Search
Now showing items 311-320 of 648
Neural Network Models for Zebra Finch Song Production and Reinforcement Learning
(2004-11-09)
The zebra finch is a standard experimental system for studying learning and generation of temporally extended motor patterns. The first part of this project concerned the evaluation of simple models for the operation and ...
A new biologically motivated framework for robust object recognition
(2004-11-14)
In this paper, we introduce a novel set of features for robust object recognition, which exhibits outstanding performances on a variety ofobject categories while being capable of learning from only a fewtraining examples. ...
Availability-Consistency Trade-Offs in a Fault-Tolerant Stream Processing System
(2004-11-22)
processing. In contrast to previous techniques that handlenode failures, our approach also tolerates network failuresand network partitions. The approach is based on a principledtrade-off between consistency and availability ...
Comparing Network Coding with Multicommodity Flow for the k-pairs Communication Problem
(2004-11-24)
Given a graph G = (V,E) and k source-sink pairs of vertices, this papers investigates the maximum rate r at which all pairs can simultaneously communicate. We view this problem from two perspectives and compare their ...
Learning with Matrix Factorizations
(2004-11-22)
Matrices that can be factored into a product of two simpler matricescan serve as a useful and often natural model in the analysis oftabulated or high-dimensional data. Models based on matrixfactorization (Factor Analysis, ...
Capacity Allocation in Wireless LANs
(2004-11-12)
Today's access point based wireless LANs (WLANs) are inefficient and unfair. For many traffic loads they provide far less total throughput than they should, and do a poor job allocating what throughput they do deliver. ...
Regularization Through Feature Knock Out
(2004-11-12)
In this paper, we present and analyze a novel regularization technique based on enhancing our dataset with corrupted copies of the original data. The motivation is that since the learning algorithm lacks information about ...
Simultaneous Localization and Tracking in Wireless Ad-hoc Sensor Networks
(2005-05-31)
In this thesis we present LaSLAT, a sensor network algorithm thatsimultaneously localizes sensors, calibrates sensing hardware, andtracks unconstrained moving targets using only range measurementsbetween the sensors and ...
Comparing Visual Features for Morphing Based Recognition
(2005-05-25)
This thesis presents a method of object classification using the idea of deformable shape matching. Three types of visual features, geometric blur, C1 and SIFT, are used to generate feature descriptors. These feature ...
A Novel Active Contour Framework. Multi-component Level Set Evolution under Topology Control
(2005-06-01)
We present a novel framework to exert a topology control over a level set evolution. Level set methods offer several advantages over parametric active contours, in particular automated topological changes. In some applications, ...