We show how a general grammar may be automatically adapted for fast parsing of utterances from a specific domain by means of constituent pruning and grammar specialization based o...
Abstract. Ensemble methods are popular learning methods that usually increase the predictive accuracy of a classifier though at the cost of interpretability and insight in the deci...
Traditional methods for ATR Automatic Target Recognition use infrared IR sensors for detecting heat emanating fromtargets. IR-based ATR techniques are susceptible to sensor-in...
— A learning machine is called singular if its Fisher information matrix is singular. Almost all learning machines used in information processing are singular, for example, layer...
Abstract. We consider the problem of learning an acyclic discrete circuit with n wires, fan-in bounded by k and alphabet size s using value injection queries. For the class of tran...
Dana Angluin, James Aspnes, Jiang Chen, Lev Reyzin