Three cohorts of rats with extensive hippocampal lesions received multiple tests to examine the relationships between particular forms of associative learning and an influential account of hippocampal function (the cognitive map hypothesis). Hippocampal lesions spared both the ability to discriminate two different digging media and to discriminate two different room locations in a go/no-go task...

Deep Learning models enjoy considerable success in Natural Language Processing. While deep architectures produce useful representations that lead to improvements in various tasks, they are often difficult to interpret. This makes the analysis of learned structures particularly difficult. In this paper, we rely on empirical tests to see whether a particular structure makes sense. We present an a...

Deep learning techniques have led to massive improvements in recent years, but large amounts of labeled data are typically required to learn these complex models. We present a semi-supervised approach for training deep models that combines the feature learning capabilities of neural networks with the probabilistic modeling of Gaussian processes and demonstrate that unlabeled data can significan...

Semi-supervised and cross-lingual knowledge transfer learnings are two strategies for boosting performance of lowresource speech recognition systems. In this paper, we propose a unified knowledge transfer learning method to deal with these two learning tasks. Such a knowledge transfer learning is realized by fine-tuning of Deep Neural Network (DNN). We demonstrate its effectiveness in both mono...

BACKGROUND Taeniodonta is a clade of Late Cretaceous-Paleogene mammals remarkable for their relatively extreme cranial, dental, and postcranial adaptations and notable for being among the first mammals to achieve relatively large size following the Cretaceous-Paleogene mass extinction. Previous workers have hypothesized that taeniodonts can be divided into two clades: Conoryctidae, a group of s...