Using multi-GPU systems, including GPU clusters, is gaining popularity in scientific computing. However, when using multiple GPUs concurrently, the conventional data parallel GPU...
We consider the problem of learning a similarity function from a set of positive equivalence constraints, i.e. 'similar' point pairs. We define the similarity in informa...
We discuss properties of high order neurons in competitive learning. In such neurons, geometric shapes replace the role of classic `point' neurons in neural networks. Complex ...
: Web usage mining, possibly used in conjunction with standard approaches to personalization such as collaborative filtering, can help address some of the shortcomings of these tec...
Bamshad Mobasher, Honghua Dai, Tao Luo, Miki Nakag...
Context-dependent word similarity can be measured over multiple cross-cutting dimensions. For example, lung and breath are similar thematically, while authoritative and superfici...