开课单位--赫尔辛基大学
21
22
23
24
25
26
27
28
29
30
![](functions/showpic.php?filename=2019071008340862.png)
Independent Component Analysis[独立成分分析]
Aapo Hyvärinen(赫尔辛基大学) In independent component analysis (ICA), the purpose is to linearly decompose a multidimensional data vector into components that are as statistically...
热度:133
Aapo Hyvärinen(赫尔辛基大学) In independent component analysis (ICA), the purpose is to linearly decompose a multidimensional data vector into components that are as statistically...
热度:133
![](functions/showpic.php?filename=2020060601091881.png)
Efficient Multiple-Click Models in Web Search[网络搜索中的高效多点击模型]
Chao Liu, Fan Guo, Yi-Min Wang(赫尔辛基大学)
热度:41
Chao Liu, Fan Guo, Yi-Min Wang(赫尔辛基大学)
热度:41
![](functions/showpic.php?filename=2016092502224216.png)
![](functions/showpic.php?filename=2016012501590342.png)
Causal Modelling Combining Instantaneous and Lagged Effects: an Identifiable Model Based on Non-Gaussianity[因果模型结合瞬时和滞后效应:基于非高斯的识别模型]
Aapo Hyvärinen(赫尔辛基大学) Causal analysis of continuous-valued variables typically uses either autoregressive models or linear Gaussian Bayesian networks with instantaneous eff...
热度:32
Aapo Hyvärinen(赫尔辛基大学) Causal analysis of continuous-valued variables typically uses either autoregressive models or linear Gaussian Bayesian networks with instantaneous eff...
热度:32
![](functions/showpic.php?filename=2016060506401641.png)
Efficient max-margin Markov learning via conditional gradient and probabilistic inference[基于条件梯度和概率推理的马尔可夫学习效率最大化]
Juho Rousu(赫尔辛基大学) We present a general and efficient optimisation methodology for for max-margin sructured classification tasks. The efficiency of the method relies on ...
热度:35
Juho Rousu(赫尔辛基大学) We present a general and efficient optimisation methodology for for max-margin sructured classification tasks. The efficiency of the method relies on ...
热度:35
![](functions/showpic.php?filename=2016052809491875.png)
Estimation of human endogeneous retrovirus activities from expressed sequence databases[表达序列数据库内的人类内源性逆转录病毒活性的估计]
Merja Oja(赫尔辛基大学) Human endogenous retroviruses (HERVs) are remnants of ancient retrovirus infections and now reside within the human DNA. Recently HERV expression has ...
热度:44
Merja Oja(赫尔辛基大学) Human endogenous retroviruses (HERVs) are remnants of ancient retrovirus infections and now reside within the human DNA. Recently HERV expression has ...
热度:44
![](functions/showpic.php?filename=2016070701575698.png)
Multilabel prediction of drug activity[药物活性的多标签预测]
Juho Rousu(赫尔辛基大学) Machine learning has become increasingly important in drug discovery where viable molecular structures are searched or designed for therapeutic effica...
热度:42
Juho Rousu(赫尔辛基大学) Machine learning has become increasingly important in drug discovery where viable molecular structures are searched or designed for therapeutic effica...
热度:42
![](functions/showpic.php?filename=2016042709344224.png)
Sigma point and particle approximations of stochastic differential equations in optimal filtering[Σ最优滤波中的随机微分方程的Σ点和近似粒子]
Simo Särkkä(赫尔辛基大学) The unscented transform (UT) is a relatively recent method for approximating non-linear transformations of random variables. Instead of the classical ...
热度:53
Simo Särkkä(赫尔辛基大学) The unscented transform (UT) is a relatively recent method for approximating non-linear transformations of random variables. Instead of the classical ...
热度:53
![](functions/showpic.php?filename=2016102209431227.jpg)
Randomization Methods in Data Mining[数据挖掘中的随机化方法]
Heikki Mannila(赫尔辛基大学) Data mining research has developed many algorithms for various analysis tasks on large and complex datasets. However, assessing the significance of da...
热度:57
Heikki Mannila(赫尔辛基大学) Data mining research has developed many algorithms for various analysis tasks on large and complex datasets. However, assessing the significance of da...
热度:57
![](functions/showpic.php?filename=2017031208131771.png)
Structured Output Prediction of Enzyme Function via Reaction Kernels[通过反应核实现酶功能的结构化输出预测]
Juho Rousu(赫尔辛基大学) Enzyme function prediction is an important problem in post-genomic bioinformatics. There are two general methods for solving the problem: transfer of ...
热度:44
Juho Rousu(赫尔辛基大学) Enzyme function prediction is an important problem in post-genomic bioinformatics. There are two general methods for solving the problem: transfer of ...
热度:44