressor protein. Here we describe and functionally characterize BCoR-L1, a homolog of BCoR. When tethered to a heterologous promoter, BCoR-L1 is capable of strong repression. Like other corepressors, BCoR-L1 associates with histone deacetylase (HDAC) activity. Specifically, BCoR-L1 coprecipitates with the Class II HDACs, HDAC4, HDAC5, and HDAC7, suggesting that they are involved in its role as a transcriptional repressor. BCoR-L1 also interacts with the CtBP corepressor through a CtBP-interacting motif in its amino terminus. Abrogation of the CtBP binding site within BCoR-L1 partially relieves BCoR-L1-mediated transcriptional repression. Furthermore, BCoR-L1 is located on the E-cadherin promoter, a known CtBP-regulated promoter, and represses the E-cadherin promoter activity in a reporter assay. The inhibition of BCoR-L1 expression by RNA-mediated interference results in derepression of E-cadherin in cells that do not normally express E-cadherin, indicating that BCoR-L1 contributes to the repression of an authentic endogenous CtBP target.

A spoofing detection method for civilian L1 GPS and the E1-B Galileo Safety of Life service

This paper describes an effective method for signal-authentication and spoofing detection for civilian GNSS receivers using the GPS L1 C/A and the Galileo E1-B Safety of Life service. The paper discusses various spoofing attack profiles and how the proposed method is able to detect these attacks. This method is relatively low-cost and can be suitable for numerous mass-market applications. This paper is the subject of a pending patent.

L1 Learning Strategy Instruction does make a difference in EFL listening: An empirical study.

In language learning, listening is the basic skill which learners should begin to develop other skills, namely speaking, reading and writing. This sequence of language learning in most English as Foreign Language (EFL) settings goes against the stream, learning first reading and writing and later listening and speaking. This study investigates the effects of cognitive, process-based approach to instructing EFL listening strategies over 11 weeks during a semester in Persian (L1). Lower intermediate female participants (N = 50) came from a couple of EFL classrooms in an English Language Institute in Iran. The experimental group (n = 25) listened to their classroom activities using a methodology that led learners through four cognitive processes (guessing, making inference, identifying topics and repetition) in Persian was basically successful in EFL listening. The same teacher taught the control group (n = 25), which listened to the same classroom listening activities without any guided attention to the learning strategy process in Persian. A pre and post listening test made by a group of experts in the language institute tracked any development in light of cognitive learning strategy instruction in EFL listening through L1. The hypothesis was that the experimental group received the guided attention in L1 during the classroom listening activities made greater gains and was verified despite the partial improvement of the control group.

Are alphabetic language-derived models of L2 reading relevant to L1 logographic background readers?

In this paper, we argue that second language (L2) reading research, which has been informed by studies involving first language (L1) alphabetic English reading, may be less relevant to L2 readers with non-alphabetic reading backgrounds, such as Chinese readers with an L1 logographic (Chinese character) learning history. We provide both neuroanatomical and behavioural evidence from Chinese language reading studies to support our claims. The paper concludes with an argument outlining the need for a universal L2 reading model which can adequately account for readers with diverse L1 orthographic language learning histories.

Enhancing foreign language learning through listening strategy delivered in L1: an experimental study

Listening used in language teaching refers to a complex process that allows us to understand spoken language. The current study, conducted in Iran with an experimental design, investigated the effectiveness of teaching listening strategies delivered in L1 (Persian) and its effect on listening comprehension in L2. Five listening strategies: Guessing, making inferences, identifying topics, repetition, and note-taking were taught over 14 weeks during a semester. Sixty lower intermediate female participants came from two EFL classrooms in an English language institute. The experimental class (n = 30) who listened to their classroom activities performed better (t value = 10.083) than the control class using a methodology that led learners through five listening strategies in Persian. The same teacher taught the students in the control class (n = 30), who listened to the same classroom listening activities without any of the above listening strategies. A pre and post listening test made by a group of experts in the language institute assessed the effect of teaching listening strategies delivered in L1. Results gathered on the post intervention listening test revealed that listening strategies delivered in L1 led to a statistically significant improvement in their discrete listening scores compared with the control group.

The impact of English as a Foreign Language (EFL) listening comprehension through first language (L1) listening strategy training

Listening is the basic and complementary skill in second language learning. The term listening is used in language teaching to refer to a complex process that allows us to understand spoken language. Listening, the most widely used language skill, is often used in conjunction with the other skills of speaking, reading and writing. Listening is not only a skill area in primary language performance (L1), but is also a critical means of acquiring a second language (L2). Listening is the channel in which we process language in real time – employing pacing, units of encoding and decoding (the 2 processes are central to interpretation and meaning making) and pausing (allows for reflection) that are unique to spoken language. Despite the wide range of areas investigated in listening strategies during training, there is a lack of research looking specifically at how effectively L1 listening strategy training may transfer to L2. To investigate the development of any such transfer patterns the instructional design and implementation of listening strategy of L1 will be critical.