Filters








3,782 Hits in 5.3 sec

DRiLLS: Deep Reinforcement Learning for Logic Synthesis [article]

Abdelrahman Hosny, Soheil Hashemi, Mohamed Shalan, Sherief Reda
2019 arXiv   pre-print
Logic synthesis requires extensive tuning of the synthesis optimization flow where the quality of results (QoR) depends on the sequence of optimizations used.  ...  In this work, we propose a novel reinforcement learning-based methodology that navigates the optimization space without human intervention.  ...  . • We introduce DRiLLS (Deep Reinforcemnet Learningbased Logic Synthesis), a novel framework based on reinforcement learning developed for generating logic synthesis optimization flows.  ... 
arXiv:1911.04021v2 fatcat:m5yvlqzkwrfo5przeacvs6taaa

Drilling Parameters Analysis on In-Situ Al/B4C/Mica Hybrid Composite and an Integrated Optimization Approach Using Fuzzy Model and Non-Dominated Sorting Genetic Algorithm

Palanikumar Kayaroganam, Velavan Krishnan, Elango Natarajan, Senthilkumar Natarajan, Kanesan Muthusamy
2021 Metals  
Reinforcement of mica is the key performance indicator in reducing the thrust force and torque in drilling of the selected material, irrespective of other parameter settings.  ...  for obtaining the lowest thrust force of 339.68 N and torque of 68.98 N.m.  ...  Synthesis and Characterization of Silicon Nitride Reinforced Al–Mg–Zn Alloy Composites. Met. Mater. Int. 2021, 27, 3058–3069. [CrossRef] 4. Rajmohan, T.; Palanikumar, K.  ... 
doi:10.3390/met11122060 fatcat:3ganlv4mm5gknlb6rcltdeousq

Expedition 335 summary [chapter]

2012 Proceedings of the Integrated Ocean Drilling Program  
desirable for drilling a moderately deep hole into the oceanic crust (~1.5-2 km).  ...  the attainment of deep targets by scientific ocean drilling Establishing the ideal location for drilling is only part of the challenge of successfully drilling moderately deep holes (2-3 km) to recover  ...  The high-velocity area extending southeast from Site 1256 may reflect the extent of the ponded lava sequence drilled at the top of Site 1256. OBH = ocean bottom hydrophone. B.  ... 
doi:10.2204/iodp.proc.335.101.2012 fatcat:6dzmiydxnfecpeps76d2q3zwpq

Drilling their Own Graves: How the European Oil and Gas Supermajors Avoid Sustainability Tensions Through Mythmaking

George Ferns, Kenneth Amaeshi, Aliette Lambert
2017 Journal of Business Ethics  
the comforts of past familiarities, (2) fantasy, or escaping the harsh reality that fossil fuels and climate change are indeed irreconcilable, and (3) projecting, or shifting blame to external actors for  ...  This is often highlighted by the common narrative of successfully drilling in ultra-deep water.  ...  an ''instrumental logic'' (Gao and Bansal 2013) .  ... 
doi:10.1007/s10551-017-3733-x fatcat:2gzze7hsingh7kqb3s4tzgse6a

BOiLS: Bayesian Optimisation for Logic Synthesis [article]

Antoine Grosnit, Cedric Malherbe, Rasul Tutunov, Xingchen Wan, Jun Wang, Haitham Bou Ammar
2021 arXiv   pre-print
Inspired by the successes of machine learning, researchers adapted deep learning and reinforcement learning to logic synthesis applications.  ...  Optimising the quality-of-results (QoR) of circuits during logic synthesis is a formidable challenge necessitating the exploration of exponentially sized search spaces.  ...  reinforcement learning. handful of ML-inspired approaches based on deep neural networks and reinforcement learning to obtain optimal structural transformations.  ... 
arXiv:2111.06178v1 fatcat:kr4s2n7kand6pdblwafibtk2ri

DemoGrasp: Few-Shot Learning for Robotic Grasping with Human Demonstration [article]

Pengyuan Wang, Fabian Manhardt, Luca Minciullo, Lorenzo Garattoni, Sven Meie, Nassir Navab, Benjamin Busam
2021 arXiv   pre-print
To this end, most approaches either compute the full 6D pose for the object of interest or learn to predict a set of grasping points.  ...  Finally, we transfer the a-priori knowledge from the relative pose between object and human hand with the estimate of the current object pose in the scene into necessary grasping instructions for the robot  ...  Lepetit, “Learning descriptors for object recogni- opt: Scalable deep reinforcement learning for vision-based robotic tion and 3d pose estimation,” in CVPR, 2015.  ... 
arXiv:2112.02849v1 fatcat:kpwrzj6r4re6rodinzlrer25si

Task-Aware Verifiable RNN-Based Policies for Partially Observable Markov Decision Processes

Steven Carr, Nils Jansen, Ufuk Topcu
2021 The Journal of Artificial Intelligence Research  
However, it is hard to verify whether the POMDP driven by such RNN-based policies satisfies safety constraints, for instance, given by temporal logic specifications.  ...  The method synthesizes policies that satisfy temporal logic specifications for POMDPs with up to millions of states, which are three orders of magnitude larger than comparable approaches.  ...  Related Work RNNs pose suitable policy representations for deep reinforcement learning problems that need to account for sequences of data.  ... 
doi:10.1613/jair.1.12963 fatcat:usbrnbs6dvarrbnj2x4bmmmrwa

Too Big to Fail? Active Few-Shot Learning Guided Logic Synthesis [article]

Animesh Basak Chowdhury, Benjamin Tan, Ryan Carey, Tushit Jain, Ramesh Karri, Siddharth Garg
2022 arXiv   pre-print
Generating sub-optimal synthesis transformation sequences ("synthesis recipe") is an important problem in logic synthesis. Manually crafted synthesis recipes have poor quality.  ...  State-of-the art machine learning (ML) works to generate synthesis recipes do not scale to large netlists as the models need to be trained from scratch, for which training data is collected using time  ...  decision process (MDP) that is solved using reinforcement learning (RL).  ... 
arXiv:2204.02368v1 fatcat:5f54zlkzxrfwhg6b7g4z2kxvwu

Paradigm Shift: Engineering Artificial Intelligence And Management Strategies Fusion

A. H. Harb, AKA Abd Alhameed Abd Alhameed Alsayyid
2017 Zenodo  
Qualitative methodology was used to assess components such as fuzzy logic that can produce answers determined by multiple factors that can be integrated into a determinant solution.  ...  AI systems can account for errors in human judgment through computational processes that supersede the capabilities of human intelligence alone.  ...  Shell, ExxonMobil, Suncor, and Imperial Oil use fuzzy logic in deep water drilling, reservoir analysis, and petrophysics.  ... 
doi:10.5281/zenodo.848050 fatcat:y2diaj6isfam3iffvhgxyxzhqy

PARADIGM SHIFT: ENGINEERING ARTIFICIAL INTELLIGENCE AND MANAGEMENT STRATEGIES FUSION

A. H. Harb, AbdAlhameedAbdAlhameed Alsayyid
2016 International journal of research - granthaalayah  
Qualitative methodology was used to assess components such as fuzzy logic that can produce answers determined by multiple factors that can be integrated into a determinant solution.  ...  AI systems can account for errors in human judgment through computational processes that supersede the capabilities of human intelligence alone.  ...  Shell, ExxonMobil, Suncor, and Imperial Oil use fuzzy logic in deep water drilling, reservoir analysis, and petrophysics.  ... 
doi:10.29121/granthaalayah.v4.i2.2016.2807 fatcat:t42npbcvprchdkzcboowrg5vru

2021 Index IEEE Robotics and Automation Letters Vol. 6

2021 IEEE Robotics and Automation Letters  
The Author Index contains the primary entry for each item, listed under the first author's name.  ...  ., +, LRA Oct. 2021 6977-6984 Modular Deep Reinforcement Learning for Continuous Motion Planning With Temporal Logic.  ...  ., +, LRA Oct. 2021 6313-6320 Modular Deep Reinforcement Learning for Continuous Motion Planning With Temporal Logic.  ... 
doi:10.1109/lra.2021.3119726 fatcat:lsnerdofvveqhlv7xx7gati2xu

Understanding social collaboration between actors and technology in an automated and digitised deep mining environment

M.-A. Sanda, J. Johansson, B. Johansson, L. Abrahamsson
2011 Ergonomics  
Acknowledgements The authors thank the management of Renstro¨m mines, Boliden, for their cooperation and also acknowledge the support of the Centre of Advanced Mining and Metallurgy (CAMM), Lulea˚University  ...  Figure 5 . 5 Miner engaged in physical activity during production drilling using rock-drilling machine (with 2 boomers) in the digitised deep mine.  ...  By implication, there is a need for the creation of new learning that includes generic theoretical knowledge for creating flexibility in the production systems of underground mines on the basis of the  ... 
doi:10.1080/00140139.2011.606922 pmid:21973002 fatcat:m35u6httfvashkam2hd7g3rpwm

Automation of the Work Environment and the Human-Technology Collaboration Challenge: A Critical Reflection

Mohammed Aminu Sanda
2017 International Robotics & Automation Journal  
The aim is to argue for the development of the requisite knowledge in the application of digitized/automated systems that allows for open collaboration between the technological functions and the workforce  ...  It is posited analytic strategies for examining mediated action between the human and an automated system can be made possible by isolating its elements.  ...  Figure 1 : 1 Figure 1: Operator engaged in highly mechanized deep mining activity of production drilling.  ... 
doi:10.15406/iratj.2017.03.00074 fatcat:blx3qeghsnbcfc6ficycfkhmiu

Combining Task and Motion Planning: Challenges and Guidelines

Masoumeh Mansouri, Federico Pecora, Peter Schüller
2021 Frontiers in Robotics and AI  
By doing so, this article aims to provide a guideline for designing combined TAMP solutions that are adequate and effective in the target scenario.  ...  All authors listed have made a substantial, direct, and intellectual contribution to the work and approved it for publication.  ...  Q3, on the other hand, has to do with how to obtain these models, and is particularly in focus today thanks to the rise in popularity of machine learning techniques, in particular deep (reinforcement)  ... 
doi:10.3389/frobt.2021.637888 pmid:34095239 pmcid:PMC8170405 fatcat:4dmykcbhezbktfjzafv7t7wjfa

Generating Personalized Data Narrations from EDA Notebooks

Alexandre Chanson, Faten El Outa, Nicolas Labroche, Patrick Marcel, Verónika Peralta, Willeme Verdeaux, Lucile Jacquemart
2022 International Workshop on Data Warehousing and OLAP  
The approach consists of extracting features from notebooks to learn what interesting messages they expose.  ...  In this short paper, we present our preliminary results for generating personalized data narrations by extracting messages from a collection of Exploratory Data Analysis (EDA) notebooks over a given dataset  ...  They shaped EDA into a control problem, and devised a novel Deep Reinforcement Learning architecture to effectively optimize the notebook generation. Personnaz et al.  ... 
dblp:conf/dolap/ChansonOLMPVJ22 fatcat:3jeepeqxcbe7dnelaisw3ucexy
« Previous Showing results 1 — 15 out of 3,782 results