We propose a model of the hippocampus aimed at learning the timed association between subsequent sensory events. The properties of the neural network allow it to learn and predict ...
We describe and analyze efficient algorithms for learning a linear predictor from examples when the learner can only view a few attributes of each training example. This is the ca...
We propose a new framework for speaker recognition, referred as Fishervoice. It includes the design of a feature representation known as the structured score vector (SSV), which r...
This paper describes the Arabic broadcast transcription system fielded by IBM in the GALE Phase 3.5 machine translation evaluation. Key advances compared to our Phase 2.5 system ...
George Saon, Hagen Soltau, Upendra Chaudhari, Step...
Given the great amount of data that are generated of the experiments to analyze information of extracted chemical fluids of the brain of a rodent, arises the necessity to design an...