Online optimal learning algorithm for Stackelberg games with partially unknown dynamics and constrained inputs

2021 ◽  
Author(s):  
Xiaohong Cui ◽  
Binrui Wang ◽  
Lina Wang ◽  
Jiayu Chen
Keyword(s):  
Learning Algorithm ◽  
Stackelberg Games ◽  
Optimal Learning ◽  
Constrained Inputs

Convergence analysis of distributed multi-penalty regularized pairwise learning

2019 ◽  
Vol 18 (01) ◽  
pp. 109-127
Author(s):  
Ting Hu ◽  
Jun Fan ◽  
Dao-Hong Xiang
Keyword(s):  
Single Machine ◽  
Learning Algorithm ◽  
Target Function ◽  
Distributed Learning ◽  
Divide And Conquer ◽  
Learning Performance ◽  
Manifold Regularization ◽  
Optimal Learning ◽  
Pairwise Learning ◽  
Optimal Learning Rate

In this paper, we establish the error analysis for distributed pairwise learning with multi-penalty regularization, based on a divide-and-conquer strategy. We demonstrate with [Formula: see text]-error bound that the learning performance of this distributed learning scheme is as good as that of a single machine which could process the whole data. With semi-supervised data, we can relax the restriction of the number of local machines and enlarge the range of the target function to guarantee the optimal learning rate. As a concrete example, we show that the work in this paper can apply to the distributed pairwise learning algorithm with manifold regularization.

CHARACTERIZING ONE-LAYER ASSOCIATIVE NEURAL NETWORKS WITH OPTIMAL NOISE-REDUCTION ABILITY

1992 ◽  
Vol 06 (05) ◽  
pp. 1009-1025 ◽  
Author(s):  
TAO WANG ◽  
XIAOLIANG XING ◽  
XINHUA ZHUANG
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Cost Function ◽  
Noise Reduction ◽  
Gradient Descent ◽  
Storage Capacity ◽  
Learning Algorithm ◽  
Optimal Learning ◽  
The Neural Network ◽  
The Cost

In this paper, we describe an optimal learning algorithm for designing one-layer neural networks by means of global minimization. Taking the properties of a well-defined neural network into account, we derive a cost function to measure the goodness of the network quantitatively. The connection weights are determined by the gradient descent rule to minimize the cost function. The optimal learning algorithm is formed as either the unconstraint-based or the constraint-based minimization problem. It ensures the realization of each desired associative mapping with the best noise reduction ability in the sense of optimization. We also investigate the storage capacity of the neural network, the degree of noise reduction for a desired associative mapping, and the convergence of the learning algorithm in an analytic way. Finally, a large number of computer experimental results are presented.

scholarly journals Fused Convolutional Neural Network for Facial Expression Recognition

2019 ◽  
Vol 8 (12S2) ◽  
pp. 528-532
Keyword(s):  
Neural Network ◽  
Facial Expression ◽  
Convolutional Neural Network ◽  
Facial Expression Recognition ◽  
Cross Validation ◽  
Learning Algorithm ◽  
Expression Recognition ◽  
Optimal Learning ◽  
Group Of Seven ◽  
Fold Cross Validation

This study aims to find the optimal learning algorithm parameter, model and connection, initialization weight and normalization method using fused Convolutional Neural Network (CNN) for facial expression recognition. The best model and parameters are identified using a ten-fold cross validation method. By determining these ideal elements, a superior accuracy can potentially be achieved. CNN was utilized to a group of seven emotions from various facial expressions, namely, happy, sad, angry, surprise, disgust, fear and neutral. The four layer CNN configuration was prepared with the JAFFE dataset, and yielded an overall accuracy of 83.72%. The outcome demonstrates that the fused CNN with the mentioned aims can generate higher accuracy with a smaller network compared to related models.

scholarly journals Optimal Learning and Self-Awareness Versus PDI

Algorithms ◽  
2020 ◽  
Vol 13 (1) ◽  
pp. 23 ◽  
Author(s):  
Brendon Smeresky ◽  
Alex Rizzo ◽  
Timothy Sands
Keyword(s):  
Feedback Control ◽  
Learning Algorithm ◽  
Feedforward Control ◽  
Body Motion ◽  
Self Awareness ◽  
Optimal Learning ◽  
Simulink Simulation ◽  
Specific Term ◽  
Integral Controller ◽  
Proportional Integral Derivative Control

This manuscript will explore and analyze the effects of different paradigms for the control of rigid body motion mechanics. The experimental setup will include deterministic artificial intelligence composed of optimal self-awareness statements together with a novel, optimal learning algorithm, and these will be re-parameterized as ideal nonlinear feedforward and feedback evaluated within a Simulink simulation. Comparison is made to a custom proportional, derivative, integral controller (modified versions of classical proportional-integral-derivative control) implemented as a feedback control with a specific term to account for the nonlinear coupled motion. Consistent proportional, derivative, and integral gains were used throughout the duration of the experiments. The simulation results will show that akin feedforward control, deterministic self-awareness statements lack an error correction mechanism, relying on learning (which stands in place of feedback control), and the proposed combination of optimal self-awareness statements and a newly demonstrated analytically optimal learning yielded the highest accuracy with the lowest execution time. This highlights the potential effectiveness of a learning control system.

Sign in / Sign up

Export Citation Format

Share Document