Tamás Zeffer

16647583000

Publications - 3

The configurable digital cellular neural - Hopfield network

Tamás Zeffer T. Hidvégi

Publication Name: Ines 2006 10th International Conference on Intelligent Engineering Systems 2006

Publication Date: 2006-12-01

Volume: Unknown

Issue: Unknown

Page Range: 160-164

Description:

A configurable Artificial Neuron Network that is capable of establishing both the emulated digital Cellular Neural Network (CNN) and the Hopfield Network is described. The configurable neural network is designed with the method of modularity where each module is a three weighted input neuron. The network can be optionally large limited only by the gate number available on a chip. Also, the network is reconfigurable during operation. © 2006 IEEE.

Open Access: Yes

DOI: DOI not available

A programmable digital cellular neural network processing on- and off-chip sensory information

Tamás Zeffer T. Hidvégi

Publication Name: Proceedings of the IEEE International Workshop on Cellular Neural Networks and their Applications

Publication Date: 2006-12-01

Volume: Unknown

Issue: Unknown

Page Range: Unknown

Description:

In this paper, the architecture of a mixed-signal CNN visual processor with on board photodetecting sensor array analog RAM, and a switching matrix to process off chip sensor signals is proposed. In our design, the CMOS sensor array possesses high performance readout circuitry and embedded data storage capability. For further compactness, a new template memory structure is built that requires about quarter of silicon size compared to previous designs. The vision chip comprises most of the modules of a sensory system and keeps tight relationship between the sensors and the processor. © 2008 IEEE.

Open Access: Yes

DOI: 10.1109/CNNA.2006.341603

The configurable digital neural network with emulated digital cellular neural network cores

Tamás Zeffer T. Hidvégi

Publication Name: 2006 IEEE International Conference on Mechatronics Icm

Publication Date: 2006-12-01

Volume: Unknown

Issue: Unknown

Page Range: 312-315

Description:

A configurable Artificial Neuron Network that is capable of establishing both the emulated digital Cellular Neural Network (CNN) and the static Multilayered Feedforward Neural Network (MFNN) is described. The configurable neural network is designed with the method of modularity where each module is a three weighted input neuron. The network can be optionally large limited only by the gate number available on a chip. © 2006 IEEE.

Open Access: Yes

DOI: 10.1109/ICMECH.2006.252545