Loading...
Please wait, while we are loading the content...
The Design of Neural Chips with Learning Capability and Silicon Retina Input and Their Applications in Image Processing$
| Content Provider | Semantic Scholar |
|---|---|
| Author | Jiang, Hongchen |
| Copyright Year | 2000 |
| Abstract | In this project, a new silicon retina structure is used to develop pre-image-processing chips with more functions such as rotating motion sensing, velocity sensing, or intelligent motion sensing. In researching of rotating motion sensor, an experimental sensor chip that can detect both the directions and angular velocities of rotating motions has been developed. The correct functions of the fabricated sensor chip have been verified through measurements. A new device structure called the neuron-bipolar junction transistor(νBJT) for the compact implementation of VLSI neural network. The νBJT neuron cell has been successfully applied to the implementation of the analog Hamming neural network. The analog Hamming network can store many sets of exemplar patterns with different gray levels. Moreover, the input patterns can be weighted or scaled to eliminate the common offsets and increase the dynamic range and the processing flexibility. With simple and compact structure and high integration capability, the proposed νBJT has a great potential in the VLSI implementation of neural network. Keywords: silicon retinaÆ pre-image-processing chipÆmotion detecting sensorÆneural networkÆ νÆHamming neural network 'mb)¬ tH Ç¿ÈÉÊOË© ̈Ì Í Ì ÍÎϬ~Ð 'K¿Ñvr@tzÒÓÔ)_b zÌ Ír°Õ{*)_b{w| FGHIÌ Ín oFGHIpqrijÖp@Sb efEЫ×!ØEÙÚr? ÛNÜ \stu v¬E3⁄4Ýefh_`K |
| File Format | PDF HTM / HTML |
| Alternate Webpage(s) | https://ir.nctu.edu.tw/bitstream/11536/94245/1/882215E009074.pdf |
| Language | English |
| Access Restriction | Open |
| Content Type | Text |
| Resource Type | Article |
