Sciweavers

3222 search results - page 222 / 645
» A Data Model for Effectively Computable Functions
Sort
View
ICANN
2003
Springer
15 years 10 months ago
Unsupervised Learning of a Kinematic Arm Model
Abstract. An abstract recurrent neural network trained by an unsupervised method is applied to the kinematic control of a robot arm. The network is a novel extension of the Neural ...
Heiko Hoffmann, Ralf Möller
167
Voted
DCOSS
2006
Springer
15 years 9 months ago
An Optimal Data Propagation Algorithm for Maximizing the Lifespan of Sensor Networks
We consider the problem of data propagation in wireless sensor networks and revisit the family of mixed strategy routing schemes. We show that maximizing the lifespan, balancing th...
Aubin Jarry, Pierre Leone, Olivier Powell, Jos&eac...
DCC
2010
IEEE
16 years 14 days ago
Lossless Compression Based on the Sequence Memoizer
In this work we describe a sequence compression method based on combining a Bayesian nonparametric sequence model with entropy encoding. The model, a hierarchy of Pitman-Yor proce...
Jan Gasthaus, Frank Wood, Yee Whye Teh
NIPS
1998
15 years 7 months ago
Coding Time-Varying Signals Using Sparse, Shift-Invariant Representations
A common way to represent a time series is to divide it into shortduration blocks, each of which is then represented by a set of basis functions. A limitation of this approach, ho...
Michael S. Lewicki, Terrence J. Sejnowski
187
Voted
DSN
2005
IEEE
15 years 11 months ago
TIBFIT: Trust Index Based Fault Tolerance for Arbitrary Data Faults in Sensor Networks
Since sensor data gathering is the primary functionality of sensor networks, it is important to provide a fault tolerant method for reasoning about sensed events in the face of ar...
Mark D. Krasniewski, Padma Varadharajan, Bryan Rab...