Search
Now showing items 51-60 of 112
Toward nonlinear local reinforcement learning rules through neuroevolution
(2013)
We consider the problem of designing local reinforcement learning rules for artificial neural network (ANN) controllers. Motivated by the universal approximation properties of ANNs, we adopt an ANN representation for the ...
pFusion: A P2P architecture for internet-scale content-based search and retrieval
(2007)
The emerging Peer-to-Peer (P2P) model has become a very powerful and attractive paradigm for developing Internet-scale systems for sharing resources, including files and documents. The distributed nature of these systems, ...
Instruction-Isomorphism in program execution
(2003)
This paper identifies a fundamental runtime program property: Instruction-Isomorphism. An instruction instance is said to be isomorphic if its component - Information derived from the instruction and its backward dynamic ...
Image-based crowd rendering
(2002)
Rendering crowded scenes with thousands of different animated virtual people in real time is challenging. An image-based rendering approach for displaying multiple avatars is proposed. The system allows real-time rendering ...
Region of interest video coding for low bit-rate transmission of carotid ultrasound videos over 3G wireless networks.
(2007)
Efficient medical video transmission over 3G wireless is of great importance for fast diagnosis and on site medical staff training purposes. In this paper we present a region of interest based ultrasound video compression ...
Behavioral plasticity through the modulation of switch neurons
(2016)
A central question in artificial intelligence is how to design agents capable of switching between different behaviors in response to environmental changes. Taking inspiration from neuroscience, we address this problem by ...
Fast cloth animation on walking avatars
(2001)
This paper describes a fast technique for animating clothing on walking humans. It exploits a mass-spring cloth model but applies a new velocity directional modification approach to overcome its super-elasticity. The ...
Improved detection of breast cancer nuclei using modular neural networks
(2000)
A modular neural network-based approach to detect and classify breast cancer nuclei stained for steroid receptors in hispathological sections is evaluated. The system named biopsy analysis support system (BASS) is designed ...
Towards in-situ data storage in sensor databases
(2005)
The advances in wireless communications along with the exponential growth of transistors per integrated circuit lead to a rapid evolution of Wireless Sensor Devices (WSDs), that can be used for monitoring environmental ...