专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

US20210201126A1 OPTOELECTRONIC COMPUTING SYSTEMS 有权
公开(公告)号：US20210201126A1
公开(公告)日：2021-07-01
申请号：US17204320
申请日：2021-03-17
申请人： Lightelligence, Inc.
发明人： Huaiyu Meng , Yelong Xu , Gilbert Hendry , Longwu Ou , Jingdong Deng , Ronald Gagnon , Cheng-Kuan Lu , Maurice Steinman , Mike Evans , Jianhua Wu , Yichen Shen
IPC分类号： G06N3/067 , G06E1/04
摘要： An optoelectronic computing system includes a first semiconductor die having a photonic integrated circuit (PIC) and a second semiconductor die having an electronic integrated circuit (EIC). The PIC includes optical waveguides, in which input values are encoded on respective optical signals carried by the optical waveguides. The PIC includes an optical copying distribution network having optical splitters. The PIC includes an array of optoelectronic circuitry sections, each receiving an optical wave from one of the output ports of the optical copying distribution network, and each optoelectronic circuitry section includes: at least one photodetector detecting at least one optical wave from the optoelectronic operation. The EIC includes electrical input ports receiving respective electrical values. The first semiconductor die and the second semiconductor die are electrically coupled in a controlled collapse chip connection, with the electrical output port of the PIC connected to one of the electrical input ports of the EIC.

2. 发明申请

US20210132906A1 CONSTRUCTION METHOD of MSD PARALLEL ADDER BASED ON TERNARY LOGIC OPERATOR 有权
公开(公告)号：US20210132906A1
公开(公告)日：2021-05-06
申请号：US17120077
申请日：2020-12-11
申请人： SHANGHAI UNIVERSITY
发明人： Yi JIN , Yunfu SHEN , Shan OUYANG , Junjie PENG , Junjie ZHANG , Hongjian WANG
IPC分类号： G06F7/505 , G06E1/04
摘要： Disclosed is a method for configuring an MSD parallel adder based on ternary logic operators. Five ternary logic operators that satisfy a sufficient condition for MSD addition are used to configure an MSD parallel adder. During the arrangement of a ternary logic operator, any method in the following may be used: each of ternary operators of n bits is reconfigured into a ternary logic operator each time, and reconfiguration is performed five times for implementation; each of ternary operators of n bits is reconfigured into two ternary logic operators having the same input each time, and reconfiguration is performed three times for implementation; each of ternary operators of n bits is reconfigured into five ternary logic operators of the same time, and reconfiguration is performed once for implementation; corresponding unreconfigurable ternary logic operators are used instead for the foregoing reconfiguration process.

3. 发明授权

US10984073B2 Dual phase matrix-vector multiplication system 有权
公开(公告)号：US10984073B2
公开(公告)日：2021-04-20
申请号：US16535619
申请日：2019-08-08
申请人： International Business Machines Corporation
发明人： Mauricio J. Serrano , Manoj Kumar , Pratap Pattnaik
IPC分类号： G06F17/16 , G06E1/04 , G06F9/38 , G06N5/02
摘要： A processor can scan a portion of a vector to identify first nonzero entries. The processor can scan another portion of the vector to identify second nonzero entries. The processor can scale a portion of a matrix using the first nonzero entries to generate first intermediate elements. The processor can scale another portion of the matrix using the second nonzero entries to generate second intermediate elements. The processor can store the first intermediate elements in a first buffer and store the second intermediate elements in a second buffer. The processor can copy a subset of the first intermediate elements from the first buffer to a memory and copy a subset of the second intermediate elements from the second buffer to the memory. The subsets of first and second intermediate elements can be aggregated to generate an output vector.

4. 发明申请

US20200272195A1 PATH-NUMBER-BALANCED UNIVERSAL PHOTONIC NETWORK 审中-公开
公开(公告)号：US20200272195A1
公开(公告)日：2020-08-27
申请号：US16799153
申请日：2020-02-24
申请人： Lightmatter, Inc.
发明人： Darius Bunandar , Martin B.Z. Forsythe , Michael Gould , Tomo Lazovich
IPC分类号： G06E1/04
摘要： Systems and methods for performing matrix operations using a path-number balanced optical network are provided. The optical network is formed as an array including active optical components and passive optical components arranged at a substantially central location of the array. The optical network includes at least NM active optical components which are used to implement a first matrix of any size N×M by embedding the first matrix in a second matrix of a larger size. The optical network performs matrix-vector and matrix-matrix operations by propagating one or more pluralities of optical signals corresponding to an input vector through the optical network.

5. 发明申请

US20200250533A1 OPTOELECTRONIC COMPUTING SYSTEMS 审中-公开
公开(公告)号：US20200250533A1
公开(公告)日：2020-08-06
申请号：US16852642
申请日：2020-04-20
申请人： Lightelligence, Inc.
发明人： Yichen Shen , Li Jing , Rumen Dangovski , Peng Xie , Huaiyu Meng , Matthew Khoury , Cheng-Kuan Lu , Ronald Gagnon , Maurice Steinman , Jianhua Wu , Arash Hosseinzadeh
IPC分类号： G06N3/08 , G06F17/16 , G06F17/14 , G06E1/04
摘要： Systems and methods that include: providing input information in an electronic format; converting at least a part of the electronic input information into an optical input vector; optically transforming the optical input vector into an optical output vector based on an optical matrix multiplication; converting the optical output vector into an electronic format; and electronically applying a non-linear transformation to the electronically converted optical output vector to provide output information in an electronic format.In some examples, a set of multiple input values are encoded on respective optical signals carried by optical waveguides. For each of at least two subsets of one or more optical signals, a corresponding set of one or more copying modules splits the subset of one or more optical signals into two or more copies of the optical signals. For each of at least two copies of a first subset of one or more optical signals, a corresponding multiplication module multiplies the one or more optical signals of the first subset by one or more matrix element values using optical amplitude modulation. For results of two or more of the multiplication modules, a summation module produces an electrical signal that represents a sum of the results of the two or more of the multiplication modules.

6. 发明申请

US20190087723A1 VARIABLE ISA VECTOR-BASED COMPACTION IN DISTRIBUTED TRAINING OF NEURAL NETWORKS 审中-公开
公开(公告)号：US20190087723A1
公开(公告)日：2019-03-21
申请号：US15710000
申请日：2017-09-20
申请人： International Business Machines Corporation
发明人： Minsik Cho , Ulrich A. Finkler
IPC分类号： G06N3/08 , G06E1/04 , G06F17/16
摘要： Using a processor and a memory at a worker machine, a gradient vector is computed corresponding to a set of weights associated with a set of nodes of a neural network instance being trained in the worker machine. In an ISA vector corresponding to the gradient vector, an ISA instruction is constructed corresponding to a gradient in a set of gradients in the gradient vector, wherein a data transmission of the ISA instruction is smaller as compared to a data transmission of the gradient. The ISA vector is transmitted from the worker machine to a parameter server, the ISA vector being responsive to one iteration of a training of the neural network instance, the ISA vector being transmitted instead of the gradient vector to reduce an amount of data transmitted from the worker machine to the parameter server for the one iteration of the training.

7. 发明申请

US20100165432A1 IMPROVEMENTS RELATNG TO OPTICAL VECTOR MATRIX MULTIPLIERS 有权
标题翻译：相对于光学矢量矩阵乘法器的改进
公开(公告)号：US20100165432A1
公开(公告)日：2010-07-01
申请号：US12087578
申请日：2008-01-11
申请人： Leslie Charles Laycock , Vincent Andrei Henderek
发明人： Leslie Charles Laycock , Vincent Andrei Henderek
IPC分类号： G06E1/04
CPC分类号： G06E1/04
摘要： Improved optical vector matrix multipliers are disclosed. The multipliers comprise: a plurality of light sources, each operable to radiate light of intensity ui; fan-out optics arranged to expand the light radiated by the light sources in one dimension; a spatial light modulator comprising a plurality of light modulating zones, each zone receiving light from one of the light sources and being operable to modulate the intensity of said received light by a factor of vij; and fan-in optics arranged to focus the modulated light onto a plurality of light detectors. The fan out optics, spatial light modulator, and fan-in optics are arranged such that an intensity of light proportional to ∑ i   u i  v ij is received at each light detector; and the fan-out optics comprise guided-wave optical components. Specific embodiments are disclosed in which the fanout optics comprise optical splitters, or a partially guiding wedge prism.
摘要翻译：公开了改进的光矢量矩阵乘法器。乘法器包括：多个光源，每个光源可操作以辐射强度为ui的光; 散热光学器件，用于在一个维度上扩展由光源辐射的光; 包括多个光调制区域的空间光调制器，每个区域接收来自所述光源之一的光，并且可操作以将所述接收的光的强度调制为因子vij; 以及布置成将调制的光聚焦到多个光检测器上的扇入光学器件。扇形光学器件，空间光调制器和扇入式光学器件被布置成使得在每个光检测器处接收与第i个照度成正比的光强度; 并且扇出光学器件包括导波光学部件。公开了具体实施例，其中扇出光学器件包括光分离器或部分引导楔形棱镜。

8. 发明授权

US07536431B2 Vector-matrix multiplication 失效
标题翻译：矢量矩阵乘法
公开(公告)号：US07536431B2
公开(公告)日：2009-05-19
申请号：US10488581
申请日：2002-09-03
申请人： Avner Goren , Aviram Sariel , Shimon Levit , Yosefa Asaf , Sergio Liberman , Benzion Sender , Tzvi Tzelnick , Yaron Hefetz , Eyal Moses , Vered Machal
发明人： Avner Goren , Aviram Sariel , Shimon Levit , Yosefa Asaf , Sergio Liberman , Benzion Sender , Tzvi Tzelnick , Yaron Hefetz , Eyal Moses , Vered Machal
IPC分类号： G06E3/00 , G06E1/04
CPC分类号： G06E1/045 , G06T1/0007
摘要： An integrated VMM (vector-matrix multiplier) module, including an electro-optical VMM component that multiplies an input vector by a matrix to produce an output vector; and an electronic VPU (vector processing unit) that processes at least one of the input and output vectors. Various error reducing mechanisms are also discussed.
摘要翻译：一个集成的VMM（矢量矩阵乘法器）模块，包括一个电光VMM分量，将一个输入矢量乘以一个矩阵，产生一个输出矢量; 以及处理输入和输出向量中的至少一个的电子VPU（向量处理单元）。还讨论了各种错误减少机制。

9. 发明授权

US07447719B2 Quantum computing method and quantum computer 有权
标题翻译：量子计算方法和量子计算机
公开(公告)号：US07447719B2
公开(公告)日：2008-11-04
申请号：US10975445
申请日：2004-10-29
申请人： Hayato Goto , Kouichi Ichimura
发明人： Hayato Goto , Kouichi Ichimura
IPC分类号： G06E1/04
CPC分类号： G06N99/002 , B82Y10/00
摘要： An (N+1) number of physical systems each having five energy levels |0>, |1>, |2>, |3>, and |4>, a qubit being expressed by |0> and |1>, are provided in an optical cavity having a cavity mode resonant with |2>-|3>, such that an N number of control systems and a target system are prepared. The target system is irradiated with light pulses resonant with |0>-|4>, |1>-|4>, and |2>-|4> to change a superposed state |c> to |2>. All of the physical systems are irradiated with light pulses resonant with |0>-|3> and |1>-|3>, and a phase of the light pulse resonant with the target system is shifted by a specific value dependent on a unitary transformation U. The target system is irradiated with light pulses resonant with |0>-|4>, |1>-|4>, and |2>-|4>, with a phase difference between them being set to a specific value dependent on the unitary transformation U, to return |2> to |c>.
摘要翻译：由| 0>和| 1>表示的量子位的每个具有五个能级的物理系统的数量（N + 1）分别为：| 0>，| 1>，| 2>，| 3>和| 4> 设置在具有与| 2> - | 3>共振的腔模式的光学腔中，使得准备N个控制系统和目标系统。用| 0> - | 4>，| 1> - | 4>和| 2> - | 4>共振的光脉冲照射目标系统，以将叠加状态c>更改为| 2>。所有的物理系统都用与光电脉冲共振的光脉冲进行照射，并且与目标系统谐振的光脉冲的相位偏移一个取决于单位的特定值用| 0> - | 4>，| 1> - | 4>和| 2> - | 4>共振的光脉冲照射目标系统，将它们之间的相位差设定为特定值依赖于酉变换U，返回| 2>到| c>。

10. 发明申请

US20080228844A1 Method of Enhancing Spectral Data 审中-公开
标题翻译：增强光谱数据的方法
公开(公告)号：US20080228844A1
公开(公告)日：2008-09-18
申请号：US10598359
申请日：2005-02-25
申请人： Jean-Marc Bohlen , Edmund Halasz
发明人： Jean-Marc Bohlen , Edmund Halasz
IPC分类号： G06F17/14 , G06E1/04 , G01J3/28
CPC分类号： G06F17/141 , G01J3/0294 , G01J3/45
摘要： A method of enhancing spectral data such as a frequency, wavelength or mass spectrum comprises applying an inverse Fourier Transform to the data in the frequency, wavelength or mass spectrum, zero-filling and, optionally, apodizing that inverse transform data, and then applying a Fourier Transform to convert the inverse data back into the frequency, wavelength or mass domain. The resultant processed spectrum provides a more accurate indication of peak location, shape and height.
摘要翻译：一种增强诸如频率，波长或质谱之类的频谱数据的方法包括对频率，波长或质谱数据中的数据进行逆傅立叶变换，零填充，以及任选地对该逆变换数据进行变迹，然后应用傅里叶变换将逆数据转换回频率，波长或质量域。所得到的加工光谱提供了峰值位置，形状和高度的更准确的指示。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式