A review of online learning in supervised neural networks
Learning in neural networks can broadly be divided into two categories, viz., off-line (or
batch) learning and online (or incremental) learning. In this paper, a review of a variety of …
batch) learning and online (or incremental) learning. In this paper, a review of a variety of …
Reinforcement learning for portfolio management
A Filos - arXiv preprint arXiv:1909.09571, 2019 - arxiv.org
In this thesis, we develop a comprehensive account of the expressive power, modelling
efficiency, and performance advantages of so-called trading agents (ie, Deep Soft Recurrent …
efficiency, and performance advantages of so-called trading agents (ie, Deep Soft Recurrent …
Balance control of a biped robot on a rotating platform based on efficient reinforcement learning
A Xi, TW Mudiyanselage, D Tao… - IEEE/CAA Journal of …, 2019 - ieeexplore.ieee.org
In this work, we combined the model based reinforcement learning (MBRL) and model free
reinforcement learning (MFRL) to stabilize a biped robot (NAO robot) on a rotating platform …
reinforcement learning (MFRL) to stabilize a biped robot (NAO robot) on a rotating platform …
Posture self-stabilizer of a biped robot based on training platform and reinforcement learning
W Wu, L Gao - Robotics and Autonomous Systems, 2017 - Elsevier
In order to solve the problem of stability control for biped robots, the concept of stability
training is proposed by using a training platform to exert random disturbance with amplitude …
training is proposed by using a training platform to exert random disturbance with amplitude …
Learning with Chemical versus Electrical Synapses Does it Make a Difference?
Bio-inspired neural networks have the potential to advance our understanding of neural
computation and improve the state-of-the-art of AI systems. Bio-electrical synapses directly …
computation and improve the state-of-the-art of AI systems. Bio-electrical synapses directly …
A machine learning-based motion training approach applied to multilegged and bipedal robots
To promptly gain an understanding of disasters as they occur and to draft plans for search
and rescue operations, various types of robots are used. Robots not only increase rescue …
and rescue operations, various types of robots are used. Robots not only increase rescue …
Two-legged robot motion control with recurrent neural networks
B Çatalbaş, Ö Morgül - Journal of Intelligent & Robotic Systems, 2022 - Springer
Legged locomotion is a desirable ability for robotic systems thanks to its agile mobility and
wide range of motions that it provides. In this paper, the use of neural network-based …
wide range of motions that it provides. In this paper, the use of neural network-based …
A UKF-based predictable SVR learning controller for biped walking
An unscented Kalman filter (UKF)-based predictable support vector regression (SVR)
learning controller is proposed to improve the flexibility of biped walking robots. After …
learning controller is proposed to improve the flexibility of biped walking robots. After …
Ultrasonic sensor triangulation for accurate 3D relative positioning of humanoid robot feet
L Chassagne, O Bruneau, A Bialek… - IEEE Sensors …, 2014 - ieeexplore.ieee.org
A simple measurement system with a set of six ultrasonic piezoelectric transducers is
presented for direct 3D positioning of humanoid robot limbs. A configuration with three …
presented for direct 3D positioning of humanoid robot limbs. A configuration with three …
Control and system identification of legged locomotion with recurrent neural networks
B Çatalbaş - 2022 - search.proquest.com
In recent years, robotic systems have gained massive popularity in the industry, military, and
daily use for various purposes, thanks to advancements in artificial intelligence and control …
daily use for various purposes, thanks to advancements in artificial intelligence and control …