Results 251 to 260 of about 175,748 (328)

Predicting Performance of Hall Effect Ion Source Using Machine Learning

open access: yesAdvanced Intelligent Systems, Volume 7, Issue 3, March 2025.
This study introduces HallNN, a machine learning tool for predicting Hall effect ion source performance using a neural network ensemble trained on data generated from numerical simulations. HallNN provides faster and more accurate predictions than numerical methods and traditional scaling laws, making it valuable for designing and optimizing Hall ...
Jaehong Park   +8 more
wiley   +1 more source

Uncontrolled Learning: Codesign of Neuromorphic Hardware Topology for Neuromorphic Algorithms

open access: yesAdvanced Intelligent Systems, EarlyView.
Codesign is used to implement a neuroscience‐inspired machine learning algorithm in all neuromorphic hardware. In this implementation, the hidden memristors cannot be directly accessed, limiting control of the network during training. By leveraging theoretical tools, including memristor circuits dynamics and a closed form expression for the network ...
Frank Barrows   +3 more
wiley   +1 more source

UltRAP‐Net: Reverse Approximation of Tissue Properties in Ultrasound Imaging

open access: yesAdvanced Intelligent Systems, EarlyView.
This study proposes a reverse approximation neural network (UltRAP‐Net) to extract underlying physics‐aware properties using multiple images with distinct appearances obtained at the same location of tissues. Through this robust approximation, the study advances the use of ultrasound images by opening potentials for various applications such as physics‐
Yingqi Li   +4 more
wiley   +1 more source

Model‐Free Deep Reinforcement Learning with Multiple Line‐of‐Sight Guidance Laws for Autonomous Underwater Vehicles Full‐Attitude and Velocity Control

open access: yesAdvanced Intelligent Systems, EarlyView.
In this study, a deep reinforcement learning framework with multi‐line‐of‐sight guidance is proposed. An augmented‐twin delayed deep deterministic policy gradient algorithm adapts to attitude changes efficiently, reducing computational costs. Simulations show 30.8% faster training and mitigates rudder/exergy issues, validated by an X‐rudder autonomous ...
Chengren Yuan   +5 more
wiley   +1 more source

Home - About - Disclaimer - Privacy