关注
Johannes Günther
Johannes Günther
在 ualberta.ca 的电子邮件经过验证
标题
引用次数
引用次数
年份
Intelligent laser welding through representation, prediction, and control learning: An architecture with deep neural networks and reinforcement learning
J Günther, PM Pilarski, G Helfrich, H Shen, K Diepold
Mechatronics 34, 1-11, 2016
1892016
First steps towards an intelligent laser welding architecture using deep neural networks and reinforcement learning
J Günther, PM Pilarski, G Helfrich, H Shen, K Diepold
Procedia Technology 15, 474-483, 2014
1112014
Detecting the onset of machine failure using anomaly detection methods
M Riazi, O Zaiane, T Takeuchi, A Maltais, J Günther, M Lipsett
Big Data Analytics and Knowledge Discovery: 21st International Conference …, 2019
222019
Interpretable PID parameter tuning for control engineering using general dynamic neural networks: An extensive comparison
J Günther, E Reichensdörfer, PM Pilarski, K Diepold
PLOS ONE 15(12), 2020
18*2020
Machine intelligence for adaptable closed loop and open loop production engineering systems
J Günther
Technische Universität München, 2018
122018
Predictions, Surprise, and Predictions of Surprise in General Value Function Architectures
J Günther, A Kearney, MR Dawson, C Sherstan, PM Pilarski
AAAI 2018 Fall Symposium on Reasoning and Learning in Real-World Systems for …, 2018
122018
Gamma-nets: Generalizing value estimation over timescale
C Sherstan, S Dohare, J MacGlashan, J Günther, PM Pilarski
Proceedings of the AAAI Conference on Artificial Intelligence 34 (04), 5717-5725, 2020
112020
Examining the use of temporal-difference incremental delta-bar-delta for real-world predictive knowledge architectures
J Günther, NM Ady, A Kearney, MR Dawson, PM Pilarski
Frontiers in Robotics and AI 7, 34, 2020
112020
Recurrent neural networks for PID auto-tuning
E Reichensdörfer, J Günther, K Diepold
102017
Affordance as general value function: A computational model
D Graves, J Günther, J Luo
Adaptive Behavior, 21, 2020
62020
Meta-learning for Predictive Knowledge Architectures: A Case Study Using TIDBD on a Sensor-rich Robotic Arm
J Günther, A Kearney, NM Ady, MR Dawson, PM Pilarski
Proceedings of the 18th International Conference on Autonomous Agents and …, 2019
52019
Five Properties of Specific Curiosity You Didn't Know Curious Machines Should Have
NM Ady, R Shariff, J Günther, PM Pilarski
arXiv preprint arXiv:2212.00187, 2022
32022
Composite Recurrent Convolutional Neural Networks Offer a Position-Aware Prosthesis Control Alternative While Balancing Predictive Accuracy with Training Burden
HE Williams, J Günther, JS Hebert, PM Pilarski, AW Shehata
2022 International Conference on Rehabilitation Robotics (ICORR), 1-6, 2022
32022
Neural Networks for fast sensor data processing in Laser Welding
J Günther, H Shen, K Diepold
Jahreskolloquium-Bildverarbeitung in der Automation, 2014
32014
Finding useful predictions by meta-gradient descent to improve decision-making
A Kearney, A Koop, J Günther, PM Pilarski
arXiv preprint arXiv:2111.11212, 2021
22021
Automated optimization of dynamic neural network structure using genetic algorithms
C Sandner, J Günther, K Diepold
22017
Multi-Robot Warehouse Optimization: Leveraging Machine Learning for Improved Performance.
M Cairo, B Eldaphonse, P Mousavi, S Sahir, S Jubair, ME Taylor, ...
AAMAS, 3047-3049, 2023
12023
What Should I Know? Using Meta-Gradient Descent for Predictive Feature Discovery in a Single Stream of Experience
A Kearney, A Koop, J Günther, PM Pilarski
Conference on Lifelong Learning Agents, 604-616, 2022
12022
Prototyping three key properties of specific curiosity in computational reinforcement learning
NM Ady, R Shariff, J Günther, PM Pilarski
arXiv preprint arXiv:2205.10407, 2022
12022
Prediction, Knowledge, and Explainability: Examining the Use of General Value Functions in Machine Knowledge
A Kearney, J Günther, PM Pilarski
Frontiers in Artificial Intelligence 5, 826724, 2022
12022
系统目前无法执行此操作,请稍后再试。
文章 1–20