Zobrazeno 1 - 10
of 162
pro vyhledávání: '"R, Eckmiller"'
Autor:
Carsten Wilks, R. Eckmiller
Publikováno v:
Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005..
In this paper we present an optimization method for a learning algorithm for tactile stimuli generation which are adapted by means of tactile perception of a human. Because of special requirements for a learning algorithm for tactile perception tunin
Autor:
R. Eckmiller, M. Jansen
Publikováno v:
Proceedings of 1993 International Conference on Neural Networks (IJCNN-93-Nagoya, Japan).
A set of four separate three-layer-perceptrons (3LP) learns matrix components representing mass-coupling, coriolis, viscose, and static friction forces in an inverse robot model as a function of the robot's current position and payload. Based on trai
Autor:
H. Napp-Zinn, R. Eckmiller
Publikováno v:
Proceedings of 1993 International Conference on Neural Networks (IJCNN-93-Nagoya, Japan).
This paper briefly reviews the characteristic properties of biological neural systems and describes the recent development of a biology-inspired pulse processing neural network (BPN) hardware. The BPN employs pulse processing, EPSP, IPSP, membrane po
Publikováno v:
Proceedings of the International Joint Conference on Neural Networks, 2003..
We present a tactile intelligent sensory substitution system (TIS/sup 3/) as a novel tactile communication system with dialog-based tuning. TIS/sup 3/ consists of a tactile encoder (TE) which maps desired objects or patterns (P) onto spatio-temporal
Publikováno v:
NNSP
We present a novel concept of a tactile communication system with dialog-based tuning possibilities for the exploration of tactile language developments. An experimental implementation of the proposed tactile intelligent sensory substitution system (
Publikováno v:
ICASSP
A tuning method with reinforcement learning (RL) for the retina encoder (RE) of a retina implant (RI) as a visual prosthesis for blind subjects with retinal degenerations is proposed. The RE simulates retinal information processing in real time by me
Autor:
R. Eckmiller, Thomas Frontzek
Publikováno v:
IJCNN'01. International Joint Conference on Neural Networks. Proceedings (Cat. No.01CH37222).
We propose a multi-compartment system framework for analyzing and controlling complex nonlinear dynamical systems. Firstly, we define the terms compartment, multicompartment system (MCS), and multi-compartment model (MCM). Based on these definitions
Autor:
R. Eckmiller, R. Hornig
Publikováno v:
IJCNN'01. International Joint Conference on Neural Networks. Proceedings (Cat. No.01CH37222).
The purpose of this paper is to investigate the feasibility of retina implants to selectively stimulate individual retina neurons by coupled current pulses for multielectrode arrays. Retina implants with learning retina encoders for blind subjects su
Autor:
J F, Rizzo, J, Wyatt, M, Humayun, E, de Juan, W, Liu, A, Chow, R, Eckmiller, E, Zrenner, T, Yagi, G, Abrams
Publikováno v:
Ophthalmology. 108(1)
Autor:
R. Eckmiller, V. Ortmann
Publikováno v:
ICASSP
An image processing system for the real-time object detection and recognition was designed on the principles of active vision and sequential analysis. The real-world visual tasks can be solved due to predictive control of the vision sensor. The seque