Abstract: Aspects of the technology provide improvements to a Serverless Computing (SLC) workflow by determining when and how to optimize SLC jobs for computing in a Distributed Computing Framework (DCF). DCF optimization can be performed by abstracting SLC tasks into different workflow configurations to determined optimal arrangements for execution in a DCF environment. A process of the technology can include steps for receiving an SLC job including one or more SLC tasks, executing one or more of the tasks to determine a latency metric and a throughput metric for the SLC tasks, and determining if the SLC tasks should be converted to a Distributed Computing Framework (DCF) format based on the latency metric and the throughput metric. Systems and machine-readable media are also provided.

Abstract: In one embodiment, a device forms a neural network envelope cell that comprises a plurality of convolution-based filters in series or parallel. The device constructs a convolutional neural network by stacking copies of the envelope cell in series. The device trains, using a training dataset of images, the convolutional neural network to perform image classification by iteratively collecting variance metrics for each filter in each envelope cell, pruning filters with low variance metrics from the convolutional neural network, and appending a new copy of the envelope cell into the convolutional neural network.

Abstract: Aspects of the technology provide improvements to a Serverless Computing (SLC) workflow by determining when and how to optimize SLC jobs for computing in a Distributed Computing Framework (DCF). DCF optimization can be performed by abstracting SLC tasks into different workflow configurations to determined optimal arrangements for execution in a DCF environment. A process of the technology can include steps for receiving an SLC job including one or more SLC tasks, executing one or more of the tasks to determine a latency metric and a throughput metric for the SLC tasks, and determining if the SLC tasks should be converted to a Distributed Computing Framework (DCF) format based on the latency metric and the throughput metric. Systems and machine-readable media are also provided.

Abstract: Aspects of the technology provide improvements to a Serverless Computing (SLC) workflow by determining when and how to optimize SLC jobs for computing in a Distributed Computing Framework (DCF). DCF optimization can be performed by abstracting SLC tasks into different workflow configurations to determined optimal arrangements for execution in a DCF environment. A process of the technology can include steps for receiving an SLC job including one or more SLC tasks, executing one or more of the tasks to determine a latency metric and a throughput metric for the SLC tasks, and determining if the SLC tasks should be converted to a Distributed Computing Framework (DCF) format based on the latency metric and the throughput metric. Systems and machine-readable media are also provided.

Abstract: In one embodiment, a service converts a stream of network telemetry data into sketches. The stream of network telemetry data comprises a plurality of characteristics of traffic observed in a network. The service forms a time series of the sketches. The service performs anomaly detection on the time series of the sketches in part by calculating a joint distribution of ranks and frequencies of a portion of the characteristics at different points in time of the time series. The service sends an anomaly detection alert, when an anomaly is detected from the time series of the sketches.

Abstract: Aspects of the technology provide improvements to a Serverless Computing (SLC) workflow by determining when and how to optimize SLC jobs for computing in a Distributed Computing Framework (DCF). DCF optimization can be performed by abstracting SLC tasks into different workflow configurations to determined optimal arrangements for execution in a DCF environment. A process of the technology can include steps for receiving an SLC job including one or more SLC tasks, executing one or more of the tasks to determine a latency metric and a throughput metric for the SLC tasks, and determining if the SLC tasks should be converted to a Distributed Computing Framework (DCF) format based on the latency metric and the throughput metric. Systems and machine-readable media are also provided.

Abstract: In one embodiment, a device forms a neural network envelope cell that comprises a plurality of convolution-based filters in series or parallel. The device constructs a convolutional neural network by stacking copies of the envelope cell in series. The device trains, using a training dataset of images, the convolutional neural network to perform image classification by iteratively collecting variance metrics for each filter in each envelope cell, pruning filters with low variance metrics from the convolutional neural network, and appending a new copy of the envelope cell into the convolutional neural network.

Abstract: In one embodiment, a service converts a stream of network telemetry data into sketches. The stream of network telemetry data comprises a plurality of characteristics of traffic observed in a network. The service forms a time series of the sketches. The service performs anomaly detection on the time series of the sketches in part by calculating a joint distribution of ranks and frequencies of a portion of the characteristics at different points in time of the time series. The service sends an anomaly detection alert, when an anomaly is detected from the time series of the sketches.

Abstract: A method and system that allows multiple developers to collaborate together by developing, modifying and sharing code components and data which are integrated to provide a solution to a computational problem. The system enforces a sharing mechanism for the components (code and data) and an interface between components. The system allows developers to execute the components either locally or remotely. The system determines a consumption metric based on the resource consumption of each component (compute/storage/bandwidth). The system determine a contribution metric for each developer's components to the overall solution.

Abstract: A network based positioning (NBP) system is disclosed that allows any of its access points (APs) to initiate ranging operations with a station device (STA), regardless of whether the STA is in power save mode and regardless of whether a particular AP is currently associated with the STA. For example, to initiate ranging operations with the STA from a non-associated AP, the non-associated AP obtains the TSF timer of the associated AP, and then uses the obtained TSF timer to derive the associated AP's beacon transmission schedule and thereby determine when the STA's corresponding wake-up periods occur. Thereafter, the non-associated AP can initiate ranging operations with the STA during the STA wake-up periods, thereby ensuring that probes sent from the non-associated AP will arrive at the STA while the STA is awake from power save mode.

Abstract: A wireless network is disclosed that allows an access point (AP) to keep a station (STA) in an awake state for an extended duration by periodically sending “keep-awake” frames to the STA. The keep-awake frames may be NULL frames having an asserted “more data” bit. For some embodiments, the AP transmits a beacon frame to the STA, wherein the beacon frame includes an asserted traffic indication bit that causes the STA to remain in the awake state for an additional wake-up period. Then, the AP transmits a sequence of keep-awake frames to the STA, wherein each keep-awake frame causes the STA to remain in the awake state for an additional time period.

Abstract: A wireless network is disclosed that allows an access point (AP) to keep a station (STA) in an awake state for an extended duration by periodically sending “keep-awake” frames to the STA. The keep-awake frames may be NULL frames having an asserted “more data” bit. For some embodiments, the AP transmits a beacon frame to the STA, wherein the beacon frame includes an asserted traffic indication bit that causes the STA to remain in the awake state for an additional wake-up period. Then, the AP transmits a sequence of keep-awake frames to the STA, wherein each keep-awake frame causes the STA to remain in the awake state for an additional time period.

Abstract: A network based positioning (NBP) system is disclosed that allows any of its access points (APs) to initiate ranging operations with a station device (STA), regardless of whether the STA is in power save mode and regardless of whether a particular AP is currently associated with the STA. For example, to initiate ranging operations with the STA from a non-associated AP, the non-associated AP obtains the TSF timer of the associated AP, and then uses the obtained TSF timer to derive the associated AP's beacon transmission schedule and thereby determine when the STA's corresponding wake-up periods occur. Thereafter, the non-associated AP can initiate ranging operations with the STA during the STA wake-up periods, thereby ensuring that probes sent from the non-associated AP will arrive at the STA while the STA is awake from power save mode.

Abstract: The position of wireless repeaters within a wireless communication network can affect the throughput and performance of the wireless communication network. A wireless repeater and/or an access point associated with the wireless communication network can be configured to determine the optimal position of the wireless repeater based on throughput achieved on communication links between the access point, the repeater, and/or the client stations. The throughput achieved on communication links between the access point, the repeater, and/or the client stations can be determined by exchanging training packets, receiving acknowledgement messages in response to the training packets, and subsequently analyzing the received acknowledgement messages. Furthermore, the throughput achieved on communication links between the access point, the repeater, and/or the client stations can also be analyzed to determine whether each of the client stations should associate with the access point or the wireless repeater.

Abstract: Starting up and synchronizing multiple access points in a wireline communications circuit using transceivers compatible with a wireless communications protocol with an adaptive Time Division Multiple Access scheme for a multi-channel medium with colocated transceivers. Synchronization readiness is asserted and the access points wait for a synchronization start signal's assertion. Methods of operating an access point, its implementation as a chip are further disclosed. An access point assembly including the access points and a synchronization circuit are also disclosed.

Abstract: The position of wireless repeaters within a wireless communication network can affect the throughput and performance of the wireless communication network. A wireless repeater and/or an access point associated with the wireless communication network can be configured to determine the optimal position of the wireless repeater based on throughput achieved on communication links between the access point, the repeater, and/or the client stations. The throughput achieved on communication links between the access point, the repeater, and/or the client stations can be determined by exchanging training packets, receiving acknowledgement messages in response to the training packets, and subsequently analyzing the received acknowledgement messages. Furthermore, the throughput achieved on communication links between the access point, the repeater, and/or the client stations can also be analyzed to determine whether each of the client stations should associate with the access point or the wireless repeater.

Abstract: A wireline communications circuit using transceivers compatible with a wireless communications protocol is disclosed using access points and stations in an adaptive Time Division Multiple Access scheme for a multi-channel medium with colocated transceivers. Methods of operating an access point and a station, their implementations as chips and the implementation of a chip for either the access point or station are further disclosed.

Abstract: A wireline communications circuit using transceivers compatible with a wireless communications protocol is disclosed using access points and stations in an adaptive Time Division Multiple Access scheme for a multi-channel medium with colocated transceivers. Methods of operating an access point and a station, their implementations as chips and the implementation of a chip for either the access point or station are further disclosed.

Abstract: Systems and techniques to optically boost a router. In general, in one implementation, the technique includes: receiving an optical signal defining a packet of data, initiating electronic routing of the optical packet, and initiating optical routing of the optical packet. The optical routing involves determining forwarding information based on a routing field in the optical packet, and if optical forwarding is available, terminating the electronic routing of the packet before completion of the electronic routing, and forwarding the optical signal, which defines the packet, based on the determined forwarding information.