28,840 Hits in 2.6 sec

Page 4395 of Mathematical Reviews Vol. , Issue 2002F [page]

2002 Mathematical Reviews  
{For the entire collection see MR 2002c:68008. } 2002:68072 68Q32 Meyer, Léa (D-FRBG-IG; Freiburg) Aspects of complexity of probabilistic learning under monotonicity constraints.  ...  In Section 1, we show that 7% is necessary and sufficient to compensate the additional power of probabilistic learning ma- chines in the case of conservative (monotonic) probabilistic learn- ing with p  ... 

Page 6635 of Mathematical Reviews Vol. , Issue 2001I [page]

2001 Mathematical Reviews  
{For the entire collection see MR 2001i:68007. } 20011:68076 68Q32 Meyer, Léa (D-FRBG-IG; Freiburg) Aspects of complexity of conservative probabilistic learning.  ...  Hence, conservative probabilistic learning with p = 1/2 is too ‘rich’ to be measured in terms of Turing complexity.”  ... 

Aspects of complexity of probabilistic learning under monotonicity constraints

Léa Meyer
2001 Theoretical Computer Science  
In Section 1, we show that K is necessary and su cient to compensate the additional power of probabilistic learning machines in the case of conservative (monotonic) probabilistic learning with p ¿ 1=2  ...  In contrast, the oracle K is not su cient for compensating the power of conservative and strong-monotonic probabilistic learning with probability p = 1=2, and monotonic probabilistic learning with p =  ...  In [8, 15] , the intrinsic complexity of learning problems was investigated. Brandt [5] studied qualitative aspects of complexity in inductive inference.  ... 
doi:10.1016/s0304-3975(00)00273-5 fatcat:3c6dtr45ifdjblg7yj232nomoq

Electric genes

1999 Nature Biotechnology  
species. 303 One aspect of genome interpretation is to discover, label, and connect all of the encoded parts and to catalog the degree to which parts are lost, modified, or conserved from one type of  ...  Machine learning techniques are particularly suited for facilitating these types of investigations.  ...  Bioinformatics: The Machine Learning Approach Pierre Baldi and Søren Brunak 1998 MIT Press, 351 pages, $40 hardcover  ... 
doi:10.1038/7061 fatcat:g6ohhxhrhfawndtsj5zsr5kqmm

Machine learning methods in finance

Irina Karachun, Lyubov Vinnichek, Andrey Tuskov, S. Roshchupkin
2021 SHS Web of Conferences  
The finance industry has adopted machine learning to varying degrees of sophistication. Some key examples demonstrate the nature of machine learning and how it is used in practice.  ...  This article focuses on supervised learning and reinforcement learning. These areas overlap most with econometrics, predictive modelling, and optimal control in finance.  ...  The level of their complexity and the use of machine learning systems is constantly growing.  ... 
doi:10.1051/shsconf/202111005012 fatcat:fll3dsvghnfddab2mtkj7nuz4q

Probabilistic Prediction from Planning Perspective: Problem Formulation, Representation Simplification and Evaluation Metric

Wei Zhan, Arnaud La de Fortelle, Yi-Ting Chen, Ching-Yao Chan, Masayoshi Tomizuka
2018 2018 IEEE Intelligent Vehicles Symposium (IV)  
Typically, the performance of probabilistic predictions was only evaluated by learning metrics for approximation to the motion distribution in the dataset.  ...  To address such concerns, we provide a systematic and unified framework for the analysis of three under-explored aspects of probabilistic prediction: problem formulation, representation simplification  ...  Neither the learning metrics nor distance-based ones can take into account these aspects.  ... 
doi:10.1109/ivs.2018.8500697 dblp:conf/ivs/ZhanFCCT18 fatcat:6372huyanvbirjsa2cmztkeydy

Probabilistically Robust Learning: Balancing Average- and Worst-case Performance [article]

Alexander Robey and Luiz F. O. Chamon and George J. Pappas and Hamed Hassani
2022 arXiv   pre-print
From a theoretical point of view, this framework overcomes the trade-offs between the performance and the sample-complexity of worst-case and average-case learning.  ...  Many of the successes of machine learning are based on minimizing an averaged loss function.  ...  We also show that while the sample complexity of adversarial learning can be arbitrarily high, the sample complexity of our probabilistically robust learning is the same as ERM. • Tractable algorithm.  ... 
arXiv:2202.01136v2 fatcat:cktuabhtardtnjp5mgshediw74

Automated Decision-Making and Environmental Impact Assessments: Decisions, Data Analysis and Predictions

Zoe Nay, Anna Huggins, Felicity Deane
2021 Law, Technology and Humans  
This article critically examines the opportunities and challenges that automated decision-making (ADM) poses for environmental impact assessments (EIAs) as a crucial aspect of environmental law.  ...  This latter type of ADM can augment decision-making processes without displacing the critical role of human discretion in weighing the complex environmental, social and economic considerations inherent  ...  Using ADM to make EIA decisions would require historical data of previous EIA decisions to be included as an input in order for the probabilistic system to learn what impacts are taken into account,  ... 
doi:10.5204/lthj.1846 fatcat:gkage53oibewbllyjsz7ko6wzm

Bayesian Annotation Networks for Complex Sequence Analysis

Henning Christiansen, Christian Theil Have, Ole Torp Lassen, Matthieu Petit, Marc Herbstritt
2011 International Conference on Logic Programming  
Our methodology can be implemented using the probabilistic-logic PRISM system, developed by Sato et al, in a way that allows for practical applications. ACM Subject Classification I.2.6 Learning  ...  Probabilistic models that associate annotations to sequential data are widely used in computational biology and a range of other applications.  ...  Measured in sequence length, the complexity of approximate prediction with the entire BAN coincides with the complexity for the most complex sub-model. 5 Training the network In order to obtain the probabilistic  ... 
doi:10.4230/lipics.iclp.2011.220 dblp:conf/iclp/ChristiansenHLP11 fatcat:cu3zfgruzrgqziygz5mlidfxae

Equipping robot control programs with first-order probabilistic reasoning capabilities

Dominik Jain, Lorenz Mosenlechner, Michael Beetz
2009 2009 IEEE International Conference on Robotics and Automation  
An autonomous robot system that is to act in a real-world environment is faced with the problem of having to deal with a high degree of both complexity as well as uncertainty.  ...  relational learning, which possesses the required level of expressiveness and generality.  ...  Since we as system designers or knowledge engineers cannot generally quantify the degree of uncertainty that applies to a particular aspect of the domain in question, the probabilistic parameters of our  ... 
doi:10.1109/robot.2009.5152676 dblp:conf/icra/JainMB09 fatcat:p22wlt7nivhkfgha56oy7hp4jq

Probabilistic accuracy bounds for perforated programs

Martin Rinard
2011 Proceedings of the 20th ACM SIGPLAN workshop on Partial evaluation and program manipulation - PERM '11  
Hank Hoffman, Sasa Misailovic, Stelios Sidiroglou, and Anant Agarwal all contributed to various aspects of the loop perforation project.  ...  Machine learning algorithms usually work with probabilistic models that capture some, but not all, aspects of phenomena that are difficult (if not impossible) to model with complete accuracy [2] .  ...  Probabilistic Reasoning How can one justify the application of loop perforation?  ... 
doi:10.1145/1929501.1929517 dblp:conf/pepm/Rinard11 fatcat:2xmthesgwrbrdnn6l7wz5ys4o4

Permissive Supervisor Synthesis for Markov Decision Processes through Learning [article]

Bo Wu, Xiaobin Zhang, Hai Lin
2017 arXiv   pre-print
With the recent advance in assume-guarantee reasoning verification for probabilistic systems, building the composed system can be avoided to alleviate the state space explosion and our framework learn  ...  This paper considers the permissive supervisor synthesis for probabilistic systems modeled as Markov Decision Processes (MDP).  ...  So this complexity analysis is rather conservative. We then prove that the result of supervisor synthesis is correct by design and our framework always terminates. Theorem 2.  ... 
arXiv:1703.07351v1 fatcat:gh6nvxhlzffqlkxr4pbbwd5xqe

Probabilistic boosting-tree: learning discriminative models for classification, recognition, and clustering

Zhuowen Tu
2005 Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1  
In this paper, a new learning framework-probabilistic boosting-tree (PBT), is proposed for learning two-class and multi-class discriminative models.  ...  In the learning stage, the probabilistic boosting-tree automatically constructs a tree in which each node combines a number of weak classifiers (evidence, knowledge) into a strong classifier (a conditional  ...  Acknowledgment I thank Xiang (Sean) Zhou, Xiangrong Chen, Tao Zhao, Adrian Barbu, Piotr Dollar, and Xiaodong Fan for helpful comments and assistance in getting some of the training datasets.  ... 
doi:10.1109/iccv.2005.194 dblp:conf/iccv/Tu05a fatcat:7qy4k7vuerexzbc5avoq4ohz7a

Developing treatments for cognitive deficits in schizophrenia: The challenge of translation

JW Young, MA Geyer, Judith Pratt
2014 Journal of Psychopharmacology  
This approach would increase the likelihood that the neural substrates underlying relevant behaviors will be conserved across species.  ...  Schizophrenia is a life-long debilitating mental disorder affecting tens of millions of people worldwide.  ...  Numerous tasks exist to measure different aspects of reinforcement learning and are primarily probabilistic in nature.  ... 
doi:10.1177/0269881114555252 pmid:25516372 pmcid:PMC4670265 fatcat:hhmdvmvkwfabbkbkciraqyr5wi

SpliceIT: A hybrid method for splice signal identification based on probabilistic and biological inference

Andigoni Malousi, Ioanna Chouvarda, Vassilis Koutkias, Sofia Kouidou, Nicos Maglaveras
2010 Journal of Biomedical Informatics  
The splicing mechanism involves complex interactions among positional and compositional features of different lengths.  ...  , specificity tradeoff without compromising space complexity and in a time-effective way.  ...  The time-complexity for PFS is linear with the number of the incorporated features, while for PFA the algorithmic complexity is of the order of PCA [34] .  ... 
doi:10.1016/j.jbi.2009.09.004 pmid:19800027 fatcat:t22a6ektrfg7ndgjpubix44zfy
« Previous Showing results 1 — 15 out of 28,840 results