Learn More
We aim at building a joint space trajectory generation system. Connected to a xed ma-nipulator with sensory feedback, neural networks are expected to move the end-eeector from any start to any goal connguration without colliding with obstacles. The output of our system is a series of consecutive conngurations yielding a joint-space trajectory. Sensory(More)
This paper presents a novel kind of generalizing neural storage tailored for the problem of global motion planning for six-joint manipulators in complex, changing environments. Paths are stored in a growing map of neurons with adaptive ellipsoidal receptive eld, called the Ellipsoidal Map. Path planning is based on nding the best-matching neurons for start(More)
A neural classiier of planar trajectories is presented. There already exist a large variety of classi-ers that are specialized on particular invariants contained in a trajectory classiication task such as position-invariance, rotation-invariance, size-invariance, .... That is, there exist classiiers specialized on recognizing trajectories e.g. independently(More)
We present a neural trajectory storage for manipulator trajectories. Trajectories will be neurally stored as a sequence of discrete joint positions. Every time a trajectory needs to be generated, the storage is consulted. Besides being a \classical" retrieval system, the neural network is able to generalize from stored trajectories to new trajectories and(More)
Curved nailing according to Lezius and Herzer was applied to 700 of 1,062 cases of pertrochanteric fractures of the femur at the Surgical Department of the "Carl Gustav Carus" Medical Academy, Dresden, between 1964 and 1985. Complications are described, and results are generally compared with other surgical techniques used to handle pertrochanteric(More)
Functional imaging studies on responders and non-responders to therapeutic interventions in obese children are rare. We applied fMRI before and after a one-year sports therapy in 14 obese or overweight children aged 7-16 years. During scanning, participants observed a set of standardized pictures from food categories, sports, and pleasant and neutral(More)
There exist all kinds of problems where both input and output data for neural networks are continuous and vector-valued. From our previous works we know that distributed representations of the input data are extremely useful for neural networks to embody good generalization skills and also to model forbidden regions in data space. Units are only located in(More)
PURPOSE To evaluate three automated devices for measuring the erythrocyte sedimentation rate (ESR) (VES-MATIC 60, Menarini(R); SEDISCAN Becton-Dickinson(R) y SEDIMATIC, Ral(R)) by comparison with the Westergren method (WM). MATERIAL AND METHODS A total of 1576 whole blood samples (VM: 694, SC: 316 and SM: 566) from patients of the Hospital Clínic i(More)
  • 1