Fast Task Adaptation Based on the Combination of Model-Based and Gradient-Based Meta Learning

2020 ◽  
pp. 1-10
Author(s):  
Zhixiong Xu ◽  
Xiliang Chen ◽  
Lei Cao
Keyword(s):  
Model Based ◽  
Meta Learning ◽  
Gradient Based ◽  
Task Adaptation

Hypervolemia Screening for Dialysis Patient Healthcare Using Meta Learning Model-Based Intelligent Scaler

Smart Science ◽  
2018 ◽  
Vol 7 (1) ◽  
pp. 16-27
Author(s):  
Wei-Ling Chen ◽  
Hsiang-Yueh Lai ◽  
Pi-Yun Chen ◽  
Chung-Dann Kan ◽  
Chia-Hung Lin
Keyword(s):  
Dialysis Patient ◽  
Learning Model ◽  
Model Based ◽  
Meta Learning

scholarly journals GPU acceleration of a model-based iterative method for Digital Breast Tomosynthesis

2020 ◽  
Vol 10 (1) ◽  
Author(s):  
R. Cavicchioli ◽  
J. Cheng Hu ◽  
E. Loli Piccolomini ◽  
E. Morotti ◽  
L. Zanni
Keyword(s):  
Graphics Processing Unit ◽  
Digital Breast Tomosynthesis ◽  
Projection Algorithm ◽  
Processing Unit ◽  
Data Set ◽  
Breast Tomosynthesis ◽  
Model Based ◽  
Computational Performance ◽  
Gradient Based ◽  
Time Required

AbstractDigital Breast Tomosynthesis (DBT) is a modern 3D Computed Tomography X-ray technique for the early detection of breast tumors, which is receiving growing interest in the medical and scientific community. Since DBT performs incomplete sampling of data, the image reconstruction approaches based on iterative methods are preferable to the classical analytic techniques, such as the Filtered Back Projection algorithm, providing fewer artifacts. In this work, we consider a Model-Based Iterative Reconstruction (MBIR) method well suited to describe the DBT data acquisition process and to include prior information on the reconstructed image. We propose a gradient-based solver named Scaled Gradient Projection (SGP) for the solution of the constrained optimization problem arising in the considered MBIR method. Even if the SGP algorithm exhibits fast convergence, the time required on a serial computer for the reconstruction of a real DBT data set is too long for the clinical needs. In this paper we propose a parallel SGP version designed to perform the most expensive computations of each iteration on Graphics Processing Unit (GPU). We apply the proposed parallel approach on three different GPU boards, with computational performance comparable with that of the boards usually installed in commercial DBT systems. The numerical results show that the proposed GPU-based MBIR method provides accurate reconstructions in a time suitable for clinical trials.

scholarly journals Continuous self-adaptive optimization to learn multi-task multi-agent

2021 ◽  
Author(s):  
Wenqian Liang ◽  
Ji Wang ◽  
Weidong Bao ◽  
Xiaomin Zhu ◽  
Qingyong Wang ◽  
...  
Keyword(s):  
Real World ◽  
Learning Algorithm ◽  
Superior Performance ◽  
Adaptive Optimization ◽  
Single Task ◽  
Multiple Tasks ◽  
Meta Learning ◽  
Gradient Based ◽  
Multi Agent ◽  
Self Adaptive

AbstractMulti-agent reinforcement learning (MARL) methods have shown superior performance to solve a variety of real-world problems focusing on learning distinct policies for individual tasks. These approaches face problems when applied to the non-stationary real-world: agents trained in specialized tasks cannot achieve satisfied generalization performance across multiple tasks; agents have to learn and store specialized policies for individual task and reliable identities of tasks are hardly observable in practice. To address the challenge continuously adapting to multiple tasks in MARL, we formalize the problem into a two-stage curriculum. Single-task policies are learned with MARL approaches, after that we develop a gradient-based Self-Adaptive Meta-Learning algorithm, SAML, that cannot only distill single-task policies into a unified policy but also can facilitate the unified policy to continuously adapt to new incoming tasks. In addition, to validate the continuous adaptation performance on complex task, we extend the widely adopted StarCraft benchmark SMAC and develop a new multi-task multi-agent StarCraft environment, Meta-SMAC, for testing various aspects of continuous adaptation method. Our experiments with a population of agents show that our method enables significantly more efficient adaptation than reactive baselines across different scenarios.

scholarly journals Multi-attention Meta Learning for Few-shot Fine-grained Image Recognition

2020 ◽  
Author(s):  
Yaohui Zhu ◽  
Chenlong Liu ◽  
Shuqiang Jiang
Keyword(s):  
Image Recognition ◽  
Feature Learning ◽  
Learning Approaches ◽  
Fine Grained ◽  
Meta Learning ◽  
Benchmark Datasets ◽  
Gradient Based ◽  
General Object ◽  
Base Learner ◽  
Discriminative Parts

The goal of few-shot image recognition is to distinguish different categories with only one or a few training samples. Previous works of few-shot learning mainly work on general object images. And current solutions usually learn a global image representation from training tasks to adapt novel tasks. However, fine-gained categories are distinguished by subtle and local parts, which could not be captured by global representations effectively. This may hinder existing few-shot learning approaches from dealing with fine-gained categories well. In this work, we propose a multi-attention meta-learning (MattML) method for few-shot fine-grained image recognition (FSFGIR). Instead of using only base learner for general feature learning, the proposed meta-learning method uses attention mechanisms of the base learner and task learner to capture discriminative parts of images. The base learner is equipped with two convolutional block attention modules (CBAM) and a classifier. The two CBAM can learn diverse and informative parts. And the initial weights of classifier are attended by the task learner, which gives the classifier a task-related sensitive initialization. For adaptation, the gradient-based meta-learning approach is employed by updating the parameters of two CBAM and the attended classifier, which facilitates the updated base learner to adaptively focus on discriminative parts. We experimentally analyze the different components of our method, and experimental results on four benchmark datasets demonstrate the effectiveness and superiority of our method.

Evaluation and Experimental Validation of Efficient Simulation Models for Optimization of an Electrical Formula Car

2018 ◽  
Author(s):  
Alexander Schmitt ◽  
Helge Grossert ◽  
Robert Seifried
Keyword(s):  
Vehicle Dynamics ◽  
Measurement Data ◽  
Simulation Models ◽  
Vehicle Model ◽  
Efficient Simulation ◽  
Model Based ◽  
Gradient Based ◽  
Kinematic Loops ◽  
Minimal Coordinates ◽  
Suspension Geometry

This paper presents two different ways of modeling a road vehicle for general vehicle dynamics investigation and especially to optimize the suspension geometry. Therefore a numerically highly efficient model is sought such that it can be used later in gradient-based optimization of the suspension geometry. Based on a formula style vehicle with double wishbone suspension setup, a vehicle model based on ODE-formulation using a set of minimal coordinates is built up. The kinematic loops occurring in the double wishbone suspension setup are resolved analytically to a set of independent coordinates. A second vehicle model based on a redundant coordinate formulation is used to compare the efficiency and accuracy. The performance is evaluated and the accuracy is validated with measurement data from a real formula car.

Sign in / Sign up

Export Citation Format

Share Document