112 Hits in 6.2 sec

A Primer on Maximum Causal Entropy Inverse Reinforcement Learning [article]

Adam Gleave, Sam Toyer
2022 arXiv   pre-print
Inverse Reinforcement Learning (IRL) algorithms infer a reward function that explains demonstrations provided by an expert acting in the environment.  ...  Maximum Causal Entropy (MCE) IRL is currently the most popular formulation of IRL, with numerous extensions.  ...  Acknowledgements We would like to thank Alyssa Li Dayan, Michael Dennis, Yawen Duan, Daniel Filan, Erik Jenner, Niklas Lauffer and Cody Wild for feedback on earlier versions of this manuscript.  ... 
arXiv:2203.11409v1 fatcat:gpcbomxf3nbbzkhkiw6uzqm36u

How hidden are hidden processes? A primer on crypticity and entropy convergence

John R. Mahoney, Christopher J. Ellison, Ryan G. James, James P. Crutchfield
2011 Chaos  
This is done by recasting previous results on the convergence of block entropy and block-state entropy in a geometric setting, one that is more intuitive and that leads to a number of new results.  ...  For example, we connect crypticity to how an observer synchronizes to a process. We show that the block-causal-state entropy is a convex function of block length.  ...  Over time, a system "realizes" which paths are undesirable and quits them. Consider an individual learning to navigate a new city.  ... 
doi:10.1063/1.3637502 pmid:21974675 fatcat:bxquwvxq6zfxtijl5wfjo5zqny

Stochastic Thermodynamics of Learning

Sebastian Goldt, Udo Seifert
2017 Physical Review Letters  
Here, we use stochastic thermodynamics to analyse the learning of a classification rule by a neural network.  ...  We show that the information acquired by the network is bounded by the thermodynamic cost of learning and introduce a learning efficiency η<1.  ...  However, we can show that I G (w n : T n ) is a lower bound on I(w n : T n ) using the maximum entropy principle.  ... 
doi:10.1103/physrevlett.118.010601 pmid:28106416 fatcat:bppyz42akbhjnlbpzbcrzcccom

Corticobasal ganglia projecting neurons are required for juvenile vocal learning but not for adult vocal plasticity in songbirds

Miguel Sánchez-Valpuesta, Yumeno Suzuki, Yukino Shibata, Noriyuki Toji, Yu Ji, Nasiba Afrin, Chinweike Norman Asogwa, Ippei Kojima, Daisuke Mizuguchi, Satoshi Kojima, Kazuo Okanoya, Haruo Okado (+2 others)
2019 Proceedings of the National Academy of Sciences of the United States of America  
The learning of such sequential vocalizations depends on the neural function of the motor cortex and basal ganglia.  ...  Birdsong, like human speech, consists of a sequence of temporally precise movements acquired through vocal learning.  ...  region implicated in reinforcement learning (61, 62) .  ... 
doi:10.1073/pnas.1913575116 pmid:31636217 pmcid:PMC6842584 fatcat:zefuteiczfcwldbbl335x4l7iq

Unit commitment considering multiple charging and discharging scenarios of plug-in electric vehicles

Zhile Yang, Kang Li, Qun Niu, Aoife Foley
2015 2015 International Joint Conference on Neural Networks (IJCNN)  
Strategies on Tiled Large High-Resolution Displays using Inverse Reinforcement Learning [#15571] Redwan Abdo A.  ...  on-policy neural reinforcement learning of working memory tasks [#15520] Davide Zambrano, Roelfsema Pieter and Bohte Sander 3:40PM Online Reinforcement Learning by Bayesian Inference [#15242] Zhongpu  ... 
doi:10.1109/ijcnn.2015.7280446 dblp:conf/ijcnn/YangLNF15 fatcat:6xlakikcfzfyhhm2spooe2j7ra

Causal inference methods for combining randomized trials and observational studies: a review [article]

Bénédicte Colnet, Imke Mayer, Guanhua Chen, Awa Dieng, Ruohong Li, Gaël Varoquaux, Jean-Philippe Vert, Julie Josse, Shu Yang
2022 arXiv   pre-print
In this paper, we review the growing literature on methods for causal inference on combined RCTs and observational studies, striving for the best of both worlds.  ...  Finally, we compare the main methods using a simulation study and real world data to analyze the effect of tranexamic acid on the mortality rate in major trauma patients.  ...  Acknowledgement This work is initiated by a SAMSI working group jointly led by JJ and SY in the 2020 causal inference program.  ... 
arXiv:2011.08047v3 fatcat:o2ddcual4vcuvajcs2rjkdpbjq

A Review of Kernel Methods for Feature Extraction in Nonlinear Process Monitoring

Karl Ezra Pilario, Mahmood Shafiee, Yi Cao, Liyun Lao, Shuang-Hua Yang
2019 Processes  
Kernel methods are a class of learning machines for the fast recognition of nonlinear patterns in any data set.  ...  First, we describe the reasons for using kernel methods and contextualize them among other machine learning tools.  ...  The Bayesian network is an architecture for causality analysis, where the concepts of Granger causality and transfer entropy are used to define if one variable is caused by another based on their time  ... 
doi:10.3390/pr8010024 fatcat:7qnidseekjgj5epeceaezzggrm

Modern applications of machine learning in quantum sciences [article]

Anna Dawid, Julian Arnold, Borja Requena, Alexander Gresch, Marcin Płodzień, Kaelan Donatella, Kim Nicoli, Paolo Stornati, Rouven Koch, Miriam Büttner, Robert Okuła, Gorka Muñoz-Gil (+17 others)
2022 arXiv   pre-print
In these Lecture Notes, we provide a comprehensive introduction to the most recent advances in the application of machine learning methods in quantum sciences.  ...  We cover the use of deep learning and kernel methods in supervised, unsupervised, and reinforcement learning algorithms for phase classification, representation of many-body quantum states, quantum feedback  ...  Reinforcement learning. In contrast to the two previous types of learning, in reinforcement learning (RL), we typically do not have a data set available at all.  ... 
arXiv:2204.04198v1 fatcat:rae77aetd5hahnovchru6kjbcy

A theory of benchmarking

John P. Moriarty
2011 Benchmarking : An International Journal  
Originality: This research focuses on the causal linkages between benchmarking and organisational sustainability.  ...  of a thesis submitted in fulfilment of the requirements for the Degree of Doctor of Philosophy A Theory of Benchmarking By J. P.  ...  Thus benchmarking is a learning tool. learning from errors) are cited as techniques that abet organisational learning.  ... 
doi:10.1108/14635771111147650 fatcat:aep7le47crcavlszyufswjgcnm

A comprehensive survey on machine learning for networking: evolution, applications and research opportunities

Raouf Boutaba, Mohammad A. Salahuddin, Noura Limam, Sara Ayoubi, Nashid Shahriar, Felipe Estrada-Solano, Oscar M. Caicedo
2018 Journal of Internet Services and Applications  
In this way, readers will benefit from a comprehensive discussion on the different learning paradigms and ML techniques applied to fundamental problems in networking, including traffic prediction, routing  ...  There are various surveys on ML for specific areas in networking or for specific network technologies.  ...  Reinforcement learning for intrusion detection (RL) MARL [407] is a Multi-Agent Reinforcement Learning system for the detection of DoS and DDoS attacks.  ... 
doi:10.1186/s13174-018-0087-2 fatcat:jvwpewceevev3n4keoswqlcacu

Quantum computing enhanced machine learning for physico-chemical applications [article]

Manas Sajjan, Junxu Li, Raja Selvarajan, Shree Hari Sureshbabu, Sumit Suresh Kale, Rishabh Gupta, Sabre Kais
2021 arXiv   pre-print
We shall not only present a brief overview of the well-known techniques but also highlight their learning strategies using statistical physical insight.  ...  Machine learning (ML) has emerged into formidable force for identifying hidden but pertinent patterns within a given data set with the objective of subsequent generation of automated predictive behavior  ...  Another quantum state preparation method was presented in 225 based on reinforcement learning which is a machine learning training architecture framework that finds an optimal solution to a problem based  ... 
arXiv:2111.00851v1 fatcat:i2caiglszvbufbyfmf3cwkcduu

Integrating Audio Signal Processing and Deep Learning Algorithms for Gait Pattern Classification in Brazilian Gaited Horses

Anderson Antonio Carvalho Alves, Lucas Tassoni Andrietta, Rafael Zinni Lopes, Fernando Oliveira Bussiman, Fabyano Fonseca e Silva, Roberto Carvalheiro, Luiz Fernando Brito, Júlio César de Carvalho Balieiro, Lucia Galvão Albuquerque, Ricardo Vieira Ventura
2021 Frontiers in Animal Science  
Machine learning (random forest, RF; support vector machine, SVM) and deep learning (multilayer perceptron neural networks, MLP; convolution neural networks, CNN) algorithms were used to classify the gait  ...  This study focused on assessing the usefulness of using audio signal processing in the gaited horse industry.  ...  CONCLUSIONS This study provides a primer on the suitability of applying audio signal processing technology in the gaited horse industry.  ... 
doi:10.3389/fanim.2021.681557 fatcat:prnp6rpxdzclhdfehizqxvdwmq

The Information in Emotion Communication [article]

Alison Duncan Kerr, Kevin Scharp
2020 arXiv   pre-print
The quantitative theory of emotion information presented here is based on Shannon's mathematical theory of information in communication systems.  ...  One important application of the information theory of emotion communication is that it permits the development of emotion security systems for social networks to guard against the widespread emotion manipulation  ...  There is no textbook on Bayesian Theory of Mind (BToM), but Reinforcement Learning: An Introduction by Andrew Barto and Richard S.  ... 
arXiv:2002.08470v1 fatcat:57wauv3s7nfcdb52bamge3jbsm

A scalable sparse Cholesky based approach for learning high-dimensional covariance matrices in ordered data

Kshitij Khare, Sang-Yun Oh, Syed Rahman, Bala Rajaratnam
2019 Machine Learning  
the maximum length of a gap is a min{ , } O a σ σ steps.  ...  Gain j Entropy Entropy j ϒ = ϒ − ϒ (8.40) e aim of using this definition is to maximize the gain, dividing by overall entropy due to split argument y by value j.  ...  By using learning based on a Bayesian network based on statistical dependencies, one can answer a wide range of queries, such as whether there is dependence between expression levels of a gene and the  ... 
doi:10.1007/s10994-019-05810-5 fatcat:nulmjvxvwjgojfoe2ywv3pjrpu

A Survey of Systemic Risk Analytics

Dimitrios Bisias, Mark Flood, Andrew W. Lo, Stavros Valavanis
2012 Annual Review of Financial Economics  
The Office of Financial Research (OFR) Working Paper Series allows staff and their co-authors to disseminate preliminary research findings in a format intended to generate discussion and critical comments  ...  OFR Working Papers may be quoted without additional permission. We provide a survey of 31 quantitative measures of systemic risk in the economics and finance literature, chosen to  ...  There remains here a large residual category of other measures, denoted by the tag o , as any such categorization is necessarily approximate and incomplete.  ... 
doi:10.1146/annurev-financial-110311-101754 fatcat:x5ahuebz5jhlxdgfkb2xgp3p3u
« Previous Showing results 1 — 15 out of 112 results