首页 | 本学科首页   官方微博 | 高级检索  
文章检索
  按 检索   检索词:      
出版年份:   被引次数:   他引次数: 提示:输入*表示无穷大
  收费全文   39篇
  国内免费   2篇
  完全免费   24篇
  自动化技术   65篇
  2018年   1篇
  2017年   6篇
  2016年   2篇
  2015年   8篇
  2014年   12篇
  2013年   8篇
  2012年   7篇
  2011年   6篇
  2010年   3篇
  2009年   4篇
  2008年   5篇
  2004年   1篇
  1992年   1篇
  1986年   1篇
排序方式: 共有65条查询结果,搜索用时 156 毫秒
1.
Transfer of Learning by Composing Solutions of Elemental Sequential Tasks   总被引:2,自引:0,他引:2  
Although building sophisticated learning agents that operate in complex environments will require learning to perform multiple tasks, most applications of reinforcement learning have focused on single tasks. In this paper I consider a class of sequential decision tasks (SDTs), called composite sequential decision tasks, formed by temporally concatenating a number of elemental sequential decision tasks. Elemental SDTs cannot be decomposed into simpler SDTs. I consider a learning agent that has to learn to solve a set of elemental and composite SDTs. I assume that the structure of the composite tasks is unknown to the learning agent. The straightforward application of reinforcement learning to multiple tasks requires learning the tasks separately, which can waste computational resources, both memory and time. I present a new learning algorithm and a modular architecture that learns the decomposition of composite SDTs, and achieves transfer of learning by sharing the solutions of elemental SDTs across multiple composite SDTs. The solution of a composite SDT is constructed by computationally inexpensive modifications of the solutions of its constituent elemental SDTs. I provide a proof of one aspect of the learning algorithm.  相似文献
2.
迁移学习研究进展   总被引:2,自引:2,他引:0       下载免费PDF全文
近年来,迁移学习已经引起了广泛的关注和研究.迁移学习是运用已存有的知识对不同但相关领域问题进行求解的一种新的机器学习方法.它放宽了传统机器学习中的两个基本假设:(1)用于学习的训练样本与新的测试样本满足独立同分布的条件;(2)必须有足够可利用的训练样本才能学习得到一个好的分类模型.目的是迁移已有的知识来解决目标领域中仅有少量有标签样本数据甚至没有的学习问题.对迁移学习算法的研究以及相关理论研究的进展进行了综述,并介绍了在该领域所做的研究工作,特别是利用生成模型在概念层面建立迁移学习模型.最后介绍了迁移学习在文本分类、协同过滤等方面的应用工作,并指出了迁移学习下一步可能的研究方向.  相似文献
3.
A key assumption of traditional machine learning approach is that the test data are draw from the same distribution as the training data. However, this assumption does not hold in many real-world scenarios. For example, in facial expression recognition, the appearance of an expression may vary significantly for different people. As a result, previous work has shown that learning from adequate person-specific data can improve the expression recognition performance over the one from generic data. However, person-specific data is typically very sparse in real-world applications due to the difficulties of data collection and labeling, and learning from sparse data may suffer from serious over-fitting. In this paper, we propose to learn a person-specific model through transfer learning. By transferring the informative knowledge from other people, it allows us to learn an accurate model for a new subject with only a small amount of person-specific data. We conduct extensive experiments to compare different person-specific models for facial expression and action unit (AU) recognition, and show that transfer learning significantly improves the recognition performance with a small amount of training data.  相似文献
4.
一类基于谱方法的强化学习混合迁移算法   总被引:1,自引:0,他引:1       下载免费PDF全文
在状态空间比例放大的迁移任务中, 原型值函数方法只能有效迁移较小特征值对应的基函数, 用于目标任务的值函数逼近时会使部分状态的值函数出现错误. 针对该问题, 利用拉普拉斯特征映射能保持状态空间局部拓扑结构不变的特点, 对基于谱图理论的层次分解技术进行了改进, 提出一种基函数与子任务最优策略相结合的混合迁移方法. 首先, 在源任务中利用谱方法求取基函数, 再采用线性插值技术将其扩展为目标任务的基函数; 然后, 用插值得到的次级基函数(目标任务的近似Fiedler特征向量)实现任务分解, 并借助改进的层次分解技术求取相关子任务的最优策略; 最后, 将扩展的基函数和获取的子任务策略一起用于目标任务学习中. 所提的混合迁移方法可直接确定目标任务部分状态空间的最优策略, 减少了值函数逼近所需的最少基函数数目, 降低了策略迭代次数, 适用于状态空间比例放大且具有层次结构的迁移任务. 格子世界的仿真结果验证了新方法的有效性.  相似文献
5.
Boosting for transfer learning from multiple data sources   总被引:1,自引:0,他引:1  
Transfer learning aims at adapting a classifier trained on one domain with adequate labeled samples to a new domain where samples are from a different distribution and have no class labels. In this paper, we explore the transfer learning problems with multiple data sources and present a novel boosting algorithm, SharedBoost. This novel algorithm is capable of applying for very high dimensional data such as in text mining where the feature dimension is beyond several ten thousands. The experimental results illustrate that the SharedBoost algorithm significantly outperforms the traditional methods which transfer knowledge with supervised learning techniques. Besides, SharedBoost also provides much better classification accuracy and more stable performance than some other typical transfer learning methods such as the structural correspondence learning (SCL) and the structural learning in the multiple sources transfer learning problems.  相似文献
6.
Convex multi-task feature learning   总被引:1,自引:1,他引:0  
We present a method for learning sparse representations shared across multiple tasks. This method is a generalization of the well-known single-task 1-norm regularization. It is based on a novel non-convex regularizer which controls the number of learned features common across the tasks. We prove that the method is equivalent to solving a convex optimization problem for which there is an iterative algorithm which converges to an optimal solution. The algorithm has a simple interpretation: it alternately performs a supervised and an unsupervised step, where in the former step it learns task-specific functions and in the latter step it learns common-across-tasks sparse representations for these functions. We also provide an extension of the algorithm which learns sparse nonlinear representations using kernels. We report experiments on simulated and real data sets which demonstrate that the proposed method can both improve the performance relative to learning each task independently and lead to a few learned features common across related tasks. Our algorithm can also be used, as a special case, to simply select—not learn—a few common variables across the tasks. Editors: Daniel Silver, Kristin Bennett, Richard Caruana. This is a longer version of the conference paper (Argyriou et al. in Advances in neural information processing systems, vol. 19, 2007a). It includes new theoretical and experimental results.  相似文献
7.
Transfer in variable-reward hierarchical reinforcement learning   总被引:1,自引:1,他引:0  
Transfer learning seeks to leverage previously learned tasks to achieve faster learning in a new task. In this paper, we consider transfer learning in the context of related but distinct Reinforcement Learning (RL) problems. In particular, our RL problems are derived from Semi-Markov Decision Processes (SMDPs) that share the same transition dynamics but have different reward functions that are linear in a set of reward features. We formally define the transfer learning problem in the context of RL as learning an efficient algorithm to solve any SMDP drawn from a fixed distribution after experiencing a finite number of them. Furthermore, we introduce an online algorithm to solve this problem, Variable-Reward Reinforcement Learning (VRRL), that compactly stores the optimal value functions for several SMDPs, and uses them to optimally initialize the value function for a new SMDP. We generalize our method to a hierarchical RL setting where the different SMDPs share the same task hierarchy. Our experimental results in a simplified real-time strategy domain show that significant transfer learning occurs in both flat and hierarchical settings. Transfer is especially effective in the hierarchical setting where the overall value functions are decomposed into subtask value functions which are more widely amenable to transfer across different SMDPs.  相似文献
8.
Flexible latent variable models for multi-task learning   总被引:1,自引:1,他引:0  
Given multiple prediction problems such as regression or classification, we are interested in a joint inference framework that can effectively share information between tasks to improve the prediction accuracy, especially when the number of training examples per problem is small. In this paper we propose a probabilistic framework which can support a set of latent variable models for different multi-task learning scenarios. We show that the framework is a generalization of standard learning methods for single prediction problems and it can effectively model the shared structure among different prediction tasks. Furthermore, we present efficient algorithms for the empirical Bayes method as well as point estimation. Our experiments on both simulated datasets and real world classification datasets show the effectiveness of the proposed models in two evaluation settings: a standard multi-task learning setting and a transfer learning setting.  相似文献
9.
Transfer of learning in virtual environments: a new challenge?   总被引:1,自引:0,他引:1  
The aim of all education is to apply what we learn in different contexts and to recognise and extend this learning to new situations. Virtual learning environments can be used to build skills. Recent research in cognitive psychology and education has shown that acquisitions are linked to the initial context. This provides a challenge for virtual reality in education or training. A brief overview of transfer issues highlights five main ideas: (1) the type of transfer enables the virtual environment (VE) to be classified according to what is learned; (2) the transfer process can create conditions within the VE to facilitate transfer of learning; (3) specific features of VR must match and comply with transfer of learning; (4) transfer can be used to assess a VE’s effectiveness; and (5) future research on transfer of learning must examine the singular context of learning. This paper discusses how new perspectives in cognitive psychology influence and promote transfer of learning through the use of VEs.  相似文献
10.
迁移学习数据分类中的ESVM算法   总被引:1,自引:0,他引:1       下载免费PDF全文
在迁移学习中对变化后的数据集进行分类时,噪音导致分类结果不合理。为此,提出一种迁移学习数据分类中的扩展支持向量机(ESVM)算法。使用变化前数据集的概率分布信息及学习经验,指导缓慢变化后的数据集进行分类,使分割面既可以准确分割现有数据集,同时也保留原先数据集的一些属性。实验结果表明,该算法具有一定的抗噪性能。  相似文献
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号