Filters








61,588 Hits in 4.5 sec

Verifiable and Compositional Reinforcement Learning Systems [article]

Cyrus Neary, Christos Verginis, Murat Cubuktepe, Ufuk Topcu
2022 arXiv   pre-print
We propose a framework for verifiable and compositional reinforcement learning (RL) in which a collection of RL subsystems, each of which learns to accomplish a separate subtask, are composed to achieve  ...  This in turn allows for the independent training and testing of the subsystems; if they each learn a policy satisfying the appropriate subtask specification, then their composition is guaranteed to satisfy  ...  Acknowledgements This work was supported in part by ONR N00014-20-1-2115, ARO W911NF-20-1-0140, and NSF 1652113.  ... 
arXiv:2106.05864v3 fatcat:gbres3mpqrfxjctmmle4c744d4

Safe Reinforcement Learning via Formal Methods: Toward Safe Control Through Proof and Learning

Nathan Fulton, André Platzer
2018 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
by reinforcement learning.  ...  This is especially true in Cyber-Physical Systems because high-fidelity physical models of systems are expensive to develop and often intractable to verify.  ...  Our approach is compositional with other approaches to safe learning.  ... 
doi:10.1609/aaai.v32i1.12107 fatcat:ihbimfppzbakbna25vrmo6rcxu

Durability Assessment of PVA Fiber-Reinforced Cementitious Composite Containing Nano-SiO2 Using Adaptive Neuro-Fuzzy Inference System

Ting-Yu Liu, Peng Zhang, Qing-Fu Li, Shao-Wei Hu, Yi-Feng Ling
2020 Crystals  
In this study, the durability of polyvinyl alcohol fiber-reinforced cementitious composite containing nano-SiO2 was evaluated using the adaptive neuro-fuzzy inference system (ANFIS).  ...  Compared with the traditional expert evaluation method, the durability evaluation system based on the ANFIS learned expert experience, stored the expert experience in fuzzy rules, and eliminated the subjectivity  ...  This study applied the ANFIS inference system to assess the durability of PVA fiber-reinforced cementitious composites containing nano-SiO 2 .  ... 
doi:10.3390/cryst10050347 fatcat:ryr3n3jhlzheflnkqomb7ki73a

Performance Evaluation of CFRP Reinforced Concrete Members Utilizing Fuzzy Technique

Lan Chung, Moo-Won Hur, Taewon Park
2018 International Journal of Concrete Structures and Materials  
Aging and structural deterioration under severe environments are major causes of damage in reinforced concrete (RC) structures, such as buildings and bridges.  ...  Recently, FRP composite materials have emerged as a cost-effective alternative to conventional materials for repairing, strengthening, and retrofitting deteriorating/deficient concrete structures, by externally  ...  Availability of Data and Materials Not applicable. Funding Dankook University.  ... 
doi:10.1186/s40069-018-0313-0 fatcat:uvdiqgzdgzd5nlisitgt4duo5i

Cumulative Learning Through Intrinsic Reinforcements [chapter]

Vieri G. Santucci, Gianluca Baldassarre, Marco Mirolli
2014 Evolution, Complexity and Artificial Life  
We compare different versions of the system varying the composition of the learning signal and we show that the only system able to reach high performance in the task is the one that implements the learning  ...  In particular, we suggest that the particular composition of such a signal, determined by both extrinsic and intrinsic reinforcements, would be suitable to improve the implementation of cumulative learning  ...  We varied the composition of the learning signal and we verified that only the one implementing our hypothesis was able to guide the simulated robot in the achievement of the task.  ... 
doi:10.1007/978-3-642-37577-4_7 fatcat:6cwp4qht7jaolgwr4klrdlwdfm

Hierarchical principles of embodied reinforcement learning: A review [article]

Manfred Eppe, Christian Gumbsch, Matthias Kerzel, Phuong D.H. Nguyen, Martin V. Butz, Stefan Wermter
2020 arXiv   pre-print
Among the most promising computational approaches to provide comparable learning-based problem-solving abilities for artificial agents and robots is hierarchical reinforcement learning.  ...  We then relate these insights with contemporary hierarchical reinforcement learning methods, and identify the key machine intelligence approaches that realise these mechanisms.  ...  prerequisites of computational hierarchical reinforcement learning systems (cf.  ... 
arXiv:2012.10147v1 fatcat:dfkdehyz2rggtimmlcmtvycpxe

Towards Verified Artificial Intelligence [article]

Sanjit A. Seshia, Dorsa Sadigh, S. Shankar Sastry
2020 arXiv   pre-print
This paper considers Verified AI from a formal methods perspective. We describe five challenges for achieving Verified AI, and five corresponding principles for addressing these challenges.  ...  Verified artificial intelligence (AI) is the goal of designing AI-based systems that that have strong, ideally provable, assurances of correctness with respect to mathematically-specified requirements.  ...  and Assured Autonomy programs, by Toyota under the iCyPhy center, and by Berkeley Deep Drive.  ... 
arXiv:1606.08514v4 fatcat:ozoldsdnzjghddhwz5xju6zqvu

The use of deep learning algorithm and digital media art in all-media intelligent electronic music system

Yingming Zheng, Zhihan Lv
2020 PLoS ONE  
In the development of digital media art, to explore the preliminary application of deep learning method in intelligent electronic music system, and promote the integration of deep learning method and digital  ...  The accuracy rate of task test corresponding to intelligent system in different scenarios is above 95%, which is better than other conventional algorithms in task test; the self-reinforcement network algorithm  ...  The system integrates the deep reinforcement learning algorithm and the deep learning algorithm composition into it.  ... 
doi:10.1371/journal.pone.0240492 pmid:33075083 fatcat:wld2hu7qarbh3e7utrndrjqgoy

2020 Index IEEE Transactions on Services Computing Vol. 13

2021 IEEE Transactions on Services Computing  
-Oct. 2020 843-856 MMDP: A Mobile-IoT Based Multi-Modal Reinforcement Learning Service Framework.  ...  ., +, TSC July-Aug. 2020 653-662 MMDP: A Mobile-IoT Based Multi-Modal Reinforcement Learning Service Framework.  ... 
doi:10.1109/tsc.2021.3055723 fatcat:eumbihmezvehxdfbmlp6ufzkwe

Flexible learning experiences available

2010 British Dental Journal  
, composite and porcelain.  ...  The course will cover areas including comparison between different fi bre systems currently available in the market, durability and performance of the fi bre reinforced restorations, different indications  ... 
doi:10.1038/sj.bdj.2010.325 fatcat:ufirderkozc5hdxgxsvgbwaxfq

Damage Analysis and Prediction in Glass Fiber Reinforced Polyester Composite Using Acoustic Emission and Machine Learning

2022 Journal of Robotics and Automation Research  
This study assesses the progression of damage occurring on glass fiber reinforced polyester composite specimens using two approaches of machine learning, namely, Supervised and Unsupervised learning.  ...  A methodology for damage detection and characterization of composite is presented. The result shows that machine learning can predict damages in composite materials.  ...  and damage propagation in glass fiber reinforced polyester composite material under cyclic fatigue test.  ... 
doi:10.33140/jrar.03.02.01 fatcat:txsuk6htinbpnbanvvt63ntgie

Learning from Human Decision-Making Behaviors — An Application to RoboCup Software Agents [chapter]

Ruck Thawonmas, Junichiro Hirayama, Fumiaki Takeda
2002 Lecture Notes in Computer Science  
As a result, online learning techniques have been used in order to make software agents automatically learn to decide proper condition-action rules from their experiences.  ...  However, for complicated problems this approach requires a large amount of time and might not guarantee the optimality of rules.  ...  Experiments of Learning from Human Decision-Making Behaviors We extensively conducted experiments in order to verify whether it is possible to learn the decision-making behaviors of the human player who  ... 
doi:10.1007/3-540-48035-8_14 fatcat:pqlhr7mljzhxvlvndikbees55q

Practical training experience

2010 British Dental Journal  
, composite and porcelain.  ...  The course will cover areas including comparison between different fi bre systems currently available in the market, durability and performance of the fi bre reinforced restorations, different indications  ... 
doi:10.1038/sj.bdj.2010.329 fatcat:rvkvusycwzbb7nj4b7yapsoh4m

Formulation of the Effect of Different Alloying Elements on the Tensile Strength of the in situ Al-Mg2Si Composites

Halil Kurt, Murat Oduncuoglu
2015 Metals  
The proposed model shows good agreement with test results and can be used to find the ultimate tensile strength of Al-Mg2Si composites.  ...  In addition, it is observed that magnesium and copper have a stronger effect on the ultimate tensile strength of Al-Mg2Si composites comparison to other alloying elements.  ...  Composites the produced by in situ technique exhibit the better particle wetting, even distribution of the reinforcing phase and thermodynamically stable system [4, 5] .  ... 
doi:10.3390/met5010371 fatcat:vb5eipzmovg2dafj33fhleztd4

Classification of Textile Polymer Composites: Recent Trends and Challenges

Nesrine Amor, Muhammad Tayyab Noman, Michal Petru
2021 Polymers  
Therefore, classification of textiles products and fibre reinforced polymer composites is a challenging task.  ...  The inclusion of natural polymeric fibres as reinforcement in carbon fibre reinforced composites manufacturing delineates an economic way, enhances their surface, structural and mechanical properties by  ...  (GFRP), basalt fiber reinforced polymer composites (BFRP) and aramid fiber reinforced polymer composites (AFRP).  ... 
doi:10.3390/polym13162592 pmid:34451132 pmcid:PMC8398028 fatcat:5hnoal6zprfk5iwljrctggyn6y
« Previous Showing results 1 — 15 out of 61,588 results