15 results match your criteria Artificial Intelligence[Journal]

  • Page 1 of 1

Learning in the Machine: Random Backpropagation and the Deep Learning Channel.

Artif Intell 2018 Jul 3;260:1-35. Epub 2018 Apr 3.

Department of Mathematics, University of California, Irvine.

Random backpropagation (RBP) is a variant of the backpropagation algorithm for training neural networks, where the transpose of the forward matrices are replaced by fixed random matrices in the calculation of the weight updates. It is remarkable both because of its effectiveness, in spite of using random matrices to communicate error information, and because it completely removes the taxing requirement of maintaining symmetric weights in a physical neural system. To better understand random backpropagation, we first connect it to the notions of local learning and learning channels. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.artint.2018.03.003DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC5931406PMC
July 2018
2 Reads

Methods for solving reasoning problems in abstract argumentation - A survey.

Artif Intell 2015 Mar;220:28-63

Vienna University of Technology, Institute of Information Systems, Austria.

Within the last decade, abstract argumentation has emerged as a central field in Artificial Intelligence. Besides providing a core formalism for many advanced argumentation systems, abstract argumentation has also served to capture several non-monotonic logics and other AI related principles. Although the idea of abstract argumentation is appealingly simple, several reasoning problems in this formalism exhibit high computational complexity. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.artint.2014.11.008DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC4318991PMC

Genetic Programming and Frequent Itemset Mining to Identify Feature Selection Patterns of iEEG and fMRI Epilepsy Data.

Eng Appl Artif Intell 2015 Mar;39:198-214

Intelligent Control Systems Laboratory, Department of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, Georgia 30332.

Pattern classification for intracranial electroencephalogram (iEEG) and functional magnetic resonance imaging (fMRI) signals has furthered epilepsy research toward understanding the origin of epileptic seizures and localizing dysfunctional brain tissue for treatment. Prior research has demonstrated that implicitly selecting features with a genetic programming (GP) algorithm more effectively determined the proper features to discern biomarker and non-biomarker interictal iEEG and fMRI activity than conventional feature selection approaches. However for each the iEEG and fMRI modalities, it is still uncertain whether the stochastic properties of indirect feature selection with a GP yield (a) consistent results within a patient data set and (b) features that are specific or universal across multiple patient data sets. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.engappai.2014.12.008DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC4285716PMC

Modeling the Complex Dynamics and Changing Correlations of Epileptic Events.

Artif Intell 2014 Nov;216:55-75

Department of Bioengineering, University of Pennsylvania, Philadelphia, PA ; Department of Neurology, University of Pennsylvania, Philadelphia, PA.

Patients with epilepsy can manifest short, sub-clinical epileptic "bursts" in addition to full-blown clinical seizures. We believe the relationship between these two classes of events-something not previously studied quantitatively-could yield important insights into the nature and intrinsic dynamics of seizures. A goal of our work is to parse these complex epileptic events into distinct dynamic regimes. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.artint.2014.05.006DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC4180222PMC
November 2014
5 Reads

The Dropout Learning Algorithm.

Artif Intell 2014 May;210:78-122

Department of Computer Science University of California, Irvine Irvine, CA 92697-3435.

Dropout is a recently introduced algorithm for training neural network by randomly dropping units during training to prevent their co-adaptation. A mathematical analysis of some of the static and dynamic properties of dropout is provided using Bernoulli gating variables, general enough to accommodate dropout on units or connections, and with variable rates. The framework allows a complete analysis of the ensemble averaging properties of dropout in linear networks, which is useful to understand the non-linear case. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.artint.2014.02.004DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC3996711PMC
May 2014
6 Reads

Using Wikipedia to learn semantic feature representations of concrete concepts in neuroimaging experiments.

Artif Intell 2013 Jan 10;194:240-252. Epub 2012 Jul 10.

Psychology Department and Princeton Neuroscience Institute, Princeton University, Princeton, NJ 08540.

In this paper we show that a corpus of a few thousand Wikipedia articles about concrete or visualizable concepts can be used to produce a low-dimensional semantic feature representation of those concepts. The purpose of such a representation is to serve as a model of the mental context of a subject during functional magnetic resonance imaging (fMRI) experiments. A recent study [19] showed that it was possible to predict fMRI data acquired while subjects thought about a concrete concept, given a representation of those concepts in terms of semantic features obtained with human supervision. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.artint.2012.06.005DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC3519435PMC
January 2013
1 Read

The Local Geometry of Multiattribute Tradeoff Preferences.

Artif Intell 2011 May;175(7-8):1122-1152

Computer Science and ArtificialIntelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA 02139 USA

Existing representations for multiattribute ceteris paribus preference statements have provided useful treatments and clear semantics for qualitative comparisons, but have not provided similarly clear representations or semantics for comparisons involving quantitative tradeoffs. We use directional derivatives and other concepts from elementary differential geometry to interpret conditional multiattribute ceteris paribus preference comparisons that state bounds on quantitative tradeoff ratios. This semantics extends the familiar economic notion of marginal rate of substitution to multiple continuous or discrete attributes. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.artint.2010.11.014DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC3081600PMC
May 2011
2 Reads

Updating action domain descriptions.

Artif Intell 2010 Oct;174(15):1172-1221

Institute of Information Systems, Vienna University of Technology, Vienna, Austria.

Incorporating new information into a knowledge base is an important problem which has been widely investigated. In this paper, we study this problem in a formal framework for reasoning about actions and change. In this framework, action domains are described in an action language whose semantics is based on the notion of causality. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.artint.2010.07.004DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC2978003PMC
October 2010
1 Read

Join-Graph Propagation Algorithms.

J Artif Intell Res 2010 Jan;37:279-328

Microsoft Research 7 J J Thomson Avenue Cambridge CB3 0FB, UK

The paper investigates parameterized approximate message-passing schemes that are based on bounded inference and are inspired by Pearl's belief propagation algorithm (BP). We start with the bounded inference mini-clustering algorithm and then move to the iterative scheme called Iterative Join-Graph Propagation (IJGP), that combines both iteration and bounded inference. Algorithm IJGP belongs to the class of Generalized Belief Propagation algorithms, a framework that allowed connections with approximate algorithms from statistical physics and is shown empirically to surpass the performance of mini-clustering and belief propagation, as well as a number of other state-of-the-art algorithms on several classes of networks. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1613/jair.2842DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC2926991PMC
January 2010

A comparative runtime analysis of heuristic algorithms for satisfiability problems.

Artif Intell 2009 Feb;173(2):240-257

School of Computer Science and Engineering, South China University of Technology, Guangzhou 510640, China.

The satisfiability problem is a basic core NP-complete problem. In recent years, a lot of heuristic algorithms have been developed to solve this problem, and many experiments have evaluated and compared the performance of different heuristic algorithms. However, rigorous theoretical analysis and comparison are rare. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.artint.2008.11.002DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC2774825PMC
February 2009

Efficient Markov Network Structure Discovery Using Independence Tests.

J Artif Intell Res 2009 May;35(1):449-484

Departamento de Sistemas de Informaciόn, Universidad Tecnolόgica Nacional, Mendoza, Argentina.

We present two algorithms for learning the structure of a Markov network from data: GSMN* and GSIMN. Both algorithms use statistical independence tests to infer the structure by successively constraining the set of structures consistent with the results of these tests. Until very recently, algorithms for structure learning were based on maximum likelihood estimation, which has been proved to be NP-hard for Markov networks due to the difficulty of estimating the parameters of the network, needed for the computation of the data likelihood. Read More

View Article

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC3400681PMC
May 2009
7 Reads
1 Citation
1.260 Impact Factor

A Fuzzy Reasoning Design for Fault Detection and Diagnosis of a Computer-Controlled System.

Eng Appl Artif Intell 2008 Mar;21(2):157-170

Department of Mechanical Engineering, Chung Yuan Christian University, 200, Chung Pei Rd., Chung Li, Taiwan 32023, R.O.C.

A Fuzzy Reasoning and Verification Petri Nets (FRVPNs) model is established for an error detection and diagnosis mechanism (EDDM) applied to a complex fault-tolerant PC-controlled system. The inference accuracy can be improved through the hierarchical design of a two-level fuzzy rule decision tree (FRDT) and a Petri nets (PNs) technique to transform the fuzzy rule into the FRVPNs model. Several simulation examples of the assumed failure events were carried out by using the FRVPNs and the Mamdani fuzzy method with MATLAB tools. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.engappai.2007.04.007DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC2598772PMC

Model-Free Visualization of Suspicious Lesions in Breast MRI Based on Supervised and Unsupervised Learning.

Eng Appl Artif Intell 2008 Mar;21(2):129-140

Department of Electrical and Computer Engineering, Florida State University, Tallahassee, Florida 32310-6046.

Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) has become an important tool in breast cancer diagnosis, but evaluation of multitemporal 3D image data holds new challenges for human observers. To aid the image analysis process, we apply supervised and unsupervised pattern recognition techniques for computing enhanced visualizations of suspicious lesions in breast MRI data. These techniques represent an important component of future sophisticated computer-aided diagnosis (CAD) systems and support the visual exploration of spatial and temporal features of DCE-MRI data stemming from patients with confirmed lesion diagnosis. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.engappai.2007.04.005DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC2597847PMC
March 2008
6 Reads

Genetic Programming of Conventional Features to Detect Seizure Precursors.

Eng Appl Artif Intell 2007 Dec;20(8):1070-1085

, Ph.D. Candidate, Georgia Institute of Technology, Intelligent Control Systems Laboratory, Biomedical Engineering Research Group, 813 Ferst Drive, N.W., Atlanta, GA 30332.

This paper presents an application of genetic programming (GP) to optimally select and fuse conventional features (C-features) for the detection of epileptic waveforms within intracranial electroencephalogram (IEEG) recordings that precede seizures, known as seizure-precursors. Evidence suggests that seizure-precursors may localize regions important to seizure generation on the IEEG and epilepsy treatment. However, current methods to detect epileptic precursors lack a sound approach to automatically select and combine C-features that best distinguish epileptic events from background, relying on visual review predominantly. Read More

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.engappai.2007.02.002DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC2390867PMC
December 2007
1 Read

Online Planning Algorithms for POMDPs.

J Artif Intell Res 2008 Jul;32(2):663-704

School of Computer Science, McGill University, Montreal, Canada, H3A 2A7.

Partially Observable Markov Decision Processes (POMDPs) provide a rich framework for sequential decision-making under uncertainty in stochastic domains. However, solving a POMDP is often intractable except for small problems due to their complexity. Here, we focus on online approaches that alleviate the computational complexity by computing good local policies at each decision step during the execution. Read More

View Article

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC2748358PMC
July 2008
5 Reads
  • Page 1 of 1