公开(公告)号：US6078938A

公开(公告)日：2000-06-20

申请号：US657471

申请日：1996-05-29

Applicant: ShaoWei Pan ,  Srinivas L. Panchumarthi ,  Ramamoorthy Srinath ,  Shay-Ping T. Wang

Inventor： ShaoWei Pan ,  Srinivas L. Panchumarthi ,  Ramamoorthy Srinath ,  Shay-Ping T. Wang

IPC: G06F17/12 ,  G06F1/02

CPC classification number: G06F17/12

Abstract: A system and method of using a computer processor (34) to generate a solution to a linear system of equations is provided. The computer processor (34) executes a Jacobi iterative technique to produce outputs representing the solution. Multiplication operations required by the iterative technique are performed using logarithmic arithmetic. With logarithmic arithmetic, a multiplication operation is accomplished using addition. For a given n.times.n matrix A, the computer processor (34) can compute an inverse matrix A.sup.-1 by repeatedly executing the iterative technique to solve n linear systems.

Abstract translation: 提供了一种使用计算机处理器（34）产生线性方程组的解的方法。 计算机处理器（34）执行Jacobi迭代技术以产生表示该解的输出。 使用对数算术执行迭代技术所需的乘法运算。 使用对数算术，使用加法来完成乘法运算。 对于给定的n×n矩阵A，计算机处理器（34）可以通过重复执行迭代技术来求解n个线性系统来计算逆矩阵A-1。

公开(公告)号：US5831872A

公开(公告)日：1998-11-03

申请号：US496122

申请日：1995-06-27

Applicant: Shao Wei Pan ,  Shay-Ping T. Wang

Inventor： Shao Wei Pan ,  Shay-Ping T. Wang

IPC: H04N7/26 ,  H04N7/30 ,  H04N7/46 ,  H04N11/04 ,  G06F5/00 ,  G06F7/00

CPC classification number: H04N19/59 ,  H04N19/132 ,  H04N19/17 ,  H04N19/527 ,  H04N19/587 ,  H04N19/86 ,  H04N11/044

Abstract: A video signal is converted into a coefficient signal for each frame in a video image. Each coefficient signal comprises block coefficient signals which represent the pixels in a pixel map block (420) in a pixel map (410) with the coefficients in a hybrid polynomial. The coefficient signal for only selected frames is transmitted to a receiving computer (130). The coefficient signals are selected based on a number of coefficients in the coefficient signal for a current frame that vary from corresponding coefficients in the coefficient signal for a sequentially previous frame.

Abstract translation: 视频信号被转换为视频图像中的每个帧的系数信号。 每个系数信号包括块系数信号，其表示像素图（410）中的像素映射块（420）中具有混合多项式中的系数的像素。 只有选择的帧的系数信号被发送到接收计算机（130）。 系数信号是根据当前帧的系数信号中的一系列系数来选择的，该系数信号随着前一帧的系数信号中的相应系数而变化。

公开(公告)号：US5724486A

公开(公告)日：1998-03-03

申请号：US517519

申请日：1995-08-21

Applicant: Shay-Ping T. Wang

Inventor： Shay-Ping T. Wang

IPC: G06N3/04 ,  G06N5/02 ,  G06F15/18

CPC classification number: G06N5/025 ,  G06N3/0427

Abstract: Polynomial processors learn expert system rules, for either business or real-time applications, to improve the robustness and speed of execution of the expert system. One or more polynomial processors are constructed which incorporate the production rules of one or more expert systems. Each polynomial processor is constructed of computing elements or neuron circuits each having only one significant processing element in the form of a multiplier. Each polynomial processor utilizes a training algorithm which does not require repetitive training and which yields a global minimum to each given set of input vectors.

Abstract translation: 多项式处理器可以为业务或实时应用程序学习专家系统规则，以提高专家系统的稳健性和执行速度。 构建一个或多个多项式处理器，其中包含一个或多个专家系统的生产规则。 每个多项式处理器由计算元件或神经元电路构成，每个运算元件或神经元电路仅具有乘法器形式的一个有效处理元件。 每个多项式处理器使用不需要重复训练并且对每个给定的输入向量集合产生全局最小值的训练算法。

公开(公告)号：US5612899A

公开(公告)日：1997-03-18

申请号：US495154

申请日：1995-06-27

Applicant: Shao W. Pan ,  Shay-Ping T. Wang ,  Nicholas M. Labun

Inventor： Shao W. Pan ,  Shay-Ping T. Wang ,  Nicholas M. Labun

IPC: G06T9/00 ,  H04N7/26 ,  H04N7/30 ,  G06F17/00

CPC classification number: H04N19/18 ,  H04N19/126 ,  H04N19/132 ,  H04N19/15 ,  H04N19/152 ,  H04N19/176 ,  H04N19/186

Abstract: A video signal is converted into compressed frame signals, each comprising a coefficient signal of block coefficient signals for each frame in a video image. Each of the block coefficient signals represents the pixels in a pixel map block (420) with the coefficients in a hybrid polynomial. The hybrid polynomial contains discrete cosine terms, a constant term separated from the discrete cosine terms, and polynomial terms extracted from the discrete cosine terms. Each block coefficient signal contains a background component representing a coefficient of the constant term, a linear component representing the coefficients of the polynomial terms, and a nonlinear component representing the coefficients of the discrete cosine terms.

Abstract translation: 视频信号被转换为压缩帧信号，每个信号包括视频图像中每帧的块系数信号的系数信号。 每个块系数信号表示具有混合多项式中的系数的像素映射块（420）中的像素。 混合多项式包含离散余弦项，与离散余弦项分离的常数项，以及从离散余弦项提取的多项式项。 每个块系数信号包含表示常数项的系数的背景分量，表示多项式项的系数的线性分量，以及表示离散余弦项的系数的非线性分量。

公开(公告)号：US5581661A

公开(公告)日：1996-12-03

申请号：US269243

申请日：1994-06-30

Applicant: Shay-Ping T. Wang

Inventor： Shay-Ping T. Wang

IPC: G06N3/063 ,  G06F15/18 ,  G06E1/00

CPC classification number: G06N3/063

Abstract: An artificial neuron, which may be implemented on an integrated circuit, has only one significant processing element in the form of an adder. Inputs are first fed through gating functions to produce gated inputs. These gated inputs are then added together to produce a sum which is added to a weight to produce the neuron output.

公开(公告)号：US5548685A

公开(公告)日：1996-08-20

申请号：US176604

申请日：1994-01-03

Applicant: Shay-Ping T. Wang

Inventor： Shay-Ping T. Wang

IPC: G06F15/18 ,  G06F17/10 ,  G06N3/063 ,  G06E1/00 ,  G06E3/00

CPC classification number: G06N3/063

Abstract: An artificial neuron, which may be implemented on an integrated circuit, has only one significant processing element in the form of an adder. Inputs are first fed through gating functions to produce gated inputs. These gated inputs are then added together to produce a sum which is added to a weight to produce the neuron output.

Abstract translation: 可以在集成电路上实现的人造神经元仅具有加法器形式的一个有效处理元件。 首先通过门控功能输入输入以产生门控输入。 然后将这些门控输入加在一起以产生加到权重以产生神经元输出的总和。

公开(公告)号：US5546302A

公开(公告)日：1996-08-13

申请号：US358426

申请日：1994-12-19

Applicant: Shay-Ping T. Wang ,  Dan Teng ,  Bruce E. Stuckman ,  David A. Hayner

Inventor： Shay-Ping T. Wang ,  Dan Teng ,  Bruce E. Stuckman ,  David A. Hayner

IPC: G05B13/04

CPC classification number: G05B13/042

Abstract: A system polynomial is determined using a plurality of system I/O data, wherein the system polynomial expresses the system output in terms of the system input, and wherein the system polynomial has r' terms including at least one linear term and at least one nonlinear term, the r' terms found using a regression subsets technique. A control polynomial is determined, the control polynomial having at least one cancellation term and at least one control term, the at least one cancellation term calculated to cancel the at least one nonlinear term of the system polynomial, and the at least one control term calculated to control the at least one linear term of the system polynomial. A control output signal is generated based on the control polynomial and the control input signal.

Abstract translation: 使用多个系统I / O数据确定系统多项式，其中系统多项式以系统输入表示系统输出，并且其中系统多项式具有包括至少一个线性项和至少一个非线性项的r'项， 使用回归子集技术发现r'项。 控制多项式被确定，所述控制多项式具有至少一个抵消项和至少一个控制项，所述至少一个抵消项被计算为抵消所述系统多项式的所述至少一个非线性项，并且所述至少一个控制项被计算 以控制系统多项式的至少一个线性项。 基于控制多项式和控制输入信号生成控制输出信号。

公开(公告)号：US5517667A

公开(公告)日：1996-05-14

申请号：US76601

申请日：1993-06-14

Applicant: Shay-Ping T. Wang

Inventor： Shay-Ping T. Wang

IPC: G06F15/18 ,  G06F7/552 ,  G06N3/04 ,  G06N3/063

CPC classification number: G06N3/063 ,  G06F7/552 ,  G06F2207/5523

Abstract: A neural network, which may be implemented either in hardware or software, is constructed of neurons or neuron circuits each having only one significant processing element in the form of a multiplier. A hidden neuron in the neural network generates an output based on the product of a plurality of functions. The neural network utilizes a training algorithm which does not require repetitive training and which yields a global minimum to each given set of input vectors.

Abstract translation: 可以以硬件或软件实现的神经网络由神经元或神经元电路构成，每个神经元或神经元电路仅具有乘法器形式的一个重要处理元件。 神经网络中的隐藏神经元基于多个功能的乘积生成输出。 神经网络利用不需要重复训练的训练算法，并且对每个给定的输入向量集合产生全局最小值。

公开(公告)号：US5509103A

公开(公告)日：1996-04-16

申请号：US253893

申请日：1994-06-03

Applicant: Shay-Ping T. Wang

Inventor： Shay-Ping T. Wang

IPC: G06N3/04 ,  G10L15/02 ,  G10L15/06 ,  G10L15/10 ,  G10L15/16 ,  G10L15/22 ,  G10L15/26 ,  G10L9/00

CPC classification number: G06K9/6287 ,  G06N3/0454 ,  G10L15/16 ,  G10L15/26 ,  G10L15/02 ,  G10L15/063 ,  G10L15/10

Abstract: A speech-recognition system for recognizing isolated words includes pre-processing circuitry for performing analog-to-digital conversion and cepstral analysis, and a plurality of neural networks which compute discriminant functions based on polynomial expansions. The system may be implemented using either hardware or software or a combination thereof. The speech wave-form of a spoken word is analyzed and converted into a sequence of data frames. The sequence of frames is partitioned into data blocks, and the data blocks are then broadcast to a plurality of neural networks. Using the data blocks, the neural networks compute polynomial expansions. The output of the neural networks is used to determine the identity of the spoken word. The neural networks utilize a matrix-inversion or alternatively a least-squares estimation training algorithm which does not require repetitive training and which yields a global minimum to each given set of training examples.

Abstract translation: 用于识别孤立词的语音识别系统包括用于执行模数转换和倒谱分析的预处理电路，以及基于多项式扩展来计算判别函数的多个神经网络。 该系统可以使用硬件或软件或其组合来实现。 口语中的语音波形被分析并转换为数据帧序列。 将帧序列划分为数据块，然后将数据块广播到多个神经网络。 使用数据块，神经网络计算多项式扩展。 神经网络的输出用于确定口语单词的身份。 神经网络利用矩阵反演或可选的最小二乘估计训练算法，其不需要重复训练，并且对每个给定的训练样本集合产生全局最小值。

公开(公告)号：US5390136A

公开(公告)日：1995-02-14

申请号：US076602

申请日：1993-06-14

Applicant: Shay-Ping T. Wang

Inventor： Shay-Ping T. Wang

IPC: G06F15/18 ,  G06F7/552 ,  G06N3/063 ,  G06N3/08 ,  G06F7/52

CPC classification number: G06F7/552 ,  G06N3/063 ,  G06F2207/5523

Abstract: An artificial neuron, which may be implemented either in hardware or software, has only one significant processing element in the form of a multiplier. Inputs are first fed through gating functions to produce gated inputs. These gated inputs are then multiplied together to produce a product which is multiplied by a weight to produce the neuron output.