This paper describes a new on-demand wake-up prediction policy for reducing leakage power. The key insight is that branch prediction can be used to selectively wake up only the nee...
We present a data-driven approach to learn user-adaptive referring expression generation (REG) policies for spoken dialogue systems. Referring expressions can be difficult to unde...
Genetic programming is an automatic method for creating a computer program or other complex structure to solve a problem. This paper first reviews various instances where genetic p...
John R. Koza, Martin A. Keane, Jessen Yu, Forrest ...
We present an architectural approach to learning problem solving skills from demonstration, using internal models to represent problem-solving operational knowledge. Internal forwa...
Haris Dindo, Antonio Chella, Giuseppe La Tona, Mon...
We have developed a function-level power estimation methodology for predicting the power dissipation of embedded software. For a given microprocessor core, we empirically build th...
Gang Qu, Naoyuki Kawabe, Kimiyoshi Usami, Miodrag ...