在机器学习中,表征学习或表示学习是允许系统从原始数据中自动发现特征检测或分类所需的表示的一组技术。这取代了手动特征工程,并允许机器学习特征并使用它们执行特定任务。在有监督的表征学习中,使用标记的输入数据来学习特征,包括监督神经网络,多层感知器和(监督)字典学习。在无监督表征学习中,特征是与未标记的输入数据一起学习的,包括字典学习,独立成分分析,自动编码器,矩阵分解和各种形式的聚类。

VIP内容

我们生活在一个由大量不同模态内容构建而成的多媒体世界中,不同模态信息之间具有高度的相关性和互补性,多模态表征学习的主要目的就是挖掘出不同模态之间的共性和特性,产生出可以表示多模态信息的隐含向量.该文章主要介绍了目前应用较广的视觉语言表征的相应研究工作,包括传统的基于相似性模型的研究方法和目前主流的基于语言模型的预训练的方法.目前比较好的思路和解决方案是将视觉特征语义化然后与文本特征通过一个强大的特征抽取器产生出表征,其中Transformer[1]作为主要的特征抽取器被应用表征学习的各类任务中.文章分别从研究背景、不同研究方法的划分、测评方法、未来发展趋势等几个不同角度进行阐述.

http://www.jos.org.cn/jos/ch/reader/view_abstract.aspx?file_no=6125&flag=1

成为VIP会员查看完整内容
0
93

最新内容

Neural networks in the lazy training regime converge to kernel machines. Can neural networks in the rich feature learning regime learn a kernel machine with a data-dependent kernel? We demonstrate that this can indeed happen due to a phenomenon we term silent alignment, which requires that the tangent kernel of a network evolves in eigenstructure while small and before the loss appreciably decreases, and grows only in overall scale afterwards. We show that such an effect takes place in homogenous neural networks with small initialization and whitened data. We provide an analytical treatment of this effect in the linear network case. In general, we find that the kernel develops a low-rank contribution in the early phase of training, and then evolves in overall scale, yielding a function equivalent to a kernel regression solution with the final network's tangent kernel. The early spectral learning of the kernel depends on the depth. We also demonstrate that non-whitened data can weaken the silent alignment effect.

0
0
下载
预览

最新论文

Neural networks in the lazy training regime converge to kernel machines. Can neural networks in the rich feature learning regime learn a kernel machine with a data-dependent kernel? We demonstrate that this can indeed happen due to a phenomenon we term silent alignment, which requires that the tangent kernel of a network evolves in eigenstructure while small and before the loss appreciably decreases, and grows only in overall scale afterwards. We show that such an effect takes place in homogenous neural networks with small initialization and whitened data. We provide an analytical treatment of this effect in the linear network case. In general, we find that the kernel develops a low-rank contribution in the early phase of training, and then evolves in overall scale, yielding a function equivalent to a kernel regression solution with the final network's tangent kernel. The early spectral learning of the kernel depends on the depth. We also demonstrate that non-whitened data can weaken the silent alignment effect.

0
0
下载
预览
参考链接
Top