搜索结果: 1-15 共查到“计算机科学技术 Training”相关记录23条 . 查询时间(0.078 秒)
Academy of Mathematics and Systems Science, CAS Colloquia & Seminars：Accelerating Decentralized Deep Training with Sparse and Effective Topologies
稀疏有效 拓扑加速 分散式 深度训练
2023/11/13
Decentralized optimization algorithms save remarkable communication overheads in distributed deep learning since each node averages locally with neighbors. The network topology connecting all nodes de...
Imagine sitting on a park bench, watching someone stroll by. While the scene may constantly change as the person walks, the human brain can transform that dynamic visual information into a more stable...
Supercomputing Speeds Up Deep Learning Training（图）
Supercomputing Speeds Up Learning Training
2017/11/24
A team of researchers from the University of California, Berkeley, the University of California, Davis and the Texas Advanced Computing Center (TACC) published the results of an effort to harness the ...
The synergy of education and technology can transform the world we live in. A virtual experience is usually achieved by feeding sensory information to a user via virtual displays (head mounted display...
IUPUI study:Training computers to differentiate between people with the same name
Training computers differentiate between people same name
2017/2/16
All individuals are unique but millions of people share names. How to distinguish -- or as it is technically known, disambiguate -- people with common names and determine which John Smith or Maria Gar...
DIRECTION OF DIGITAL IMAGE ANALYSIS TRAINING THROUGH THE 28 YEARS EXPERIENCE
remote sensing classroom lecture hands-on training e-learning
2015/8/24
Remote Sensing Technology Center of Japan (RESTEC) has been organizing various kinds of remote sensing training programs
since RESTEC was established in 1975. Among them, remote sensing training cou...
Efficient EM Training of Gaussian Mixtures with Missing Data
Gaussian mixtures missing data EM algorithm imputation.
2012/11/23
In data-mining applications, we are frequently faced with a large fraction of missing entries in the data matrix, which is problematic for most discriminant machine learning algorithms. A solution tha...
Maximum Rank Correlation Training for Statistical Machine Translation
Maximum Rank Correlation Training Statistical Machine Translation
2013/4/22
We propose Maximum Ranking Correlation (MRC) as an objective function in discrimi-native tuning of parameters in a linear model of Statistical Machine Translation (SMT). We try to maximize the ranking...
Testing Delivery Systems in Transnational Virtual Learning: The Vocational Management Training for the European Tourism Industry (VocMat) Case Study
Testing Delivery Systems Transnational Virtual Vocational Management
2010/9/25
This article discusses the lessons learned from developing and delivering the Vocational Management Training for the European Tourism Industry (VocMat) online training programme, which was aimed at pr...
针对中文组织机构名识别中的标注语料匮乏问题，提出了一种基于协同训练机制的组织机构名识别方法。该算法利用Tri-training学习方式将基于条件随机场的分类器、基于支持向量机的分类器和基于记忆学习方法的分类器组合成一个分类体系，并依据最优效用选择策略进行新加入样本的选择。在大规模真实语料上与co-training方法进行了比较实验，实验结果表明，此方法能有效利用大量未标注语料提高算法的泛化能力。
...
Weakly-Supervised Violence Detection in Movies with Audio and Video Based Co-training
Violence Weakly-supervised pLSA Audio Video Co-training
2013/7/16
In this work, we present a novel method to detect violent shots in movies. The detection process is split into two views–––the audio and video views. From the audio-view, a weakly-supervised method is...
Optimization of a training set for more robust face detection
Face detection Manifold Genetic algorithm Resampling
2013/7/16
The performance of a learning-based method highly depends on the quality of a training set. However, it is very challenging to collect an efficient and effective training set for training a good class...
基于Tri-training的半监督SVM
半监督学习 协同训练 Tri-training
2009/9/30
当前机器学习面临的主要问题之一是如何有效地处理海量数据，而标记训练数据是十分有限且不易获得的。提出了一种新的半监督SVM算法，该算法在对SVM训练中，只要求少量的标记数据，并能利用大量的未标记数据对分类器反复的修正。在实验中发现，Tri-training的应用确实能够提高SVM算法的分类精度，并且通过增大分类器间的差异性能够获得更好的分类效果，所以Tri-training对分类器的要求十分宽松，通...
基于互联网和self-training的中文问答模式学习
互联网 问答模式 self-training
2009/9/18
在已有的问答模式学习中，模式定义和候选答案评分偏于简单，而且学习过程依赖于人工标定语料。通过挖掘Web文本中动、名词序列的骨架模式，用以扩充模式定义；将self-training学习机制引入问答模式学习：用一对训练语料进行初始学习，通过互联网搜索，自动选择可靠程度较高的问答对，重新训练；扩充了启发规则，改进候选答案的评分方法。实验结果表明：所提出的问答模式学习方法能有效地提高中文问答系统的性能。