Filters








14,473 Hits in 5.4 sec

Model-based Exploration of the Frontier of Behaviours for Deep Learning System Testing [article]

Vincenzo Riccio, Paolo Tonella
2020 arXiv   pre-print
With the increasing adoption of Deep Learning (DL) for critical tasks, such as autonomous driving, the evaluation of the quality of systems that rely on DL has become crucial.  ...  We developed DeepJanus, a search-based tool that generates frontier inputs for DL systems.  ...  Giacomelli for their contributions to the project.  ... 
arXiv:2007.02787v1 fatcat:42gvte5u5zffdoeeignsfdrxbu

Voronoi-Based Multi-Robot Autonomous Exploration in Unknown Environments via Deep Reinforcement Learning

Junyan Hu, Hanlin Niu, Joaquin Carrasco, Barry Lennox, Farshad Arvin
2020 IEEE Transactions on Vehicular Technology  
To deal with sudden obstacles in the unknown environment, an integrated deep reinforcement learning based collision avoidance algorithm is then proposed, which enables the control policy to learn from  ...  Autonomous exploration is an important application of multi-vehicle systems, where a team of networked robots are coordinated to explore an unknown environment collaboratively.  ...  In [14] , the traditional approach of frontier-based exploration and deep reinforcement learning were combined to allow a robot to autonomously explore unknown cluttered environments.  ... 
doi:10.1109/tvt.2020.3034800 fatcat:xhz5x7demngcvkkwsly5i7ef2u

Editorial: Application of Big Data, Deep Learning, Machine Learning, and Other Advanced Analytical Techniques in Environmental Economics and Policy

Tsun Se Cheong, Xunpeng (Roc) Shi, Yanfei Li, Yongping Sun
2022 Frontiers in Environmental Science  
To fill this gap, the International Society for Energy Transition Studies (ISETS) collaborated with Frontiers in an attempt to promote the application of big data, deep learning, machine learning, and  ...  The goal of this research topic is to re-examine important environmental economics and management issues by employing cutting-edge research methods based on big data, deep learning, and other machine learning  ...  point of view by revisiting the issues with the application of big data, deep learning, other machine learning techniques, as well as other Frontier techniques.  ... 
doi:10.3389/fenvs.2022.953659 fatcat:akrzzzcvabdk7fe4rrnxvgiyr4

Deep Neural Networks In Computational Neuroscience [article]

Tim Christian Kietzmann, Patrick McClure, Nikolaus Kriegeskorte
2017 bioRxiv   pre-print
At the heart of the field are its models, i.e. mathematical and computational descriptions of the system being studied, which map sensory stimuli to neural responses and/or neural to behavioural responses  ...  The goal of computational neuroscience is to find mechanistic explanations of how the nervous system processes information to give rise to cognitive function and behaviour.  ...  Yet, the overall success clearly illustrates the power of DNN models for computational neuroscience. How can deep neural networks be tested with brain and behavioural data?  ... 
doi:10.1101/133504 fatcat:6ulcyc22v5azjoz4nftprg2niq

Learning and Expertise in Mineral Exploration Decision-Making: An Ecological Dynamics Perspective

Rhys Samuel Davies, Marianne Julia Davies, David Groves, Keith Davids, Eric Brymer, Allan Trench, John Paul Sykes, Michael Dentith
2021 International Journal of Environmental Research and Public Health  
By implication of the Dynamics model, several areas are highlighted as being important for improving the quality of exploration.  ...  The Dynamics model is based on an Ecological Dynamics framework, combining Newell's Constraints model, Self Determination Theory, and including feedback loops to define an autopoietic system.  ...  Acknowledgments: Thanks are due to Doug Brewster, James Bell, and Rebecca Seal for their feedback, which greatly improved the quality of this paper.  ... 
doi:10.3390/ijerph18189752 pmid:34574692 fatcat:oyn2rzargnddvhrhucik3mgdpy

Editorial: Technological Frontiers in Dinosaur Science Mark a New Age of Opportunity for Early Career Researchers

Verónica Díez Díaz, Elena Cuesta, Daniel Vidal, Matteo Belvedere
2022 Frontiers in Earth Science  
We also would like to thank Ursula Raba, Kanzis Mattu and the Frontiers Team for their support and suggestions.  ...  ACKNOWLEDGMENTS We would like to thank all reviewers for their contributions, and all authors of the submitted manuscripts.  ...  These works set an important base for analyzing larger sets of images and samples, but also developing more complex deep learning algorithms.  ... 
doi:10.3389/feart.2022.973459 fatcat:a5recdf3abfavajyftqv34luq4

Educational Anomaly Analytics: Features, Methods, and Challenges

Teng Guo, Xiaomei Bai, Xue Tian, Selena Firmin, Feng Xia
2022 Frontiers in Big Data  
With the popularity of educational management systems and the rise of online education during the prevalence of COVID-19, a large amount of educational data is available online and offline, providing an  ...  This study aims to provide references for educational policymaking while promoting the development of educational anomaly analytics as a growing field.  ...  The other category of single-model type is the more recent and popular research based on deep learning models.  ... 
doi:10.3389/fdata.2021.811840 pmid:35098114 pmcid:PMC8795666 fatcat:2cejzd6kkvesbly6ytxfy5lb2e

An Evaluation of Speech-Based Recognition of Emotional and Physiological Markers of Stress

Alice Baird, Andreas Triantafyllopoulos, Sandra Zänkert, Sandra Ottl, Lukas Christ, Lukas Stappen, Julian Konzok, Sarah Sturmbauer, Eva-Maria Meßner, Brigitte M. Kudielka, Nicolas Rohleder, Harald Baumeister (+1 others)
2021 Frontiers in Computer Science  
We present cross-corpus and transfer learning results which explore the efficacy of the speech signal to predict three physiological markers of stress—sequentially measured saliva-based cortisol, continuous  ...  For the task of predicting cortisol levels from speech, deep learning improves on results obtained by conventional support vector regression—yielding a Spearman correlation coefficient (ρ) of 0.770 and  ...  be a valid deep learning architecture for modelling states thus raising ethical concerns which make the collection of of continuous stress, and motivates us to explore the use of this  ... 
doi:10.3389/fcomp.2021.750284 fatcat:2rdv6mngzrhhfcj3s5f53p55jy

A human-centric AI-driven framework for exploring large and complex datasets

Maria Francesca Costabile, Giuseppe Desolda, Giovanni Dimauro, Rosa Lanzilotti, Daniele Loiacono, Maristella Matera, Massimo Zancanaro
2022 International Working Conference on Advanced Visual Interfaces  
This position paper presents our ongoing research aiming to extend the HCAI framework for better supporting designers in creating AI-based systems.  ...  Human-Centered Artificial Intelligence (HCAI) is a new frontier of research at the intersection between HCI and AI.  ...  It implies strategies for different types of explanations as an alternative to the socalled "black-box" of deep learning systems (e.g., [20] ).  ... 
dblp:conf/avi/CostabileDDLLMZ22 fatcat:fh5yvwtblvbmrkjdhfebk5vmqu

Adding features of educational games for Teaching Physics

Karla Munoz, Julieta Noguez, Paul Mc Kevitt, Luis Neri, Victor Robledo-Rella, Tom Lunney
2009 2009 39th IEEE Frontiers in Education Conference  
For the second evaluation the results suggest that using the GVL resulted in higher learning gains than using VL.  ...  This work introduces the Olympia architecture, which is based on a previous architecture that combines VLs and intelligent tutoring systems (ITSs).  ...  Virtual laboratories (VLs) have the potential to provide significantly enhanced and more effective learning experiences. VLs can facilitate deep learning in model-based knowledge domains (e.g.  ... 
doi:10.1109/fie.2009.5350630 fatcat:ueyzn25gqnhrngou2rlgjcvtb4

Maximum Entropy Gain Exploration for Long Horizon Multi-goal Reinforcement Learning [article]

Silviu Pitis, Harris Chan, Stephen Zhao, Bradly Stadie, Jimmy Ba
2020 arXiv   pre-print
We propose to optimize this objective by having the agent pursue past achieved goals in sparsely explored areas of the goal space, which focuses exploration on the frontier of the achievable goal set.  ...  When the desired (test time) goal distribution is too distant to offer a useful learning signal, we argue that the agent should not pursue unobtainable goals.  ...  Zhang and the anonymous reviewers for their helpful comments.  ... 
arXiv:2007.02832v1 fatcat:i75hyfiownchvbfp5bdjzgavky

A Hybrid and Hierarchical Approach for Spatial Exploration in Dynamic Environments

Qi Zhang, Yukai Song, Peng Jiao, Yue Hu
2022 Electronics  
To this end, we present a three-tiered hierarchical and modular spatial exploration model that combines the intrinsic motivation integrated deep reinforcement learning (DRL) and rule-based real-time obstacle  ...  On the higher level, a DRL based global module learns to determine a distant but easily reachable target that maximizes the current exploration progress.  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/electronics11040574 fatcat:iisbw65a4jctvcs6jucl5pni5u

Exploring Neural Architecture Search Space via Deep Deterministic Sampling

Keith G. Mills, Mohammad Salameh, Di Niu, Fred X. Han, Seyed Saeed Changiz Rezaei, Hengshuai Yao, Wei Lu, Shuo Lian, Shangling Jui
2021 IEEE Access  
We propose Deep Deterministic Architecture Sampling (DDAS) based on deep deterministic policy gradient and the actor-critic framework, to selectively sample important architectures in the supernet for  ...  Contrary to this approach, DDAS employs a reinforcement learning-based agent and focuses on discovering a Pareto frontier containing many architectures over the course of a single experiment requiring  ...  In this paper, we use Reinforcement Learning to efficiently explore an architecture search space and propose Deep Deterministic Architecture Sampling (DDAS), a weight sharing NAS algorithm based on Deep  ... 
doi:10.1109/access.2021.3101975 fatcat:5h46jvt33bcp5fmqklfrzerzmy

DeepHyperion: Exploring the Feature Space of Deep Learning-Based Systems through Illumination Search [article]

Tahereh Zohdinasab, Vincenzo Riccio, Alessio Gambi, Paolo Tonella
2021 arXiv   pre-print
We developed DeepHyperion, a search-based tool for DL systems that illuminates, i.e., explores at large, the feature space, by providing developers with an interpretable feature map where automatically  ...  of the system.  ...  The driving simulator has been provided by BeamNG GmbH.  ... 
arXiv:2107.06997v1 fatcat:d3liwpva4jad5jyqowhzuxsm5i

A System Dynamics Approach to Increasing Ocean Literacy

Caroline Brennan, Matthew Ashley, Owen Molloy
2019 Frontiers in Marine Science  
systems-based OL learning.  ...  Through the identification and use of systems archetypes and general systems features such as feedback loops, we also tested for the acquisition of transferable skills and the ability to identify, apply  ...  This research was carried out as part of the project ResponSEAble (Project No. 652643), funded by the EU Horizon 2020 Framework Programme for Research and Innovation.  ... 
doi:10.3389/fmars.2019.00360 fatcat:76zcppqa5zeudgqdmjyft2frmi
« Previous Showing results 1 — 15 out of 14,473 results