Abstract: A memory system may monitor a bit error rate in data read from a memory in the memory system. The memory system may determine that the monitored bit error rate satisfies an acceptable memory error condition. The memory system may adjust operation of the memory system to decrease the power consumption of the memory system, wherein the adjusted operation results in a new bit error rate monitored from data read from the memory that satisfies the acceptable memory error condition.

Abstract: This document relates to automated generation of machine learning models, such as neural networks. One example method involves obtaining a first machine learning model having one or more first inference operations. The example method also involves identifying a plurality of second inference operations that are supported by an inference hardware architecture. The example method also involves generating second machine learning models by modifying the first machine learning model to include individual second inference operations that are supported by the inference hardware architecture. The example method also involves selecting a final machine learning model from the second machine learning models based on one or more metrics.

Abstract: Methods, systems and computer program products are provided for improving performance (e.g., reducing power consumption) of a hardware accelerator (e.g., neural processor) comprising hybrid or analog multiply and accumulate (MAC) processing elements (PEs). Selective variation of the precision of an array of MAC PEs may reduce power consumption of a neural processor. Power may be conserved by dynamically controlling the precision of analog to digital (ADC) output bits for one or more MAC PEs. Dynamic control of ADC output bit precision may be based on precision information determined during training and/or post-training (e.g., quantization) of an artificial intelligence (AI) neural network (NN) model implemented by the neural processor. Precision information may include a range of dynamic precision for each of a plurality of nodes of a computation graph for the AI NN model.

Abstract: Methods, systems and computer program products are provided for improving performance (e.g., reducing power consumption) of a hardware accelerator (e.g., neural processor) comprising hybrid or analog multiply and accumulate (MAC) processing elements (PEs). Selective variation of the precision of an array of MAC PEs may reduce power consumption of a neural processor. Power may be conserved by dynamically controlling the precision of analog to digital (ADC) output bits for one or more MAC PEs. Dynamic control of ADC output bit precision may be based on precision information determined during training and/or post-training (e.g., quantization) of an artificial intelligence (AI) neural network (NN) model implemented by the neural processor. Precision information may include a range of dynamic precision for each of a plurality of nodes of a computation graph for the AI NN model.

Abstract: A laser machining device comprises a movable stage which is controlled by a stage controller. A laser produces a beam for machining and the beam is scanned over the part using a laser scanner under control of the laser scanner. The scanner controller controls the stage controller to synchronize movements of the stage with movements of the scanner. The stage may carry the part to be machined or the scanner.

Abstract: A method comprising, by first computer equipment: obtaining an input data point comprising a set of values, each being a value of a different element of an input feature vector; inputting the input data point to a first machine learning model on the first computer equipment to generate at least one associated output label based on the input data point; sending a partial data point to second computer equipment, the partial data point comprising the values of only part of the feature vector; and sending the associated label to the second computer equipment in association with the partial data point, thereby causing the second computer equipment to train a second machine learning model on the second computer equipment based on the sent part and the associated label.

Abstract: Embodiments described herein are directed to training techniques to reduce the power consumption and decrease the inference time of an NN. For example, during training, an estimate of power consumed by AMACs of a hardware accelerator on which the NN executes during inferencing is determined. The estimate is based at least on the non-zero midterms generated by the AMACs and the precision thereof. A loss function of the NN is modified such that it formulates the non-zero midterms and the precision thereof. The training forces the modified loss function to generate a sparse bit representation of the weights of the NN and to reduce the precision of the AMACs. Noise may also be injected at the output of nodes of the NN that emulates noise generated at an output of the AMACs. This enables the weights to account for the intrinsic noise that is experienced by the AMACs during inference.

Abstract: A method for assisting selection of an accommodation by an accommodation search system includes receiving user credentials from a user device; receiving trip parameters from the user device; determining a basic list of accommodations that correspond with the trip parameters; determining one or more factors that apply to each individual accommodation of the basic list of accommodations; applying a weight value to each of the one or more factors that apply to each individual accommodation of the basic list of accommodations; aggregating the weight values of the one or more factors that apply to each individual accommodation to determine an aggregate weighted score for each individual accommodation of the basic list of accommodations; sorting the basic list of accommodations into a sorted list of accommodations based on the aggregate weighted score for each individual accommodation; and providing the sorted list of accommodations to the user device for viewing by a user.

Abstract: A method for assisting selection of an accommodation by an accommodation search system includes receiving user credentials from a user device; receiving trip parameters from the user device; determining a basic list of accommodations that correspond with the trip parameters; determining one or more factors that apply to each individual accommodation of the basic list of accommodations; applying a weight value to each of the one or more factors that apply to each individual accommodation of the basic list of accommodations; aggregating the weight values of the one or more factors that apply to each individual accommodation to determine an aggregate weighted score for each individual accommodation of the basic list of accommodations; sorting the basic list of accommodations into a sorted list of accommodations based on the aggregate weighted score for each individual accommodation; and providing the sorted list of accommodations to the user device for viewing by a user.

Abstract: Methods, systems and computer program products are provided for improving performance (e.g., reducing power consumption) of a hardware accelerator (e.g., neural processor) comprising hybrid or analog multiply and accumulate (MAC) processing elements (PEs). Selective variation of the precision of an array of MAC PEs may reduce power consumption of a neural processor. Power may be conserved by dynamically controlling the precision of analog to digital (ADC) output bits for one or more MAC PEs. Dynamic control of ADC output bit precision may be based on precision information determined during training and/or post-training (e.g., quantization) of an artificial intelligence (AI) neural network (NN) model implemented by the neural processor. Precision information may include a range of dynamic precision for each of a plurality of nodes of a computation graph for the AI NN model.

Abstract: There is provided a system and method for creating a local social network, based on a user's location and a user's virtual social profile (e.g. a facebook profile, a myspace profile) on a virtual social network (e.g. facebook, myspace). The method includes the steps of: (1) associating a communication device with a user's virtual profile, (2) detecting a communication device within an interactive region, (3) extracting unique parameters of the communication device, (4) retrieving data associated with the communication device and with the user's virtual profile, and (5) initiating data transfer based on the retrieved data.

Abstract: Disclosed are methods, circuits, systems and associated computer executable code for detecting the presence of a mobile computing device in a specific area. Included are means for receiving a message from the mobile device including a coarse location indicator, determining that the received coarse location indicator is in proximity with one or more local (e.g. retailer) stations, and causing at least one of the one or more local stations to transmit a mobile device specific poling signal to the device.

Abstract: There is provided a system and method for creating a local social network, based on a user's location and a user's virtual social profile (e.g. a facebook profile, a myspace profile) on a virtual social network (e.g. facebook, myspace). The method includes the steps of: (1) associating a communication device with a user's virtual profile, (2) detecting a communication device within an interactive region, (3) extracting unique parameters of the communication device, (4) retrieving data associated with the communication device and with the user's virtual profile, and (5) initiating data transfer based on the retrieved data.

Abstract: Disclosed are methods, circuits, systems and associated computer executable code for detecting the presence of a mobile computing device in a specific area. included are means for receiving a message from the mobile device including a coarse location indicator, determining that the received coarse location indicator is in proximity with one or more local (e.g. retailer) stations, and causing at least one of the one or more local stations to transmit a mobile device specific poling signal to the device.

Abstract: A method for assisting selection of an accommodation by an accommodation search system includes receiving user credentials from a user device; receiving trip parameters from the user device; determining a basic list of accommodations that correspond with the trip parameters; determining one or more factors that apply to each individual accommodation of the basic list of accommodations; applying a weight value to each of the one or more factors that apply to each individual accommodation of the basic list of accommodations; aggregating the weight values of the one or more factors that apply to each individual accommodation to determine an aggregate weighted score for each individual accommodation of the basic list of accommodations; sorting the basic list of accommodations into a sorted list of accommodations based on the aggregate weighted score for each individual accommodation; and providing the sorted list of accommodations to the user device for viewing by a user.

Abstract: Disclosed are methods, circuits, systems and associated computer executable code for detecting the presence of a mobile computing device in a specific area. Included are means for receiving a message from the mobile device including a coarse location indicator, determining that the received coarse location indicator is in proximity with one or more local (e.g. retailer) stations, and causing at least one of the one or more local stations to transmit a mobile device specific poling signal to the device.

Abstract: A method for assisting selection of an accommodation by an accommodation search system includes receiving user credentials from a user device; receiving trip parameters from the user device; determining a basic list of accommodations that correspond with the trip parameters; determining one or more factors that apply to each individual accommodation of the basic list of accommodations; applying a weight value to each of the one or more factors that apply to each individual accommodation of the basic list of accommodations; aggregating the weight values of the one or more factors that apply to each individual accommodation to determine an aggregate weighted score for each individual accommodation of the basic list of accommodations; sorting the basic list of accommodations into a sorted list of accommodations based on the aggregate weighted score for each individual accommodation; and providing the sorted list of accommodations to the user device for viewing by a user.

Abstract: Disclosed are methods, circuits, systems and associated computer executable code for detecting the presence of a mobile computing device in a specific area. Included are means for receiving a message from the mobile device including a coarse location indicator, determining that the received coarse location indicator is in proximity with one or more local (e.g. retailer) stations, and causing at least one of the one or more local stations to transmit a mobile device specific poling signal to the device.

Abstract: Disclosed are methods, circuits, systems and associated computer executable code for detecting the presence of a mobile computing device in a specific area. Included are means for receiving a message from the mobile device including a coarse location indicator, determining that the received coarse location indicator is in proximity with one or more local (e.g. retailer) stations, and causing at least one of the one or more local stations to transmit a mobile device specific poling signal to the device.

Abstract: A plug-and-play Transient Suppression Unit (TSU) for Voltage Regulator Modules (VRMs), which comprises a bi-directional current source connected via a high voltage port and a low voltage port of the TSU in parallel to a voltage output of the VRM, adapted to immediately sink or source current supplied to a load; a detection circuit for detecting mismatches between the voltage output of the VRM to a reference steady-state voltage, which comprises a first comparator for detecting a match between the voltage output of the VRM to the reference steady-state voltage; a second comparator for detecting a mismatch between the voltage output of the VRM to a predefined threshold higher than the reference steady-state voltage; a third comparator for detecting a mismatch between the voltage output of the VRM to a predefined threshold lower than the reference steady-state voltage value; a transient response accelerator, connected via a third port of the TSU to the output compensation port of the VRM error amplifier, and ada