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. 发明授权

US06453389B1 Optimizing computer performance by using data compression principles to minimize a loss function 失效
标题翻译：通过使用数据压缩原理优化计算机性能，以最大限度地减少损失
公开(公告)号：US06453389B1
公开(公告)日：2002-09-17
申请号：US09340279
申请日：1999-06-25
申请人： Marcelo Weinberger , Tomas G. Rokicki , Gadiel Seroussi , Rajiv Gupta , Neri Merhav , Joesp M. Ferrandiz
发明人： Marcelo Weinberger , Tomas G. Rokicki , Gadiel Seroussi , Rajiv Gupta , Neri Merhav , Joesp M. Ferrandiz
IPC分类号： G06F1200
CPC分类号： G06F12/0862 , G06F2212/6026
摘要： The method of prefetching data into cache to minimize CPU stall time uses a rough predictor to make rough predictions about what cache lines will be needed next by the CPU. The address difference generator uses the rough prediction and the actual cache miss address to determine the address difference. The prefetch engine builds a data structure to represent address differences and weights them according to the accumulated stall time produced by the cache misses given that the corresponding address is not prefetched. This stall time is modeled as a loss function of the form: L = ∑ j = 0 n ⁢ ⁢ L ⁢ ⁢ ( x j ) L ⁢ ⁢ ( x j ) = ∑ i = 0 sl ⁡ ( j ) - 1 ⁢ ⁢ C i ⁢ ⁢ ( b j - i , x j ) The weights in the data structure change as the prefetch engine learns more information. The prefetch engine's goal is to predict the cache line needed and prefetch before the CPU requests it.
摘要翻译：将数据预取到缓存中以最小化CPU停顿时间的方法使用粗略的预测器来粗略地预测CPU将需要什么高速缓存行。地址差产生器使用粗略预测和实际高速缓存未命中地址来确定地址差异。预取引擎构建数据结构以表示地址差异，并根据缓存未命中产生的累积停顿时间来加权它们，因为相应地址未被预取。该失速时间被建模为形式的损失函数：数据结构中的权重随着预取引擎学习更多信息而改变。预取引擎的目标是在CPU请求之前预测所需的高速缓存行和预取。

2. 发明授权

US08554746B2 Multiple-source data compression 有权
标题翻译：多源数据压缩
公开(公告)号：US08554746B2
公开(公告)日：2013-10-08
申请号：US12859220
申请日：2010-08-18
申请人： Marcelo Weinberger , Raul Herman Etkin , Erik Ordenllich , Gadiel Seroussi
发明人： Marcelo Weinberger , Raul Herman Etkin , Erik Ordenllich , Gadiel Seroussi
IPC分类号： G06F17/00
CPC分类号： G06F17/30584 , H03M7/3064 , H03M7/40 , H03M7/607
摘要： One embodiment of the present invention is directed to a method for compressing data generated by multiple data sources. The method includes steps of partitioning data generated by the multiple data sources into data partitions, the data included in each data partition containing inter-data-source redundancies and, for each data partition, compressing the data in the data partition to remove the inter-data-source redundancies.
摘要翻译：本发明的一个实施例涉及一种用于压缩由多个数据源产生的数据的方法。该方法包括以下步骤：将由多个数据源生成的数据划分为数据分区，每个数据分区中包含的数据包含数据间冗余，并且对于每个数据分区，压缩数据分区中的数据，数据源冗余。

3. 发明申请

US20120047378A1 METHOD AND SYSTEM FOR LOW-POWERED DATA TRANSMISSION 有权
标题翻译：低功耗数据传输方法与系统
公开(公告)号：US20120047378A1
公开(公告)日：2012-02-23
申请号：US12859199
申请日：2010-08-18
申请人： Raul Hernan Etkin , Erik Ordentlich , Gadiel Seroussi , Marcelo Weinberger
发明人： Raul Hernan Etkin , Erik Ordentlich , Gadiel Seroussi , Marcelo Weinberger
IPC分类号： G06F1/32
CPC分类号： H04W52/0219 , H03M7/6047 , H04W52/0251 , H04W52/44 , Y02D70/00
摘要： One embodiment of the present invention is a sensor comprising one or more sensing devices, data-transmission components that transmit sensor data to a receiving component, and a processing component. The processing component executes routines to record sensing-device output as data for transmission to the receiving entity and to control the data-transmission components to transmit the data to the receiving entity. The processing component executes one or more compressing routines to compress data prior to transmission, when data compression is estimated to result in a lower power cost than transmitting uncompressed data, and controlling the data-transmission components to transmit data without compressing the data when data compression is estimated to result in a higher power cost than transmitting uncompressed data.
摘要翻译：本发明的一个实施例是一种传感器，包括一个或多个感测装置，将传感器数据传送到接收部件的数据传输部件和处理部件。处理组件执行例程以将感测设备输出记录为数据以传输到接收实体，并且控制数据传输组件将数据发送到接收实体。处理组件执行一个或多个压缩例程以在发送之前压缩数据，当估计数据压缩导致比发送未压缩数据时更低的功率成本，并且当数据压缩时控制数据传输组件传送数据而不压缩数据估计导致比传输未压缩数据更高的电力成本。

4. 发明申请

US20100278447A1 Method and system for adaptive context-embedded prediction 失效
标题翻译：自适应上下文嵌入预测的方法和系统
公开(公告)号：US20100278447A1
公开(公告)日：2010-11-04
申请号：US12387404
申请日：2009-04-30
申请人： Gadiel Seroussi , Erik Ordentlich , Marcelo Weinberger
发明人： Gadiel Seroussi , Erik Ordentlich , Marcelo Weinberger
IPC分类号： G06K9/40
CPC分类号： G06T5/002 , G06T2207/10008 , G06T2207/30176
摘要： One embodiment of the present invention is directed to an adaptive context-based predictor that predicts a value {circumflex over (x)} from a context, stored in an electronic memory, corresponding to a noisy-dataset symbol zi of a noisy dataset corrupted with noise modeled as being introduced by a noise-introducing channel. The adaptive context-based predictor is adapted according to one or more parameters that specify adaptive context-based-predictor operation, at least one of which functionally depends, or partially functionally depends, on a level of noise represented by the noise-introducing channel. The adaptive context-based predictor computes a number of intermediate values from the context, computes the predicted value {circumflex over (x)} from the intermediate values, and stores the predicted value {circumflex over (x)} in the electronic memory.
摘要翻译：本发明的一个实施例涉及一种基于自适应基于上下文的预测器，其预测存储在电子存储器中的对应于噪声数据集符号的噪声数据集符号zi的值（从（x）噪声被噪声引入通道引入。基于自适应基于上下文的预测器操作的一个或多个参数来调整自适应基于上下文的预测器，所述参数中的至少一个在功能上取决于或部分地功能地取决于由噪声引入信道表示的噪声水平。基于自适应基于上下文的预测器从上下文计算多个中间值，从中间值计算预测值{circumflex over（x）}，并将预测值{circumflex over（x）}存储在电子存储器中。

5. 发明授权

US07426457B2 FSM closure of generalized tree models 失效
标题翻译：广义树模型的FSM关闭
公开(公告)号：US07426457B2
公开(公告)日：2008-09-16
申请号：US10768904
申请日：2004-01-29
申请人： Alvaro Martin , Gadiel Seroussi , Marcelo Weinberger
发明人： Alvaro Martin , Gadiel Seroussi , Marcelo Weinberger
IPC分类号： G06F7/60 , G06F17/10 , H03M7/00
CPC分类号： H03M7/30
摘要： Use of Generalized Context Trees to assign a unique state from a finite set to any string is provided. The method optionally refines the generalized context tree into a refined generalized context tree having a finite state machine (FSM) property. Refining occurs whenever the generalized context tree does not have the finite state machine property. Alternately, a method for constructing a representation of a source usable within an FSM is provided, comprising evaluating a node comprising a suffix tail and verifying the suffix tail is included in the representation, and inserting at least one node to the representation when the suffix tail is not in the representation.
摘要翻译：使用广义上下文树将有限集中的唯一状态分配给任何字符串。该方法可选地将广义上下文树细化为具有有限状态机（FSM）属性的精化广义上下文树。每当广义上下文树不具有有限状态机属性时，就进行精炼。或者，提供了一种用于构建可用于FSM内的源的表示的方法，包括评估包括后缀尾部和验证后缀尾的节点包括在所述表示中，并且当后缀尾部插入至少一个节点到所述表示时不在代表中。

6. 发明申请

US20080075206A1 Method and system for denoising a noisy signal generated by an impulse channel 有权
标题翻译：用于去噪由脉冲信道产生的噪声信号的方法和系统
公开(公告)号：US20080075206A1
公开(公告)日：2008-03-27
申请号：US11527062
申请日：2006-09-25
申请人： Erik Ordentlich , Ignaclo Ramirez , Gadiel Seroussi , Marcelo Weinberger
发明人： Erik Ordentlich , Ignaclo Ramirez , Gadiel Seroussi , Marcelo Weinberger
IPC分类号： H03D1/04
CPC分类号： H04N19/90 , H04N19/86
摘要： In various embodiments of the present invention, a binary mask corresponding to a noisy symbol sequence is produced to indicate which of the symbols in the noisy symbol sequence has potentially been modified, or altered, by a noisy channel. DUDE, DUDE-CTI, and other denoising methods are modified to employ the bit mask in order to avoid the computational overhead and potential errors incurred in attempting to denoise symbols that are not likely to have been altered by the noisy channel.
摘要翻译：在本发明的各种实施例中，产生对应于噪声符号序列的二进制掩码，以指示有噪声符号序列中的哪些符号可能被噪声信道修改或改变。 DUDE，DUDE-CTI和其他去噪方法被修改为采用位掩码，以避免在尝试去噪噪声信道不太可能改变的符号时产生的计算开销和潜在错误。

7. 发明授权

US07013378B2 Method and system for minimizing the length of a defect list for a storage device 有权
标题翻译：用于最小化存储设备的缺陷列表的长度的方法和系统
公开(公告)号：US07013378B2
公开(公告)日：2006-03-14
申请号：US10427526
申请日：2003-04-30
申请人： Giovanni Motta , Erik Ordentlich , Gadiel Seroussi , Marcelo Weinberger
发明人： Giovanni Motta , Erik Ordentlich , Gadiel Seroussi , Marcelo Weinberger
IPC分类号： G06F12/16
CPC分类号： G11C29/40 , G11C29/802 , G11C2029/1208 , G11C2029/4402
摘要： A number of methods and systems for efficiently storing defective-memory-location tables. A asymmetrical-distortion-model vector quantization method and a run-length quantization method for compressing a defective-memory-location bit map that identifies defective memory locations within a memory are provided. In addition, because various different compression/decompression methods may be suitable for different types of defect distributions within a memory, a method is provided to select the most appropriate compression/decompression method from among a number of compression/decompression methods as most appropriate for a particular defect probability distribution. Finally, bit-map compression and the figure-of-merit metric for selecting an appropriate compression technique may enable global optimization of error-correcting codes and defective memory-location identification.
摘要翻译：用于有效地存储缺陷存储器位置表的一些方法和系统。提供了用于压缩识别存储器内的不良存储器位置的缺陷存储器位置位图的非对称失真模型向量量化方法和游程长度量化方法。此外，由于各种不同的压缩/解压缩方法可能适合于存储器内的不同类型的缺陷分布，所以提供了一种方法来从多个压缩/解压缩方法中选择最合适的压缩/解压缩方法，最适合于特定缺陷概率分布。最后，位图压缩和用于选择适当压缩技术的品质因数度量可以实现误差校正码和缺陷存储器位置识别的全局优化。

8. 发明授权

US08437571B2 Method and system for adaptive context-embedded prediction 失效
标题翻译：自适应上下文嵌入预测的方法和系统
公开(公告)号：US08437571B2
公开(公告)日：2013-05-07
申请号：US12387404
申请日：2009-04-30
申请人： Gadiel Seroussi , Erik Ordentlich , Marcelo Weinberger
发明人： Gadiel Seroussi , Erik Ordentlich , Marcelo Weinberger
IPC分类号： G06K9/40 , G06K9/46 , H04N7/12
CPC分类号： G06T5/002 , G06T2207/10008 , G06T2207/30176
摘要： One embodiment of the present invention is directed to an adaptive context-based predictor that predicts a value {circumflex over (x)} from a context, stored in an electronic memory, corresponding to a noisy-dataset symbol zi of a noisy dataset corrupted with noise modeled as being introduced by a noise-introducing channel. The adaptive context-based predictor is adapted according to one or more parameters that specify adaptive context-based-predictor operation, at least one of which functionally depends, or partially functionally depends, on a level of noise represented by the noise-introducing channel. The adaptive context-based predictor computes a number of intermediate values from the context, computes the predicted value {circumflex over (x)} from the intermediate values, and stores the predicted value {circumflex over (x)} in the electronic memory.
摘要翻译：本发明的一个实施例涉及一种基于自适应基于上下文的预测器，其预测存储在电子存储器中的对应于噪声数据集符号的噪声数据集符号zi的值（从（x）噪声被噪声引入通道引入。基于自适应基于上下文的预测器操作的一个或多个参数来调整自适应基于上下文的预测器，所述参数中的至少一个在功能上取决于或部分地功能地取决于由噪声引入信道表示的噪声水平。基于自适应基于上下文的预测器从上下文计算多个中间值，从中间值计算预测值{circumflex over（x）}，并将预测值{circumflex over（x）}存储在电子存储器中。

9. 发明申请

US20110299455A1 COMPRESSING DATA IN A WIRELESS MULTI-HOP NETWORK 有权
标题翻译：在无线多路网络中压缩数据
公开(公告)号：US20110299455A1
公开(公告)日：2011-12-08
申请号：US12792515
申请日：2010-06-02
申请人： Erik Ordentlich , Gadiel Seroussi , Marcelo Weinberger , Raul Heman Etkin
发明人： Erik Ordentlich , Gadiel Seroussi , Marcelo Weinberger , Raul Heman Etkin
IPC分类号： H04W40/00
CPC分类号： H04L69/04 , H04L67/12
摘要： A first node receives aggregated compressed data and unaggregated data from a second node in a wireless multi-hop network. The first node compresses its own collected data based on the received unaggregated data. The first node aggregates its own compressed data with the aggregated compressed data received from the second node. The first node forwards an unaggregated version of its own collected data along with aggregated compressed data to a next hop in the wireless multi-hop network.
摘要翻译：第一节点从无线多跳网络中的第二节点接收聚合压缩数据和未分组数据。第一个节点根据收到的未分组数据来压缩自己收集的数据。第一个节点将其自己的压缩数据与从第二个节点接收到的聚合压缩数据进行聚合。第一个节点将其自己收集的数据的集合版本与聚合的压缩数据一起转发到无线多跳网络中的下一跳。

10. 发明授权

US07592936B2 Input distribution determination for denoising 有权
标题翻译：输入分布确定去噪
公开(公告)号：US07592936B2
公开(公告)日：2009-09-22
申请号：US11590436
申请日：2006-10-30
申请人： George Gemelos , Erik Ordentlich , Gadiel Seroussi , Marcelo Weinberger
发明人： George Gemelos , Erik Ordentlich , Gadiel Seroussi , Marcelo Weinberger
IPC分类号： H03M7/00
CPC分类号： G06K9/0051
摘要： A denoising process or system uses convex optimization to determine characteristics of a clean signal. In one embodiment, a noisy signal that represents a set of symbols can be scanned to determine an empirical vector with components respectively indicating respective empirical probabilities of symbols in the noisy signal that occur in a particular context. A convex optimization process can then identify a vector such that a difference between the empirical vector and a product of the identified vector and a channel matrix is minimized. The identified vector can be used to determine when a symbol in the noisy signal should be replaced when assembling a reconstructed signal.
摘要翻译：去噪过程或系统使用凸优化来确定干净信号的特性。在一个实施例中，可以扫描表示一组符号的噪声信号以确定经验向量，其中分量分别表示在特定上下文中发生的噪声信号中的符号的相应经验概率。然后，凸优化过程可以识别向量，使得经验向量与所识别的向量与信道矩阵的乘积之间的差最小化。所识别的矢量可用于确定何时在组装重构信号时更换噪声信号中的符号。

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