Abstract: 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.

Abstract: Some embodiments provide a method for processing a video that includes a sequence of images using a neural network. The method receives a set of video images as a set of inputs to successive executions of the neural network. The method executes the neural network for each successive video image of the set of video images to reduce an amount of noise in the video image by (i) identifying spatial features of the video image and (ii) storing a set of state data representing identified spatial features for use in identifying spatial features of subsequent video images in the set of video images. Identifying spatial features of a particular video image includes using the stored sets of spatial features of video images previous to the particular video image.

Abstract: Some embodiments provide a method for configuring a machine-trained (MT) network that includes input nodes, output nodes, and interior nodes between the input and output nodes. Each node produces an output value and each interior node and output node receives as input values a set of output values of other nodes and applies weights to each received input value. The weights are configurable parameters for training. The method propagates a set of inputs through the MT network to generate a set of outputs. Each input has a corresponding expected output. The method calculates a value of a continuously-differentiable augmented loss function that combines a measurement of a difference between each output and its corresponding expected output and a term that biases training of the weights towards a set of discrete values. The method trains the weights by backpropagating a gradient of the continuously-differentiable augmented loss function at the calculated value.

Abstract: Some embodiments provide a set of processing units and a set of machine-readable media. The set of machine-readable media stores sets of instructions for applying a network of computation nodes to an input received by the device. The network of computation nodes includes multiple layers of nodes. The set of machine-readable media stores a set of machine-trained weight parameters for configuring the network to perform a specific function. Each layer of nodes has an associated value, and each of the weight parameters is associated with a computation node. Each weight parameter is zero, the associated value for the layer of the computation node with which the weight parameter is associated, or the negative of the associated value for the layer of the computation node with which the weight parameter is associated. Each weight value is stored using two bits or less of data.

Abstract: Some embodiments of the invention provide a novel method for training a quantized machine-trained network. Some embodiments provide a method of scaling a feature map of a pre-trained floating-point neural network in order to match the range of output values provided by quantized activations in a quantized neural network. A quantization function is modified, in some embodiments, to be differentiable to fix the mismatch between the loss function computed in forward propagation and the loss gradient used in backward propagation. Variational information bottleneck, in some embodiments, is incorporated to train the network to be insensitive to multiplicative noise applied to each channel. In some embodiments, channels that finish training with large noise, for example, exceeding 100%, are pruned.

Abstract: Some embodiments of the invention provide a novel method for training a quantized machine-trained network. Some embodiments provide a method of scaling a feature map of a pre-trained floating-point neural network in order to match the range of output values provided by quantized activations in a quantized neural network. A quantization function is modified, in some embodiments, to be differentiable to fix the mismatch between the loss function computed in forward propagation and the loss gradient used in backward propagation. Variational information bottleneck, in some embodiments, is incorporated to train the network to be insensitive to multiplicative noise applied to each channel. In some embodiments, channels that finish training with large noise, for example, exceeding 100%, are pruned.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: Whiteboard contents are captured through a combination of hardware and software components such as a webcam and a capture application executed in a PC or a video conference system components. The captured content can be stored, used in an online meeting, processed, made available or transmitted to participants and others.

Abstract: A system and method of determining paths of components when placing and routing configurable circuits. The method identifies a probabilistic data flow through multiple components using a simplified connection matrix. The simplified connection matrix is used to determine a probabilistic data flow through the components without data flowing from any component to itself. The probabilistic data flow is used to determine a probabilistic data flow through the components with some of the components having data flowing from themselves back to themselves. The probabilistic data flow through each component and the number of inputs of the components are used to determine a cost for each component. The cost of a path through the circuit is determined from the costs of the individual components in the path. The costs of the components are used to determine which path of components to use.

Abstract: A system and method of determining paths of components when placing and routing configurable circuits. The method identifies a probabilistic data flow through multiple components using a simplified connection matrix. The simplified connection matrix is used to determine a probabilistic data flow through the components without data flowing from any component to itself. The probabilistic data flow is used to determine a probabilistic data flow through the components with some of the components having data flowing from themselves back to themselves. The probabilistic data flow through each component and the number of inputs of the components are used to determine a cost for each component. The cost of a path through the circuit is determined from the costs of the individual components in the path. The costs of the components are used to determine which path of components to use.

Abstract: A system and method of determining paths of components when placing and routing configurable circuits. The method identifies a probabilistic data flow through multiple components using a simplified connection matrix. The simplified connection matrix is used to determine a probabilistic data flow through the components without data flowing from any component to itself. The probabilistic data flow is used to determine a probabilistic data flow through the components with some of the components having data flowing from themselves back to themselves. The probabilistic data flow through each component and the number of inputs of the components are used to determine a cost for each component. The cost of a path through the circuit is determined from the costs of the individual components in the path. The costs of the components are used to determine which path of components to use.

Abstract: A system and method of determining paths of components when placing and routing configurable circuits. The method identifies a probabilistic data flow through multiple components using a simplified connection matrix. The simplified connection matrix is used to determine a probabilistic data flow through the components without data flowing from any component to itself. The probabilistic data flow is used to determine a probabilistic data flow through the components with some of the components having data flowing from themselves back to themselves. The probabilistic data flow through each component and the number of inputs of the components are used to determine a cost for each component. The cost of a path through the circuit is determined from the costs of the individual components in the path. The costs of the components are used to determine which path of components to use.

Abstract: Presence information within a meeting room is detected and published to users for managing room availability and real time status. Various means such as motion detectors, card readers, log-in mechanisms associated with in-room computers, and the like, are used to detect presence information. Different status indicators are assigned to each room and published through a communication application or hosted service providing useful and real time information to users.

Abstract: Presence information within a meeting room is detected and published to users for managing room availability and real time status. Various means such as motion detectors, card readers, log-in mechanisms associated with in-room computers, and the like, are used to detect presence information. Different status indicators are assigned to each room and published through a communication application or hosted service providing useful and real time information to users.

Abstract: Whiteboard contents are captured through a combination of hardware and software components such as a webcam and a capture application executed in a PC or a video conference system components. The captured content can be stored, used in an online meeting, processed, made available or transmitted to participants and others.

Abstract: A repeatable non-uniform segmented routing architecture in a field programmable gate array comprising: a repeatable block of routing tracks, the routing tracks grouped into sets of routing tracks, each set having a first routing track in a first track position, a second routing track in a last track position, a programmable element, and a direct address device for programming the programmable element; wherein at least one of the routing tracks is segmented into non-uniform lengths by the programmable element and the second routing track crosses-over to the first track position in a region adjacent to an edge of the repeatable block; and wherein a first plurality of the routing track sets proceed in a horizontal direction and a second plurality of the routing track sets proceed in a vertical direction.

Abstract: A repeatable non-uniform segmented routing architecture in a field programmable gate array comprising: a repeatable block of routing tracks, the routing tracks grouped into sets of routing tracks, each set having a first routing track in a first track position, a second routing track in a last track position, a programmable element, and a direct address device for programming the programmable element; wherein at least one of the routing tracks is segmented into non-uniform lengths by the programmable element and the second routing track crosses-over to the first track position in a region adjacent to an edge of the repeatable block; and wherein a first plurality of the routing track sets proceed in a horizontal direction and a second plurality of the routing track sets proceed in a vertical direction.

Abstract: A repeatable non-uniform segmented routing architecture in a field programmable gate array comprising: a repeatable block of routing tracks, the routing tracks grouped into sets of routing tracks, each set having a first routing track in a first track position, a second routing track in a last track position, a programmable element, and a direct address device for programming the programmable element; wherein at least one of the routing tracks is segmented into non-uniform lengths by the programmable element and the second routing track crosses-over to the first track position in a region adjacent to an edge of the repeatable block; and wherein a first plurality of the routing track sets proceed in a horizontal direction and a second plurality of the routing track sets proceed in a vertical direction.