scispace - formally typeset
Search or ask a question
Institution

Zoran Corporation

About: Zoran Corporation is a based out in . It is known for research contribution in the topics: Signal & Pixel. The organization has 241 authors who have published 205 publications receiving 4901 citations.


Papers
More filters
Proceedings ArticleDOI
27 Jun 2011
TL;DR: This work describes a simple and effective remedy for the loss of interpretability of fuzzy rules by casting the posed optimization problem into a general Bolza-type optimal-control mold so as to include stage costs on top of the terminal cost.
Abstract: On-line first-order backpropagation (BP) has been widely employed for optimizing a multi-layer neural network and a fuzzy neural network. When BP is applied to a TSK fuzzy system, the interpretability of fuzzy rules may be lost. We describe a simple and effective remedy for the loss by casting the posed optimization problem into a general Bolza-type optimal-control mold so as to include stage costs on top of the terminal cost; this is what we called the (on-line) hidden-node teaching. Our on-line learning scheme turns out to be useful not only in optimizing a large model, a so-called CANFIS neuro-fuzzy modular network, but also in enhancing its generalization capacity. The fundamental concept is that each (local) expert network is supervised individually by hidden-node teaching for minimizing a stage cost while all local-expert modules are encouraged to cooperate in reducing the terminal cost simultaneously. Furthermore, we show how to construct a CANFIS modular network in order to alleviate the so-called curse of dimensionality that frequently hampers the design of fuzzy systems. In simulation, our concepts have been demonstrated in the letter recognition benchmark problem as well as in small regression and XOR-classification tasks.

2 citations

Patent
28 Mar 2006
TL;DR: In this paper, a phase sensor is configured to determine a phase value in accordance with an equalized version of the in-phase component of the signal and the out-of-phase components of the time sequence of symbols.
Abstract: A circuit is configured to receive and process a signal that includes in-phase and out-of-phase components that correspond to in-phase and out-of-phase components of a time sequence of symbols. A phase sensor in the circuit is configured to determine a phase value in accordance with an equalized version of the in-phase component of the signal and the in-phase component of the time sequence of symbols. The phase sensor is further configured to generate an approximation to the out-of-phase component of the signal in accordance with a Hilbert function of order k greater than 1. Terms in the approximation that correspond to future samples of the in-phase component of the signal are replaced with terms that correspond to past samples of an error that corresponds to a difference between samples of the in-phase component of the signal and an output from a detector.

1 citations

Patent
07 Nov 2005
TL;DR: A compact disk drive controller to control the access of information from an optical compact disk (CD) digital data storage device by a host computer using an integrated drive electronics (IDE) data bus or an industry standard architecture data bus is disclosed in this paper.
Abstract: A compact disk drive controller to control the access of information from an optical compact disk (CD) digital data storage device by a host computer using an integrated drive electronics (IDE) data bus or an industry standard architecture (ISA) data bus is disclosed. A digital signal processor (DSP) interface to the drive electronics of the CD drive, a dynamic random access memory (DRAM) controller, an error correction code (ECC) data corrector, an error detection and correction (EDC) device employing cyclical redundancy checking techniques (EDC/CRC), and a host computer interface are described.

1 citations

Patent
Ilya Romm1
17 May 2007
TL;DR: In this paper, the normalization of activity normalization parameters is used to select the proper quantization value for encoded video data that directly influences the human visual system (HVS), which is a state-of-the-art technique.
Abstract: The invention facilitates the normalization of activity normalization parameters to be used to select the proper quantization value for encoded video data that directly influences the Human Visual System (HVS).

1 citations


Authors

Showing all 241 results

Network Information
Related Institutions (5)
NEC
57.6K papers, 835.9K citations

75% related

Fujitsu
75K papers, 827.5K citations

75% related

Toshiba
83.6K papers, 1M citations

74% related

Panasonic
71.1K papers, 942.7K citations

73% related

Sony Broadcast & Professional Research Laboratories
63.8K papers, 865.6K citations

73% related

Performance
Metrics
No. of papers from the Institution in previous years
YearPapers
20142
20121
20118
201014
200919
200821