公开(公告)号：US20190325294A1

公开(公告)日：2019-10-24

申请号：US15956696

申请日：2018-04-18

Applicant: QUALCOMM Incorporated

Inventor： Rosario CAMMAROTA ,  Manu RASTOGI

IPC: G06N3/063 ,  G06N3/04

Abstract: An apparatus for operating a computational network, such as a long short term memory, is configured to compute in a first cell, an input for a cell of a next layer based on a prior hidden state and a current input. A memory state may be computed for the first cell based on a prior memory state, the prior hidden state, and the current input. The first cell outputs the computed input to the next layer cell, which may also receive a second prior memory state, a second prior hidden state. In turn, the next layer cell computes an input for a subsequent layer cell based on the second prior hidden state and the input supplied by the first cell in parallel with the first cell computing a hidden state and a memory state to be supplied to a subsequent cell in the same layer.

公开(公告)号：US20160080670A1

公开(公告)日：2016-03-17

申请号：US14853991

申请日：2015-09-14

Applicant: QUALCOMM Incorporated

Inventor： Venkat RANGAN ,  William Howard CONSTABLE ,  Xin WANG ,  Manu RASTOGI

IPC: H04N5/341 ,  H04N5/374

CPC classification number: H04N5/341 ,  G06F17/10 ,  G06K9/00 ,  G06K9/00771 ,  G06K9/6857 ,  G06N3/063 ,  H04N5/374

Abstract: A method of event-based down sampling includes receiving multiple sensor events corresponding to addresses and time stamps. The method further includes spatially down sampling the addresses based on the time stamps and the addresses. The method may also include updating a pixel value for each of the multiple sensor events based on the down sampling.

Abstract translation: 基于事件的下采样的方法包括接收与地址和时间戳对应的多个传感器事件。 该方法还包括基于时间戳和地址对地址进行空间下采样。 该方法还可以包括基于下采样来更新多个传感器事件中的每一个的像素值。

公开(公告)号：US20160078321A1

公开(公告)日：2016-03-17

申请号：US14622736

申请日：2015-02-13

Applicant: QUALCOMM INCORPORATED

Inventor： Xin WANG ,  William Howard CONSTABLE ,  Venkat RANGAN ,  Manu RASTOGI

IPC: G06K9/62 ,  G06K9/00

CPC classification number: G06K9/6267 ,  G06K9/00624 ,  G06K9/20 ,  G06K9/605

Abstract: A method of interfacing an event based processing system with a frame based processing system is presented. The method includes converting multiple events into a frame. The events may be generated from an event sensor. The method also includes inputting the frame into the frame based processing system.

Abstract translation: 提出了一种基于事件的处理系统与基于帧的处理系统接口的方法。 该方法包括将多个事件转换为帧。 事件可以从事件传感器生成。 该方法还包括将帧输入到基于帧的处理系统中。

公开(公告)号：US20160078001A1

公开(公告)日：2016-03-17

申请号：US14855351

申请日：2015-09-15

Applicant: QUALCOMM Incorporated

Inventor： Xin WANG ,  Manu RASTOGI ,  Venkat RANGAN ,  William Howard CONSTABLE

IPC: G06F17/14 ,  G06F17/16

CPC classification number: G06F17/141 ,  G06K9/20 ,  G06K9/522

Abstract: A method for computing a spatial Fourier transform for an event-based system includes receiving an asynchronous event output stream including one or more events from a sensor. The method further includes computing a discrete Fourier transform (DFT) matrix based on dimensions of the sensor. The method also includes computing an output based on the DFT matrix and applying the output to an event processor.

Abstract translation: 一种用于计算基于事件的系统的空间傅里叶变换的方法包括从传感器接收包括一个或多个事件的异步事件输出流。 该方法还包括基于传感器的尺寸计算离散傅立叶变换（DFT）矩阵。 该方法还包括基于DFT矩阵计算输出并将该输出应用于事件处理器。

公开(公告)号：US20160071005A1

公开(公告)日：2016-03-10

申请号：US14835664

申请日：2015-08-25

Applicant: QUALCOMM Incorporated

Inventor： Xin WANG ,  Young Cheul YOON ,  Manu RASTOGI

IPC: G06N3/08 ,  G06N3/04

CPC classification number: G06N3/08 ,  G06F17/15 ,  G06N3/04 ,  G06N3/049

Abstract: A method of processing asynchronous event-driven input samples of a continuous time signal, includes calculating a convolutional output directly from the event-driven input samples. The convolutional output is based on an asynchronous pulse modulated (APM) encoding pulse. The method further includes interpolating output between events.

Abstract translation: 处理连续时间信号的异步事件驱动输入样本的方法包括直接从事件驱动输入样本计算卷积输出。 卷积输出基于异步脉冲调制（APM）编码脉冲。 该方法还包括在事件之间内插输出。

公开(公告)号：US20200073636A1

公开(公告)日：2020-03-05

申请号：US16120001

申请日：2018-08-31

Applicant: QUALCOMM Incorporated

Inventor： Rosario CAMMAROTA ,  Manu RASTOGI

IPC: G06F7/523 ,  G06N3/04 ,  G06N3/08

Abstract: An integrated circuit is configured to compute multiply-accumulate (MAC) operations in convolutional neural networks. The integrated circuit includes a lookup table (LUT) configured to store multiple values. The integrated circuit also includes a compute unit. The compute unit is composed of an accumulator. The compute unit also includes a first multiplier configured to receive a first value of a padded input feature and a first weight of a filter kernel. The compute unit also includes a first selector. The first selector is configured to select an input to supply to the accumulator between an output from the first multiplier and an output from the LUT.

公开(公告)号：US20190325289A1

公开(公告)日：2019-10-24

申请号：US15956674

申请日：2018-04-18

Applicant: QUALCOMM Incorporated

Inventor： Rosario CAMMAROTA ,  Michael GOLDFARB ,  Manu RASTOGI ,  Sarang OZARDE

IPC: G06N3/04 ,  G06N5/04

Abstract: An apparatus for optimizing a computational network is configure to receive an input at a first processing component. The first processing component may include at least a first programmable processing component and a second programmable processing component. The first programmable processing component is configured to compute a first nonlinear function and the second programmable processing component is configured to compute a second nonlinear function which is different than the second nonlinear function. The computational network which may be a recurrent neural network such as a long short-term memory may be operated to generate an inference based at least in part on outputs of the first programmable processing component and the second programmable processing component.