We present an approach to inductive concept learning using multiple models for time series. Our objective is to improve the efficiency and accuracy of concept learning by decomposi...
In this study, we propose increasing discriminative power on the maximum a posteriori (MAP)-based mapping function estimation for acoustic model adaptation. Based on the effective...
Pseudo-likelihood and contrastive divergence are two well-known examples of contrastive methods. These algorithms trade off the probability of the correct label with the probabili...
Mobile learning exposes learning to the natural environment. If this environment is large, the learners have to navigate to find the learning objects or to explore the environment...
— Recent advances in self-supervised learning have enabled very long-range visual detection of obstacles and pathways (to 100 hundred meters or more). Unfortunately, the category...
Pierre Sermanet, Raia Hadsell, Marco Scoffier, Urs...