Sciweavers

16 search results - page 3 / 4
» Temporal heterogeneity and the value of slowness in robotic ...
Sort
View
ATAL
2005
Springer
13 years 10 months ago
Improving reinforcement learning function approximators via neuroevolution
Reinforcement learning problems are commonly tackled with temporal difference methods, which use dynamic programming and statistical sampling to estimate the long-term value of ta...
Shimon Whiteson
APVIS
2008
13 years 6 months ago
MobiVis: A Visualization System for Exploring Mobile Data
The widespread use of mobile devices brings opportunities to capture large-scale, continuous information about human behavior. Mobile data has tremendous value, leading to busines...
Zeqian Shen, Kwan-Liu Ma
ICRA
2009
IEEE
137views Robotics» more  ICRA 2009»
13 years 11 months ago
Continuous vocal imitation with self-organized vowel spaces in Recurrent Neural Network
Abstract— A continuous vocal imitation system was developed using a computational model that explains the process of phoneme acquisition by infants. Human infants perceive speech...
Hisashi Kanda, Tetsuya Ogata, Toru Takahashi, Kazu...
IROS
2008
IEEE
161views Robotics» more  IROS 2008»
13 years 11 months ago
Segmenting acoustic signal with articulatory movement using Recurrent Neural Network for phoneme acquisition
— This paper proposes a computational model for phoneme acquisition by infants. Human infants perceive speech sounds not as discrete phoneme sequences but as continuous acoustic ...
Hisashi Kanda, Tetsuya Ogata, Kazunori Komatani, H...
AI
1998
Springer
13 years 4 months ago
Remote Agent: To Boldly Go Where No AI System Has Gone Before
Renewed motives for space exploration have inspired NASA to work toward the goal of establishing a virtual presence in space, through heterogeneous eets of robotic explorers. Info...
Nicola Muscettola, P. Pandurang Nayak, Barney Pell...