公开(公告)号：US11163986B2

公开(公告)日：2021-11-02

申请号：US16852329

申请日：2020-04-17

申请人： Perceive Corporation

发明人： Eric A. Sather ,  Steven L. Teig ,  Andrew C. Mihal

IPC分类号： G06K9/00 ,  G06T7/00 ,  G06N3/04 ,  G06N3/08 ,  G06K9/62

摘要： Some embodiments provide a method for training a machine-trained (MT) network that processes inputs using network parameters. The method propagates a set of input training items through the MT network to generate a set of output values. The set of input training items comprises multiple training items for each of multiple categories. The method identifies multiple training item groupings in the set of input training items. Each grouping includes at least two training items in a first category and at least one training item in a second category. The method calculates a value of a loss function as a summation of individual loss functions for each of the identified training item groupings. The individual loss function for each particular training item grouping is based on the output values for the training items of the grouping. The method trains the network parameters using the calculated loss function value.

公开(公告)号：US11049013B1

公开(公告)日：2021-06-29

申请号：US16457756

申请日：2019-06-28

申请人： Perceive Corporation

发明人： Kenneth Duong ,  Jung Ko ,  Steven L. Teig

IPC分类号： G06N3/08 ,  G06N3/04 ,  G06N3/063 ,  G06F17/16

摘要： Some embodiments provide a neural network inference circuit for executing a neural network that includes multiple computation nodes at multiple layers. Each of a set of the computation nodes includes a dot product of input values and weight values. The neural network inference circuit includes (i) a first set of memory units allocated to storing input values during execution of the neural network and (ii) a second set of memory units storing encoded weight value data. The weight value data is encoded such that less than one bit of memory is used per weight value of the neural network.

公开(公告)号：US10936951B1

公开(公告)日：2021-03-02

申请号：US15231789

申请日：2016-08-09

申请人： Perceive Corporation

发明人： Steven L. Teig

IPC分类号： G06N3/08

摘要： Some embodiments of the invention provide efficient, expressive machine-trained networks for performing machine learning. The machine-trained (MT) networks of some embodiments use novel processing nodes with novel activation functions that allow the MT network to efficiently define with fewer processing node layers a complex mathematical expression that solves a particular problem (e.g., face recognition, speech recognition, etc.). In some embodiments, the same activation function (e.g., a cup function) is used for numerous processing nodes of the MT network, but through the machine learning, this activation function is configured differently for different processing nodes so that different nodes can emulate or implement two or more different functions (e.g., two or more Boolean logical operators, such as XOR and AND). The activation function in some embodiments is a periodic function that can be configured to implement different functions (e.g., different sinusoidal functions).

公开(公告)号：US10863127B1

公开(公告)日：2020-12-08

申请号：US16246130

申请日：2019-01-11

申请人： Perceive Corporation

发明人： Ilyas Mohammed

IPC分类号： H04N5/374 ,  H04N5/3745 ,  H01L27/146 ,  G02B26/08

摘要： Some embodiments provide a novel compressive-sensing image capture device and a method of using data captured by the compressive-sensing image capture device. The novel compressive-sensing image capture device includes an array of sensors for detecting electromagnetic radiation. Each sensor in the sensor array has an associated mask that blocks electromagnetic radiation from portions of the sensor. In some embodiments, an array of passive masks is used to block a particular set of areas of each sensor in the sensor array. In some embodiments, the image capture device also includes an array of lenses corresponding to the sensors of the sensor array such that each sensor receives light that passes through a different lens. Some embodiments of the invention provide a dynamic mask array. In some embodiments, a novel machine trained network is provided that processes image capture data captured by the compressive-sensing image capture device to predict solutions to problems.

公开(公告)号：US10592732B1

公开(公告)日：2020-03-17

申请号：US15901459

申请日：2018-02-21

申请人： Perceive Corporation

发明人： Eric A. Sather ,  Steven L. Teig ,  Andrew C. Mihal

IPC分类号： G06K9/00 ,  G06T7/00 ,  G06N3/04 ,  G06N3/08

摘要： Some embodiments provide a method for training a machine-trained (MT) network that processes images using multiple network parameters. The method propagates a triplet of input images through the MT network to generate an output value for each of the input images. The triplet includes an anchor first image, a second image of a same category as the anchor image, and a third image of a different category as the anchor image. The method calculates a value of a loss function for the triplet that is based on a probabilistic classification of an output value for the anchor image compared to output values for the second and third images. The method uses the calculated loss function value to train the network parameters.

公开(公告)号：US12112254B1

公开(公告)日：2024-10-08

申请号：US16780843

申请日：2020-02-03

申请人： Perceive Corporation

发明人： Steven L. Teig ,  Eric A. Sather

IPC分类号： G06N3/047 ,  G06N3/048 ,  G06N3/084

CPC分类号： G06N3/047 ,  G06N3/048 ,  G06N3/084

摘要： Some embodiments provide a method for training a machine-trained (MT) network. The method uses a set of training inputs to train parameters of the MT network according to an initial loss function. The method uses a set of validation inputs to compute an error measure for the MT network as trained by the first set of training inputs. The method modifies the loss function for subsequent training of the MT network based on the computed error measure. The method uses the set of training inputs to train the parameters of the MT network according to the modified loss function.

公开(公告)号：US12008465B1

公开(公告)日：2024-06-11

申请号：US15870070

申请日：2018-01-12

申请人： Perceive Corporation

发明人： Andrew Mihal ,  Steven Teig

IPC分类号： G06N3/08 ,  G06N3/042

CPC分类号： G06N3/08 ,  G06N3/042

摘要： Some embodiments of the invention provide a novel method for training a multi-layer node network. Some embodiments train the multi-layer network using a set of inputs generated with random misalignments incorporated into the training data set. In some embodiments, the training data set is a synthetically generated training set based on a three-dimensional ground truth model as it would be sensed by a sensor array from different positions and with different deviations from ideal alignment and placement. Some embodiments dynamically generate training data sets when a determination is made that more training is required. Training data sets, in some embodiments, are generated based on training data sets for which the multi-layer node network has produced bad results.

公开(公告)号：US11995555B1

公开(公告)日：2024-05-28

申请号：US16923001

申请日：2020-07-07

申请人： Perceive Corporation

发明人： Alexandru F. Drimbarean ,  Steven L. Teig

IPC分类号： G06N3/084 ,  G06F17/16 ,  G06F18/2113 ,  G06N3/048 ,  G06N5/046 ,  G06N20/00

CPC分类号： G06N3/084 ,  G06F17/16 ,  G06F18/2113 ,  G06N3/048 ,  G06N5/046 ,  G06N20/00

摘要： Some embodiments of the invention provide a method for configuring a machine-trained (MT) network that includes multiple nodes. Each node of a set of the nodes generates an output value based on received input values and a set of configurable weights. The method propagates a set of inputs through the MT network to generate a set of outputs, with each input having a corresponding expected output. The method calculates a value of a loss function comprising (i) a first term that measures a difference between each generated output and its corresponding expected output and (ii) a second term that constrains the weights to discrete sets of allowed values and accounts for an increase in the first term due to constraining the weights to the discrete sets of values. The method uses the calculated value of the loss function to train the weights of the MT network.

公开(公告)号：US11995537B1

公开(公告)日：2024-05-28

申请号：US15921633

申请日：2018-03-14

申请人： Perceive Corporation

发明人： Eric A. Sather ,  Steven L. Teig ,  Andrew C. Mihal

IPC分类号： G06N3/08 ,  G06F11/00

CPC分类号： G06N3/08 ,  G06F11/004 ,  G06F2201/87

摘要： Some embodiments provide a method for training a machine-trained (MT) network that processes input data using network parameters. The method maps a set of input instances to a set of output values by propagating the set of input instances through the MT network. The set of input instances include input instances for each of multiple categories. The method selects multiple input instances as anchor instances. For each anchor instance, the method computes a loss function as a comparison between the output value for the anchor instance and each output value for an input instance in a different category than the anchor. The method computes a total loss function for the MT network as a sum of the loss function computed for each anchor instance. The method trains the network parameters using the computed total loss function.

公开(公告)号：US20240070225A1

公开(公告)日：2024-02-29

申请号：US18384529

申请日：2023-10-27

申请人： Perceive Corporation

发明人： Kenneth Duong ,  Jung Ko ,  Steven L. Teig

IPC分类号： G06F17/16 ,  G06N3/04 ,  G06N3/063 ,  G06N3/08 ,  G06T1/20

CPC分类号： G06F17/16 ,  G06N3/04 ,  G06N3/063 ,  G06N3/08 ,  G06T1/20 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/20224 ,  G06T2207/30201 ,  G06V40/172

摘要： Some embodiments provide an IC for implementing a machine-trained network with multiple layers. The IC includes a set of circuits to compute a dot product of (i) a first number of input values computed by other circuits of the IC and (ii) a set of predefined weight values, several of which are zero, with a weight value for each of the input values. The set of circuits includes (i) a dot product computation circuit to compute the dot product based on a second number of inputs and (ii) for each input value, at least two sets of wires for providing the input value to at least two of the dot product computation circuit inputs. The second number is less than the first number. Each input value with a corresponding weight value that is not equal to zero is provided to a different one of the dot product computation circuit inputs.