We develop an online algorithm called Component Hedge for learning structured concept classes when the loss of a structured concept sums over its components. Example classes inclu...
Wouter M. Koolen, Manfred K. Warmuth, Jyrki Kivine...
While Boltzmann Machines have been successful at unsupervised learning and density modeling of images and speech data, they can be very sensitive to noise in the data. In this pap...
Yichuan Tang, Ruslan Salakhutdinov, Geoffrey E. Hi...
This paper gives a data structure (UDS) for supporting database retrieval, inference and machine learning that attempts to unify and extend previous work in relational databases, ...
We propose a new neural network architecture, called Simple Recurrent Temporal-Difference Networks (SR-TDNs), that learns to predict future observations in partially observable en...
Japanese case markers, which indicate the grammatical relation of the complement NP to the predicate, often pose challenges to the generation of Japanese text, be it done by a for...