Model-Agnostic Meta-Learning (MAML) and its variants have shown remarkable performance in scenarios characterized by a scarcity of labeled data during the training phase of machine learning models. Despite these succe...
Model-Agnostic Meta-Learning (MAML) and its variants have shown remarkable performance in scenarios characterized by a scarcity of labeled data during the training phase of machine learning models. Despite these successes, MAML-based approaches encounter significant challenges when there is a substantial discrepancy in the distribution of training and testing tasks, resulting in inefficient learning and limited generalization across domains. Inspired by classical proportional-integral-derivative (PID) control theory, this study introduces a Layer-Adaptive PID (LA-PID) Optimizer, a MAML-based optimizer that employs efficient parameter optimization methods to dynamically adjust task-specific PID control gains at each layer of the network, conducting a first-principles analysis of optimal convergence conditions. A series of experiments conducted on four standard benchmark datasets demonstrate the efficacy of the LA-PID optimizer, indicating that LA-PID achieves state-of-the-art performance in few-shot classification and cross-domain tasks, accomplishing these objectives with fewer training steps. Code is available on https://***/yuguopin/LA-PID. Copyright 2024 by the author(s)
In this paper, a control-oriented Linear Parameter Varying (LPV) model of an energy efficient electric vehicle is proposed, designed for model-based control to minimize energy consumption. The control inputs of the mo...
详细信息
ISBN:
(数字)9798350379365
ISBN:
(纸本)9798350379372
In this paper, a control-oriented Linear Parameter Varying (LPV) model of an energy efficient electric vehicle is proposed, designed for model-based control to minimize energy consumption. The control inputs of the model include the torque reference and the actual cornering radius. The LPV model assesses the impact of cornering on driving resistances and, consequently, on energy consumption, which represents a novel approach. Due to the driving characteristics and the model nonlinear dynamics of the vehicle, a velocity-linearization based method was applied to obtain the parameter-dependent form. The obtained LPV model was then validated by using logged driving data, showing a root mean square error (RMSE) of 0.4682 m/s compared to the measured speed profile, thereby confirming the model's accuracy. The proposed LPV model can be utilized to develop energy-efficient driving strategies, making it highly relevant for the design and operation of energy-efficient vehicles.
The article proposes the architecture of an embedded information-control system (ICS) for the precision landing of an unmanned aerial vehicle (UAV). The created ICS makes it possible to ensure the landing of a UAV equ...
详细信息
Reinforcement learning methods have demonstrated advanced capabilities in training neural network controllers for specific tasks. In the industrial domain, where model discrepancies and state disturbances occur, robot...
详细信息
In order to study the motion accuracy of the RVABI (Rear Variable Area Bypass Injector) under various error-related influences, the motion analysis model of the RVABI with clearance error is established based on the s...
详细信息
The non-stationary heat exchange (heating) process is a typical kind of technological operation in metallurgy. The most common technological units for such operation are continuous heating furnaces, in which steel bil...
详细信息
The current issue includes 2 perspectives, 2 letters, and 12 regular papers. These perspectives explore critical issues within the field of IVs and pontential research directions based on the evolution of foundation m...
详细信息
The current issue includes 2 perspectives, 2 letters, and 12 regular papers. These perspectives explore critical issues within the field of IVs and pontential research directions based on the evolution of foundation models.
The paper presents a model-based controller design technique for a thermal process in silicon wafer manufacturing. The underlying model is obtained by dynamic mode decomposition which is a purely data-driven approach....
详细信息
The paper presents a model-based controller design technique for a thermal process in silicon wafer manufacturing. The underlying model is obtained by dynamic mode decomposition which is a purely data-driven approach. The control scheme consists of a state feedback controller in combination with a disturbance observer, which allows robust tracking of feasible reference temperature profiles. The approach is validated using a laboratory setup.
暂无评论