
显示样式: 排序: IF: - GO 导出
-
The Universal Approximation Property Ann. Math. Artif. Intel. (IF 0.778) Pub Date : 2021-01-22 Anastasis Kratsios
The universal approximation property of various machine learning models is currently only understood on a case-by-case basis, limiting the rapid development of new theoretically justified neural network architectures and blurring our understanding of our current models’ potential. This paper works towards overcoming these challenges by presenting a characterization, a representation, a construction
-
Column generation for the equilibrium route-flow traffic assignment problem Ann. Math. Artif. Intel. (IF 0.778) Pub Date : 2021-01-08 Alexander Krylatov
Today efficient traffic management seems to be impossible without the support of the artificial intelligence systems based on mathematical models of traffic flow assignment since a modern road network is a large-scale system with huge amounts of elements. The present paper is devoted to the route-flow traffic assignment problem, which solution is the most valuable from decision-making perspectives
-
Optimal training for adversarial games Ann. Math. Artif. Intel. (IF 0.778) Pub Date : 2021-01-07 Ovidiu Calin
We consider adversarial games solved by a continuous version of the simultaneous gradient descent method, whose associated differential system is induced by a Hamiltonian function. In this case the solution obtained by training does never converge to the Nash equilibrium, but it might be closest to it at some special time instance. We analyse this optimal training time in two distinct situations: the
-
Data driven design for online industrial auctions Ann. Math. Artif. Intel. (IF 0.778) Pub Date : 2021-01-05 Qing Chuan Ye, Jason Rhuggenaath, Yingqian Zhang, Sicco Verwer, Michiel Jurgen Hilgeman
Designing auction parameters for online industrial auctions is a complex problem due to highly heterogeneous items. Currently, online auctioneers rely heavily on their experts in auction design. The ability of predicting how well an auction will perform prior to the start comes in handy for auctioneers. If an item is expected to be a low-performing item, the auctioneer can take certain actions to influence
-
Schema mapping coverage Ann. Math. Artif. Intel. (IF 0.778) Pub Date : 2021-01-02 Ning Deng, Jan Chomicki
In this paper, we introduce and study schema mapping coverage for relational databases. Given a relational schema mapping in the presence of both source dependencies and target dependencies, the coverage problem is to decide and describe which source instances have solutions under the mapping. Our main motivation is to describe limitations of schema mappings and hence to effectively determine if the
-
An integrated bi-objective U-shaped assembly line balancing and parts feeding problem: optimization model and exact solution method Ann. Math. Artif. Intel. (IF 0.778) Pub Date : 2020-11-20 Ömer Faruk Yılmaz
In this study, an integrated bi-objective objective U-shaped assembly line balancing and parts feeding problem is explored by considering the heterogeneity inherent of workers. An optimization model is developed to formulate the addressed problem. Since the problem includes two different objectives, namely the minimizing the operational cost and maximum workload imbalance, the Pareto-optimal solutions
-
On generalization in moment-based domain adaptation Ann. Math. Artif. Intel. (IF 0.778) Pub Date : 2020-11-19 Werner Zellinger, Bernhard A. Moser, Susanne Saminger-Platz
Domain adaptation algorithms are designed to minimize the misclassification risk of a discriminative model for a target domain with little training data by adapting a model from a source domain with a large amount of training data. Standard approaches measure the adaptation discrepancy based on distance measures between the empirical probability distributions in the source and target domain. In this
-
Valid attacks in argumentation frameworks with recursive attacks Ann. Math. Artif. Intel. (IF 0.778) Pub Date : 2020-11-19 C. Cayrol, J. Fandinno, L. Fariñas del Cerro, M.-C. Lagasquie-Schiex
The purpose of this work is to study a generalisation of Dung’s abstract argumentation frameworks that allows representing recursive attacks, that is, a class of attacks whose targets are other attacks. We do this by developing a theory of argumentation where the classic role of attacks in defeating arguments is replaced by a subset of them, which is “extension-dependent” and which, intuitively, represents
-
Efficient implicit Lagrangian twin parametric insensitive support vector regression via unconstrained minimization problems Ann. Math. Artif. Intel. (IF 0.778) Pub Date : 2020-11-19 Deepak Gupta, Bharat Richhariya
In this paper, an efficient implicit Lagrangian twin parametric insensitive support vector regression is proposed which leads to a pair of unconstrained minimization problems, motivated by the works on twin parametric insensitive support vector regression (Peng: Neurocomputing. 79, 26–38, 2012), and Lagrangian twin support vector regression (Balasundaram and Tanveer: Neural Comput. Applic. 22(1), 257–267
-
Data-driven algorithm selection and tuning in optimization and signal processing Ann. Math. Artif. Intel. (IF 0.778) Pub Date : 2020-11-12 Jesús A. De Loera, Jamie Haddock, Anna Ma, Deanna Needell
Machine learning algorithms typically rely on optimization subroutines and are well known to provide very effective outcomes for many types of problems. Here, we flip the reliance and ask the reverse question: can machine learning algorithms lead to more effective outcomes for optimization problems? Our goal is to train machine learning methods to automatically improve the performance of optimization
-
Correction to: Directed Lovász Local Lemma and Shearer’s Lemma Ann. Math. Artif. Intel. (IF 0.778) Pub Date : 2020-11-09 Lefteris Kirousis, John Livieratos, Kostas I. Psaromiligkos
The proof of Theorem 1a of our article that appears in Annals of Mathematics and Artificial Intelligence 88(1–3):133-155 (2020) has a mistake. We give here the corrected proof, together with a new version of Definition 3 in that article that the correction necessitated.
-
Multiple-source adaptation theory and algorithms Ann. Math. Artif. Intel. (IF 0.778) Pub Date : 2020-11-05 Ningshan Zhang, Mehryar Mohri, Judy Hoffman
We present a general theoretical and algorithmic analysis of the problem of multiple-source adaptation, a key learning problem in applications. We derive new normalized solutions with strong theoretical guarantees for the cross-entropy loss and other similar losses. We also provide new guarantees that hold in the case where the conditional probabilities for the source domains are distinct. We further
-
Query answering DL-lite knowledge bases from hidden datasets Ann. Math. Artif. Intel. (IF 0.778) Pub Date : 2020-11-05 Ghassen Hamdi, Mohamed Nazih Omri, Salem Benferhat, Zied Bouraoui, Odile Papini
Unifying access to data using structured knowledge is the main problem studied in ontology-based data access (OBDA). Data are often provided by several information sources, and this has led to a number of methods that merge them in order to get a unified point of view. Existing merging approaches assume that the content of datasets is known and available. However, in several applications, it might
-
NSLPCD: Topic based tweets clustering using Node significance based label propagation community detection algorithm Ann. Math. Artif. Intel. (IF 0.778) Pub Date : 2020-09-24 Jagrati Singh, Anil Kumar Singh
Social networks like Twitter, Facebook have recently become the most widely used communication platforms for people to propagate information rapidly. Fast diffusion of information creates accuracy and scalability issues towards topic detection. Most of the existing approaches can detect the most popular topics on a large scale. However, these approaches are not effective for faster detection. This
-
Categorical study for algebras of Fitting’s lattice-valued logic and lattice-valued modal logic Ann. Math. Artif. Intel. (IF 0.778) Pub Date : 2020-09-21 Kumar Sankar Ray, Litan Kumar Das
The paper explores categorical interconnections between lattice-valued relational systems and algebras of Fitting’s lattice-valued modal logic. We define lattice-valued Boolean systems, and then we study adjointness and co-adjointness of functors defined on them. As a result, we get a duality for algebras of lattice-valued logic. Following this duality result, we establish a duality for algebras of
-
Black-box combinatorial optimization using models with integer-valued minima Ann. Math. Artif. Intel. (IF 0.778) Pub Date : 2020-09-19 Laurens Bliek, Sicco Verwer, Mathijs de Weerdt
When a black-box optimization objective can only be evaluated with costly or noisy measurements, most standard optimization algorithms are unsuited to find the optimal solution. Specialized algorithms that deal with exactly this situation make use of surrogate models. These models are usually continuous and smooth, which is beneficial for continuous optimization problems, but not necessarily for combinatorial
-
On integer closure in a system of unit two variable per inequality constraints Ann. Math. Artif. Intel. (IF 0.778) Pub Date : 2020-09-15 K. Subramani, P. Wojciechowski
In this paper, we study the problem of computing the lattice point closure of a conjunction of Unit Two Variable Per Inequality (UTVPI) constraints. We accomplish this by adapting Johnson’s all pairs shortest path algorithm to UTVPI constraint systems (UCSs). Thus, we obtain a closure algorithm that is efficient for sparse constraint systems. This problem has been extremely well-studied in the literature
-
Multivariate time series analysis from a Bayesian machine learning perspective Ann. Math. Artif. Intel. (IF 0.778) Pub Date : 2020-09-04 Jinwen Qiu, S. Rao Jammalamadaka, Ning Ning
In this paper, we perform multivariate time series analysis from a Bayesian machine learning perspective through the proposed multivariate Bayesian time series (MBTS) model. The multivariate structure and the Bayesian framework allow the model to take advantage of the association structure among target series, select important features, and train the data-driven model at the same time. Extensive analyses
-
Real-time solving of computationally hard problems using optimal algorithm portfolios Ann. Math. Artif. Intel. (IF 0.778) Pub Date : 2020-08-28 Yair Nof, Ofer Strichman
Various hard real-time systems have a desired requirement which is impossible to fulfill: to solve a computationally hard optimization problem within a short and fixed amount of time T, e.g., T = 0.5 seconds. For such a task, the exact, exponential algorithms, as well as various Polynomial-Time Approximation Schemes, are irrelevant because they can exceed T. What is left in practice is to combine various
-
Classifying the valence of autobiographical memories from fMRI data Ann. Math. Artif. Intel. (IF 0.778) Pub Date : 2020-08-04 Alex Frid, Larry M. Manevitz, Norberto Eiji Nawa
We show that fMRI analysis using machine learning tools are sufficient to distinguish valence (i.e., positive or negative) of freely retrieved autobiographical memories in a cross-participant setting. Our methodology uses feature selection (ReliefF) in combination with boosting methods, both applied directly to data represented in voxel space. In previous work using the same data set, Nawa and Ando
-
Correction to: Log A G : An algebraic non-monotonic logic for reasoning with graded propositions Ann. Math. Artif. Intel. (IF 0.778) Pub Date : 2020-08-02 Nourhan Ehab, Haythem O. Ismail
Due to an oversight by the Publisher during the typesetting stage, an uncorrected version of the paper was published.
-
Derivation and analysis of parallel-in-time neural ordinary differential equations Ann. Math. Artif. Intel. (IF 0.778) Pub Date : 2020-07-25 E. Lorin
The introduction in 2015 of Residual Neural Networks (RNN) and ResNET allowed for outstanding improvements of the performance of learning algorithms for evolution problems containing a “large” number of layers. Continuous-depth RNN-like models called Neural Ordinary Differential Equations (NODE) were then introduced in 2019. The latter have a constant memory cost, and avoid the a priori specification
-
Digitized rotations of 12 neighbors on the triangular grid Ann. Math. Artif. Intel. (IF 0.778) Pub Date : 2020-07-22 Aydın Avkan; Benedek Nagy; Müge Saadetoğlu
There are various geometric transformations, e.g., translations, rotations, which are always bijections in the Euclidean space. Their digital counterpart, i.e., their digitized variants are defined on discrete grids, since most of our pictures are digital nowadays. Usually, these digital versions of the transformations have different properties than the original continuous variants have. Rotations
-
Mutual conditional independence and its applications to model selection in Markov networks Ann. Math. Artif. Intel. (IF 0.778) Pub Date : 2020-07-21 Niharika Gauraha; Swapan K. Parui
The fundamental concepts underlying Markov networks are the conditional independence and the set of rules called Markov properties that translate conditional independence constraints into graphs. We introduce the concept of mutual conditional independence in an independent set of a Markov network, and we prove its equivalence to the Markov properties under certain regularity conditions. This extends
-
On a hypergraph probabilistic graphical model Ann. Math. Artif. Intel. (IF 0.778) Pub Date : 2020-07-10 Mohammad Ali Javidian; Zhiyu Wang; Linyuan Lu; Marco Valtorta
We propose a directed acyclic hypergraph framework for a probabilistic graphical model that we call Bayesian hypergraphs. The space of directed acyclic hypergraphs is much larger than the space of chain graphs. Hence Bayesian hypergraphs can model much finer factorizations than Bayesian networks or LWF chain graphs and provide simpler and more computationally efficient procedures for factorizations
-
L o g A G : An algebraic Non-Monotonic logic for reasoning with graded propositions Ann. Math. Artif. Intel. (IF 0.778) Pub Date : 2020-06-20 Nourhan Ehab, Haythem O. Ismail
We present LogAG, a weighted algebraic non-monotonic logic for reasoning with graded beliefs. LogAG is algebraic in that it is a language of only terms, some of which denote propositions and may be associated with ordered grades. The grades could be taken to represent a wide variety of phenomena including preference degrees, priority levels, trust ranks, and uncertainty measures. Reasoning in LogAG
-
Generalized feature similarity measure Ann. Math. Artif. Intel. (IF 0.778) Pub Date : 2020-05-20 Firuz Kamalov
Quantifying the degree of relation between a feature and target class is one of the key aspects of machine learning. In this regard, information gain (IG) and χ2 are two of the most widely used measures in feature evaluation. In this paper, we discuss a novel approach to unifying these and other existing feature evaluation measures under a common framework. In particular, we introduce a new generalized
-
On biased random walks, corrupted intervals, and learning under adversarial design Ann. Math. Artif. Intel. (IF 0.778) Pub Date : 2020-05-18 Daniel Berend; Aryeh Kontorovich; Lev Reyzin; Thomas Robinson
We tackle some fundamental problems in probability theory on corrupted random processes on the integer line. We analyze when a biased random walk is expected to reach its bottommost point and when intervals of integer points can be detected under a natural model of noise. We apply these results to problems in learning thresholds and intervals under a new model for learning under adversarial design
-
Leveraging cluster backbones for improving MAP inference in statistical relational models Ann. Math. Artif. Intel. (IF 0.778) Pub Date : 2020-05-07 Mohamed-Hamza Ibrahim; Christopher Pal; Gilles Pesant
A wide range of important problems in machine learning, expert system, social network analysis, bioinformatics and information theory can be formulated as a maximum a-posteriori (MAP) inference problem on statistical relational models. While off-the-shelf inference algorithms that are based on local search and message-passing may provide adequate solutions in some situations, they frequently give poor
-
Instance space analysis for a personnel scheduling problem Ann. Math. Artif. Intel. (IF 0.778) Pub Date : 2020-04-24 Lucas Kletzander, Nysret Musliu, Kate Smith-Miles
This paper considers the Rotating Workforce Scheduling Problem, and shows how the strengths and weaknesses of various solution methods can be understood by the in-depth evaluation offered by a recently developed methodology known as Instance Space Analysis. We first present a set of features aiming to describe hardness of test instances. We create a new, more diverse set of instances based on an initial
-
What do you really want to do? Towards a Theory of Intentions for Human-Robot Collaboration Ann. Math. Artif. Intel. (IF 0.778) Pub Date : 2020-03-24 Rocio Gomez, Mohan Sridharan, Heather Riley
The architecture described in this paper encodes a theory of intentions based on the key principles of non-procrastination, persistence, and automatically limiting reasoning to relevant knowledge and observations. The architecture reasons with transition diagrams of any given domain at two different resolutions, with the fine-resolution description defined as a refinement of, and hence tightly-coupled
-
Learning non-convex abstract concepts with regulated activation networks Ann. Math. Artif. Intel. (IF 0.778) Pub Date : 2020-03-21 Rahul Sharma, Bernardete Ribeiro, Alexandre Miguel Pinto, F. Amílcar Cardoso
Perceivable objects are customarily termed as concepts and their representations (localist-distributed, modality-specific, or experience-dependent) are ingrained in our lives. Despite a considerable amount of computational modeling research focuses on concrete concepts, no comprehensible method for abstract concepts has hitherto been considered. Abstract concepts can be viewed as a blend of concrete
-
Human-in-the-loop active learning via brain computer interface Ann. Math. Artif. Intel. (IF 0.778) Pub Date : 2020-03-16 Eitan Netzer, Amir B. Geva
This paper develops and examines an innovative methodology for training an artificial neural network to identify and tag target visual objects in a given database. While the field of Artificial Intelligence in general, and computer vision in particular, has greatly advanced in recent years, fast and efficient methods for tagging (i.e., labeling) visual targets are still lacking. Tagging data is important
-
Multiple k −opt evaluation multiple k −opt moves with GPU high performance local search to large-scale traveling salesman problems Ann. Math. Artif. Intel. (IF 0.778) Pub Date : 2020-04-16 Wen-Bao Qiao; Jean-Charles Créput
The 2-opt, 3-opt or k–opt heuristics are classical local search algorithms for traveling salesman problems (TSP) in combinatorial optimization area, while sequential k–opt complete neighborhood examination takes polynomial time complexity which is timeconsuming to approach large scale TSP instances. This paper introduces a reasonable methodology called “multiple k–opt evaluation, multiple k–opt moves”
-
Approximate kernel partial least squares Ann. Math. Artif. Intel. (IF 0.778) Pub Date : 2020-03-27 Xiling Liu; Shuisheng Zhou
As an extension of partial least squares (PLS), kernel partial least squares (KPLS) is an very important methods to find nonlinear patterns from data. However, the application of KPLS to large-scale problems remains a big challenge, due to storage and computation issues in the number of examples. To address this limitation, we utilize randomness to design scalable new variants of the kernel matrix
-
Characterization Of sampling patterns for low-tt-rank tensor retrieval Ann. Math. Artif. Intel. (IF 0.778) Pub Date : 2020-03-16 Morteza Ashraphijuo; Xiaodong Wang
In this paper, we analyze the fundamental conditions for low-rank tensor completion given the separation or tensor-train (TT) rank, i.e., ranks of TT unfoldings. We exploit the algebraic structure of the TT decomposition to obtain the deterministic necessary and sufficient conditions on the locations of the samples to ensure finite completability. Specifically, we propose an algebraic geometric analysis
-
Energy allocation and payment: a game-theoretic approach Ann. Math. Artif. Intel. (IF 0.778) Pub Date : 2020-02-18 Paolo Giuliodori; Stefano Bistarelli; Dimitri Mugnai
Nowadays, energy represents the most important resource; however, we need to face several energy-related rising issues, one main concern is how energy is consumed. In particular, how we can stimulate consumers on a specific behaviour. In this work, we present a model facing energy allocation and payment. Thus, we start with the explanation of the first step of our work concerning a mechanism design
-
Discrepancy-Based Theory and Algorithms for Forecasting Non-Stationary Time Series Ann. Math. Artif. Intel. (IF 0.778) Pub Date : 2020-02-04 Vitaly Kuznetsov; Mehryar Mohri
We present data-dependent learning bounds for the general scenario of non-stationary non-mixing stochastic processes. Our learning guarantees are expressed in terms of a data-dependent measure of sequential complexity and a discrepancy measure that can be estimated from data under some mild assumptions. Our learning bounds guide the design of new algorithms for non-stationary time series forecasting
-
Semantic string operation for specializing AHC algorithm for text clustering Ann. Math. Artif. Intel. (IF 0.778) Pub Date : 2020-01-13 Taeho Jo
This article proposes the modified AHC (Agglomerative Hierarchical Clustering) algorithm which clusters string vectors, instead of numerical vectors, as the approach to the text clustering. The results from applying the string vector based algorithms to the text clustering were successful in previous works and synergy effect between the text clustering and the word clustering is expected by combining
-
Sufficient conditions for the existence of a sample mean of time series under dynamic time warping Ann. Math. Artif. Intel. (IF 0.778) Pub Date : 2020-01-10 Brijnesh Jain; David Schultz
Time series averaging is an important subroutine for several time series data mining tasks. The most successful approaches formulate the problem of time series averaging as an optimization problem based on the dynamic time warping (DTW) distance. The existence of an optimal solution, called sample mean, is an open problem for more than four decades. Its existence is a necessary prerequisite to formulate
-
A branch & bound algorithm to determine optimal cross-splits for decision tree induction Ann. Math. Artif. Intel. (IF 0.778) Pub Date : 2020-01-03 Ferdinand Bollwein; Martin Dahmen; Stephan Westphal
State-of-the-art decision tree algorithms are top-down induction heuristics which greedily partition the attribute space by iteratively choosing the best split on an individual attribute. Despite their attractive performance in terms of runtime, simple examples, such as the XOR-Problem, point out that these heuristics often fail to find the best classification rules if there are strong interactions
-
The SAT+CAS method for combinatorial search with applications to best matrices Ann. Math. Artif. Intel. (IF 0.778) Pub Date : 2019-12-05 Curtis Bright; Dragomir Ž. Đoković; Ilias Kotsireas; Vijay Ganesh
In this paper, we provide an overview of the SAT+CAS method that combines satisfiability checkers (SAT solvers) and computer algebra systems (CAS) to resolve combinatorial conjectures, and present new results vis-à-vis best matrices. The SAT+CAS method is a variant of the Davis–Putnam–Logemann–Loveland DPLL(T) architecture, where the T solver is replaced by a CAS. We describe how the SAT+CAS method
-
A subdivision algorithm to reason on high-degree polynomial constraints over finite domains Ann. Math. Artif. Intel. (IF 0.778) Pub Date : 2019-12-05 Federico Bergenti; Stefania Monica
This paper proposes an algorithm to reason on constraints expressed in terms of polynomials with integer coefficients whose variables take values from finite subsets of the integers. The proposed algorithm assumes that an initial approximation of the domains of variables is available in terms of a bounding box, and it recursively subdivides the box into disjoint boxes until a termination condition
-
Learning under p -tampering poisoning attacks Ann. Math. Artif. Intel. (IF 0.778) Pub Date : 2019-12-03 Saeed Mahloujifar; Dimitrios I. Diochnos; Mohammad Mahmoody
Recently, Mahloujifar and Mahmoody (Theory of Cryptography Conference’17) studied attacks against learning algorithms using a special case of Valiant’s malicious noise, called p-tampering, in which the adversary gets to change any training example with independent probability p but is limited to only choose ‘adversarial’ examples with correct labels. They obtained p-tampering attacks that increase
-
Directed Lovász local lemma and Shearer’s lemma Ann. Math. Artif. Intel. (IF 0.778) Pub Date : 2019-12-02 Lefteris Kirousis; John Livieratos; Kostas I. Psaromiligkos
Moser and Tardos (J. ACM (JACM) 57(2), 11 2010) gave an algorithmic proof of the lopsided Lovász local lemma (LLL) in the variable framework, where each of the undesirable events is assumed to depend on a subset of a collection of independent random variables. For the proof, they define a notion of a lopsided dependency between the events suitable for this framework. In this work, we strengthen this
-
Non-terminating processes in the situation calculus Ann. Math. Artif. Intel. (IF 0.778) Pub Date : 2019-11-18 Giuseppe De Giacomo; Eugenia Ternovska; Ray Reiter
By their very design, many robot control programs are non-terminating. This paper describes a situation calculus approach to expressing and proving properties of non-terminating programs expressed in Golog, a high level logic programming language for modeling and implementing dynamical systems. Because in this approach actions and programs are represented in classical (second-order) logic, it is natural
-
Feature uncertainty bounds for explicit feature maps and large robust nonlinear SVM classifiers Ann. Math. Artif. Intel. (IF 0.778) Pub Date : 2019-11-15 Nicolas Couellan; Sophie Jan
We consider the binary classification problem when data are large and subject to unknown but bounded uncertainties. We address the problem by formulating the nonlinear support vector machine training problem with robust optimization. To do so, we analyze and propose two bounding schemes for uncertainties associated to random approximate features in low dimensional spaces. The proposed bound calculations
-
Data-driven Koopman operator approach for computational neuroscience Ann. Math. Artif. Intel. (IF 0.778) Pub Date : 2019-11-11 Natasza Marrouch, Joanna Slawinska, Dimitrios Giannakis, Heather L. Read
This article presents a novel, nonlinear, data-driven signal processing method, which can help neuroscience researchers visualize and understand complex dynamical patterns in both time and space. Specifically, we present applications of a Koopman operator approach for eigendecomposition of electrophysiological signals into orthogonal, coherent components and examine their associated spatiotemporal
-
Multi-valued logic in graph transformation theory and self-adaptive systems Ann. Math. Artif. Intel. (IF 0.778) Pub Date : 2019-11-02 Dmitry Maximov; Sergey Ryvkin
Graph transformation theory uses rules to perform a graph transformation. However, there is no a way to choose between such different transformations in the case where several of them are applicable. A way to get the choice is suggested here based on the comparing of the values of implications which correspond to different transformation variants. The relationship between the topos of bundles, and
-
Deep learning models for brain machine interfaces Ann. Math. Artif. Intel. (IF 0.778) Pub Date : 2019-10-02 Lachezar Bozhkov, Petia Georgieva
Deep Learning methods have been rising in popularity in the past few years, and are now used as a fundamental component in various application domains such as computer vision, natural language processing, bioinformatics. Supervised learning with Convolutional Neural Networks has become the state of the art approach in many image related works. However, despite the great success of deep learning methods
-
Lattice map spiking neural networks (LM-SNNs) for clustering and classifying image data Ann. Math. Artif. Intel. (IF 0.778) Pub Date : 2019-09-21 Hananel Hazan, Daniel J. Saunders, Darpan T. Sanghavi, Hava Siegelmann, Robert Kozma
Spiking neural networks (SNNs) with a lattice architecture are introduced in this work, combining several desirable properties of SNNs and self-organized maps (SOMs). Networks are trained with biologically motivated, unsupervised learning rules to obtain a self-organized grid of filters via cooperative and competitive excitatory-inhibitory interactions. Several inhibition strategies are developed and
-
Compilation of static and evolving conditional knowledge bases for computing induced nonmonotonic inference relations Ann. Math. Artif. Intel. (IF 0.778) Pub Date : 2019-08-30 Christoph Beierle; Steven Kutsch; Kai Sauerwald
Several different semantics have been proposed for conditional knowledge bases \(\mathcal {R}\) containing qualitative conditionals of the form “If A, then usually B”, leading to different nonmonotonic inference relations induced by \(\mathcal {R}\). For the notion of c-representations which are a subclass of all ranking functions accepting \(\mathcal {R}\), a skeptical inference relation, called c-inference
-
Statistical learning based on Markovian data maximal deviation inequalities and learning rates Ann. Math. Artif. Intel. (IF 0.778) Pub Date : 2019-08-29 Stephan Clémençon; Patrice Bertail; Gabriela Ciołek
In statistical learning theory, numerous works established non-asymptotic bounds assessing the generalization capacity of empirical risk minimizers under a large variety of complexity assumptions for the class of decision rules over which optimization is performed, by means of sharp control of uniform deviation of i.i.d. averages from their expectation, while fully ignoring the possible dependence
-
Analyzing cognitive processes from complex neuro-physiologically based data: some lessons Ann. Math. Artif. Intel. (IF 0.778) Pub Date : 2019-08-28 Alex Frid, Larry M. Manevitz
In the past few years, due to their ability to extract multivariate correlations, machine learning tools have become more and more important for discovery of information in very complex data sets. This has had specific application to various data sets related to human brain tasks. However, this is far from a simple and direct methodology. Some of the issues involve dealing with the extreme signal to
-
Dynamic search trajectory methods for global optimization Ann. Math. Artif. Intel. (IF 0.778) Pub Date : 2019-08-27 Stamatios-Aggelos N. Alexandropoulos; Panos M. Pardalos; Michael N. Vrahatis
A detailed review of the dynamic search trajectory methods for global optimization is given. In addition, a family of dynamic search trajectories methods that are created using numerical methods for solving autonomous ordinary differential equations is presented. Furthermore, a strategy for developing globally convergent methods that is applicable to the proposed family of methods is given and the
-
Targeting solutions in Bayesian multi-objective optimization: sequential and batch versions Ann. Math. Artif. Intel. (IF 0.778) Pub Date : 2019-08-20 David Gaudrie; Rodolphe Le Riche; Victor Picheny; Benoît Enaux; Vincent Herbert
Multi-objective optimization aims at finding trade-off solutions to conflicting objectives. These constitute the Pareto optimal set. In the context of expensive-to-evaluate functions, it is impossible and often non-informative to look for the entire set. As an end-user would typically prefer a certain part of the objective space, we modify the Bayesian multi-objective optimization algorithm which uses
-
Fundamental conditions on the sampling pattern for union of low-rank subspaces retrieval Ann. Math. Artif. Intel. (IF 0.778) Pub Date : 2019-08-16 Morteza Ashraphijuo; Xiaodong Wang
This paper is concerned with investigating the fundamental conditions on the locations of the sampled entries, i.e., sampling pattern, for finite completability of a matrix that represents the union of several subspaces with given ranks. In contrast with the existing analysis on Grassmannian manifold for the conventional matrix completion, we propose a geometric analysis on the manifold structure for
-
The price to pay for forgoing normalization in fair division of indivisible goods Ann. Math. Artif. Intel. (IF 0.778) Pub Date : 2019-08-16 Pascal Lange; Nhan-Tam Nguyen; Jörg Rothe
We study the complexity of fair division of indivisible goods and consider settings where agents can have nonzero utility for the empty bundle. This is a deviation from a common normalization assumption in the literature, and we show that this inconspicuous change can lead to an increase in complexity: In particular, while an allocation maximizing social welfare by the Nash product is known to be easy
-
Revising event calculus theories to recover from unexpected observations Ann. Math. Artif. Intel. (IF 0.778) Pub Date : 2019-08-09 Nikoleta Tsampanaki, Theodore Patkos, Giorgos Flouris, Dimitris Plexousakis
Recent extensions of the Event Calculus resulted in powerful formalisms, able to reason about a multitude of commonsense phenomena in causal domains, involving epistemic notions, functional fluents and probabilistic aspects, among others. Less attention has been paid to the problem of automatically revising (correcting) a Knowledge Base when an observation contradicts inferences made regarding the
-
Checking inference-proofness of attribute-disjoint and duplicate-preserving fragmentations Ann. Math. Artif. Intel. (IF 0.778) Pub Date : 2019-08-09 Joachim Biskup; Marcel Preuß
The transmission of own and partly confidential data to another agent comes along with the risk of enabling the receiver to infer information he is not entitled to learn. We consider a specific countermeasure against unwanted inferences about associations between data values whose combination of attributes are declared to be sensitive. This countermeasure fragments a relation instance into attribute-disjoint