Fixed, limited budgets often constrain the amount of expert annotation that can go into the construction of annotated corpora. Estimating the cost of annotation is the first step ...
Eric K. Ringger, Marc Carmen, Robbie Haertel, Kevi...
Abstract. We introduce a new class of recurrent, truly sequential SVM-like devices with internal adaptive states, trained by a novel method called EVOlution of systems with KErnel-...
We describe a method for the fully automatic learning of hierarchical finite state translation models. The input to the method is transcribed speech utterances and their correspon...
Abstract— We discuss disciplinary barriers which have traditionally prevented robotics from significantly impacting the built (architectural) environment we inhabit. Specifical...
Apoorva Kapadia, Ian D. Walker, Keith Evan Green, ...
For a Markov Decision Process with finite state (size S) and action spaces (size A per state), we propose a new algorithm--Delayed Q-Learning. We prove it is PAC, achieving near o...
Alexander L. Strehl, Lihong Li, Eric Wiewiora, Joh...