Searching for authors named "Nicolas Donckers" – sorted by Relevance.
-
Recursive learning rules for SOMs
- Introduction Self-Organizing Maps (SOMs, [1,2]) are well known in the domain of Vector Quantization (VQ). Unlike other VQ methods, the neurons (or prototypes) used for the quantization are given a position in a grid, which is often one- or two-dimensional. This predefined geometrical organization,
- Cited by 1 (1 self) – Add To MetaCart
-
Granada (Spain), 7-9 April 1999, IEEE Computer Society, ISBN 0-7695-0043-9, pp. 360 -- 365
- A novel architecture for winner-take-all (WTA) and looser-take-all (LTA) circuits is proposed. As compared with other realisations, the LTA does not require input subtraction from a reference, which decreases accuracy and input dynamics. The architectures have been designed using the g m /I D method
- Add To MetaCart
-
A Current-Mode Cmos Loser-Take-All With
- A novel architecture for loser-take-all functions is proposed. Inputs and outputs of the circuit are currents, which make the circuit appropriated for low-voltage neural hardware computation. In contrast to most existing realisations the circuit does not require subtraction from a fixed reference wh
- Add To MetaCart

