Abstract: A classification device receives sensor data from a set of sensors and generates, using a context classifier having a set of classifier model parameters, a set of raw predictions based on the received sensor data. Temporal filtering and heuristic filtering are applied to the raw predictions, producing filtered predictions. A prediction error is generated from the filtered predictions, and model parameters of the set of classifier model parameters are updated based on said prediction error. The classification device may be a wearable device.

Abstract: According to one aspect, a method for determining, for a memory allocation, placements in a memory area of data blocks generated by a neural network, comprises a development of an initial sequence of placements of blocks, each placement being selected from several possible placements, the initial sequence being defined as a candidate sequence, a development of at least one modified sequence of placements from a replacement of a given placement of the initial sequence by a memorized unselected placement, and, if the planned size of the memory area obtained by this modified sequence is less than that of the memory area of the candidate sequence, then this modified sequence becomes the candidate sequence, the placements of the blocks for the allocation being those of the placement sequence defined as a candidate sequence once each modified sequence has been developed.

Abstract: A method can be performed prior to implementation of a neural network by a processing unit. The neural network comprising a succession of layers and at least one operator applied between at least one pair of successive layers. A computational tool generates an executable code intended to be executed by the processing unit in order to implement the neural network. The computational tool generates at least one transfer function between the at least one pair of layers taking the form of a set of pre-computed values.

Abstract: A neural network classifies an input signal. For example, an accelerometer signal may be classified to detect human activity. In a first convolutional layer, two-valued weights are applied to the input signal. In a first two-valued function layer coupled at input to an output of the first convolutional layer, a two-valued function is applied. In a second convolutional layer coupled at input to an output of the first two-valued functional layer, weights of the second convolutional layer are applied. In a fully-connected layer coupled at input to an output of the second convolutional layer, two-valued weights of the fully connected layer are applied. In a second two-valued function layer coupled at input to an output of the fully connected layer, a two-valued function of the second two-valued function layer is applied. A classifier classifies the input signal based on an output signal of second two-valued function layer.

Abstract: Methods, microprocessors, and systems are provided for implementing an artificial neural network. Data buffers in virtual memory are coupled to respective processing layers in the artificial neural network. An ordered visiting sequence of layers of the artificial neural network is obtained. A virtual memory allocation schedule is produced as a function of the ordered visiting sequence of layers of the artificial neural network, the schedule including a set of instructions for memory allocation and deallocation operations applicable to the data buffers. A physical memory configuration dataset is computed as a function of the virtual memory allocation schedule for the artificial neural network, the dataset including sizes and addresses of physical memory locations for the artificial neural network.

Abstract: A computer-implemented method applies a pooling operator to an input array of data, the pooling operator having an absorbing element value and a set of pooling parameters. A size of an output buffer is computer as a function of the set of pooling parameters. The elements of the output buffer are initialized to the value of the absorbing element of the pooling operator. The output array of data is generated by, for a plurality of iterations associated with respective pooling windows: associating, as a function of the pooling parameters, elements of the input array of a pooling window with output elements of the output buffer; and combining, for each output element of the output buffer, the respective input elements associated with the output element. The combining may include determining a combination of respective elements of the output buffer with the input elements associated with the output elements.

Abstract: According to one aspect, a method for determining, for a memory allocation, placements in a memory area of data blocks generated by a neural network, comprises a development of an initial sequence of placements of blocks, each placement being selected from several possible placements, the initial sequence being defined as a candidate sequence, a development of at least one modified sequence of placements from a replacement of a given placement of the initial sequence by a memorized unselected placement, and, if the planned size of the memory area obtained by this modified sequence is less than that of the memory area of the candidate sequence, then this modified sequence becomes the candidate sequence, the placements of the blocks for the allocation being those of the placement sequence defined as a candidate sequence once each modified sequence has been developed.

Abstract: Methods, microprocessors, and systems are provided for implementing an artificial neural network. Data buffers in virtual memory are coupled to respective processing layers in the artificial neural network. An ordered visiting sequence of layers of the artificial neural network is obtained. A virtual memory allocation schedule is produced as a function of the ordered visiting sequence of layers of the artificial neural network, the schedule including a set of instructions for memory allocation and deallocation operations applicable to the data buffers. A physical memory configuration dataset is computed as a function of the virtual memory allocation schedule for the artificial neural network, the dataset including sizes and addresses of physical memory locations for the artificial neural network.

Abstract: A method can be performed prior to implementation of a neural network by a processing unit. The neural network comprising a succession of layers and at least one operator applied between at least one pair of successive layers. A computational tool generates an executable code intended to be executed by the processing unit in order to implement the neural network. The computational tool generates at least one transfer function between the at least one pair of layers taking the form of a set of pre-computed values.

Abstract: Digital image processing circuitry clusters a set of images into a set of first clusters of images and a set of unclustered images. The set of first clusters are merged, generating a set of second clusters of images. Images in the set of unclustered images are assigned to one of a cluster of the set of second clusters of images and an outlier image cluster. The clustered images may be partitioned into subclusters based on detection of objects in the images.

Abstract: A laserbeam light source is controlled to avoid light sensitive regions around the laserbeam light source. One or more laserlight-sensitive regions are identified based on images of an area around the laserbeam light source, and indications of positions corresponding to the laserlight-sensitive regions are generated. The laserbeam light source is controlled based on the indications of the positions. The laserbeam light source may be controlled to deflect a laserlight beam away from laserlight-sensitive regions, to reduce an intensity of a laserlight beam directed towards a laserlight-sensitive region, etc. Motion estimation may be used to generate the indications of positions corresponding to the laserlight-sensitive regions.

Abstract: A neural network classifies an input signal. For example, an accelerometer signal may be classified to detect human activity. In a first convolutional layer, two-valued weights are applied to the input signal. In a first two-valued function layer coupled at input to an output of the first convolutional layer, a two-valued function is applied. In a second convolutional layer coupled at input to an output of the first two-valued functional layer, weights of the second convolutional layer are applied. In a fully-connected layer coupled at input to an output of the second convolutional layer, two-valued weights of the fully connected layer are applied. In a second two-valued function layer coupled at input to an output of the fully connected layer, a two-valued function of the second two-valued function layer is applied. A classifier classifies the input signal based on an output signal of second two-valued function layer.

Abstract: A classification device receives sensor data from a set of sensors and generates, using a context classifier having a set of classifier model parameters, a set of raw predictions based on the received sensor data. Temporal filtering and heuristic filtering are applied to the raw predictions, producing filtered predictions. A prediction error is generated from the filtered predictions, and model parameters of the set of classifier model parameters are updated based on said prediction error. The classification device may be a wearable device.

Abstract: A laserbeam light source is controlled to avoid light sensitive regions around the laserbeam light source. One or more laserlight-sensitive regions are identified based on images of an area around the laserbeam light source, and indications of positions corresponding to the laserlight-sensitive regions are generated. The laserbeam light source is controlled based on the indications of the positions. The laserbeam light source may be controlled to deflect a laserlight beam away from laserlight-sensitive regions, to reduce an intensity of a laserlight beam directed towards a laserlight-sensitive region, etc. Motion estimation may be used to generate the indications of positions corresponding to the laserlight-sensitive regions.

Abstract: Human activities are classified based on activity-related data and an activity-classification model trained using a classification-equalized training data set. A classification signal is generated based on the classifications. The classification-equalized training data set, may, for example, includes a first class having a first sequence length and a number of samples N, and one or more additional classes each having a respective sequence length tj and a respective number of samples Nj determined based on the number of samples N of the first class. For example, a respective sequence length tj and a respective number of samples Nj which satisfy: (i) Nj>N, for sequence length tj; and (ii) Nj<N, for tj?1. The activity-related data may include one or more of acceleration data, orientation data, position data, and physiological data.

Abstract: Digital image processing circuitry clusters a set of images into a set of first clusters of images and a set of unclustered images. The set of first clusters are merged, generating a set of second clusters of images. Images in the set of unclustered images are assigned to one of a cluster of the set of second clusters of images and an outlier image cluster. The clustered images may be partitioned into subclusters based on detection of objects in the images.