We present an actor-critic scheme for reinforcement learning in complex domains. The main contribution is to show that planning and I/O dynamics can be separated such that an intra...
Pedro Alejandro Ortega, Daniel Alexander Braun, Si...
Abstract. The electrosensory lateral line lobe (ELL) of mormyridelectric sh is a cerebellum-likestructure that receives primarya erent input from electroreceptors in the skin. Purk...
Record linkage identifies multiple records referring to the same entity even if they are not bit-wise identical. It is thus an essential technology for data integration and data c...
We demonstrate applications of psycholinguistic and sublexical information for learning Chinese characters. The knowledge about the grapheme-phoneme conversion (GPC) rules of lang...
Grammatical relationships are an important level of natural language processing. We present a trainable approach to find these relationships through transformation sequences and-e...