Transfer learning aims to solve new learning problems by extracting and making use of the common knowledge found in related domains. A key element of transfer learning is to ident...
Qiang Yang, Vincent Wenchen Zheng, Bin Li, Hankz H...
When modeling high-dimensional richly structured data, it is often the case that the distribution defined by the Deep Boltzmann Machine (DBM) has a rough energy landscape with man...
We propose an unconventional but highly effective approach
to robust fitting of multiple structures by using statistical
learning concepts. We design a novel Mercer kernel
for t...
unsupervised construction of topological maps, which provide an abstraction of the environment in terms of visual aspects. An unsupervised clustering algorithm is used to represent...
We introduce a new approach for Clustering and Aggregating Relational Data (CARD). We assume that data is available in a relational form, where we only have information about the ...