Abstract: Methods and apparatus are disclosed herein for computation and compression efficiency in distributed video analytics. Example apparatus disclosed herein are to identify a key frame and a non-key frame in a video frame sequence input to a neural network at a client server, determine motion information between the key frame and the non-key frame based on optical flow, and determine a frame feature representation based on the motion information reconstructed at an edge server, the motion information including feature warping residual errors.

Abstract: One embodiment provides a graphics processor comprising a block of execution resources, a cache memory, a cache memory prefetcher, and circuitry including a programmable neural network unit, the programmable neural network unit comprising a network hardware block including circuitry to perform neural network operations and activation operations for a layer of a neural network, the programmable neural network unit addressable by cores within the block of graphics cores and the neural network hardware block configured to perform operations associated with a neural network configured to determine a prefetch pattern for the cache memory prefetcher.

Abstract: One embodiment provides for a graphics processor comprising a block of graphics compute units, a graphics processor pipeline coupled to the block of graphics compute units, and a programmable neural network unit including one or more neural network hardware blocks. The programmable neural network unit is coupled with the block of graphics compute units and the graphics processor pipeline. The one or more neural network hardware blocks include hardware to perform neural network operations and activation operations for a layer of a neural network. The programmable neural network unit can configure settings of one or more hardware blocks within the graphics processor pipeline based on a machine learning model trained to optimize performance of a set of workloads.

Abstract: Technologies for dynamic wireless noise mitigation include a computing device having a wireless modem and one or more antennas. The computing device activates one or more components of the computing device, monitors platform activity, and measures wireless noise received by the antennas. The computing device trains a noise prediction model based on the platform activity and the measured noise. The computing device may monitor platform activity and predict a noise prediction with the noise prediction model based on the monitored activity. The computing device may mitigate wireless noise received by the wireless antennas based on the noise prediction. The computing device may provide the noise prediction to the wireless modem. Other embodiments are described and claimed.

Abstract: One embodiment provides for a graphics processor comprising a block of graphics compute units, a graphics processor pipeline coupled to the block of graphics compute units, and a programmable neural network unit including one or more neural network hardware blocks. The programmable neural network unit is coupled with the block of graphics compute units and the graphics processor pipeline. The one or more neural network hardware blocks include hardware to perform neural network operations and activation operations for a layer of a neural network. The programmable neural network unit can configure settings of one or more hardware blocks within the graphics processor pipeline based on a machine learning model trained to optimize performance of a set of workloads.

Abstract: One embodiment provides for a graphics processor comprising a block of graphics compute units, a graphics processor pipeline coupled to the block of graphics compute units, and a programmable neural network unit including one or more neural network hardware blocks. The programmable neural network unit is coupled with the block of graphics compute units and the graphics processor pipeline. The one or more neural network hardware blocks include hardware to perform neural network operations and activation operations for a layer of a neural network. The programmable neural network unit can configure settings of one or more hardware blocks within the graphics processor pipeline based on a machine learning model trained to optimize performance of a set of workloads.

Abstract: Technologies for dynamic wireless noise mitigation include a computing device having a wireless modem and one or more antennas. The computing device activates one or more components of the computing device, monitors platform activity, and measures wireless noise received by the antennas. The computing device trains a noise prediction model based on the platform activity and the measured noise. The computing device may monitor platform activity and predict a noise prediction with the noise prediction model based on the monitored activity. The computing device may mitigate wireless noise received by the wireless antennas based on the noise prediction. The computing device may provide the noise prediction to the wireless modem. Other embodiments are described and claimed.

Abstract: One embodiment provides for a graphics processor comprising a block of graphics compute units, a graphics processor pipeline coupled to the block of graphics compute units, and a programmable neural network unit including one or more neural network hardware blocks. The programmable neural network unit is coupled with the block of graphics compute units and the graphics processor pipeline. The one or more neural network hardware blocks include hardware to perform neural network operations and activation operations for a layer of a neural network. The programmable neural network unit can configure settings of one or more hardware blocks within the graphics processor pipeline based on a machine learning model trained to optimize performance of a set of workloads.

Abstract: Some demonstrative embodiments include devices, systems of selectively providing Internet Protocol (IP) session continuity. In one example, a mobile device may include a radio to communicate with a wireless network, the radio to transmit a session setup request to setup a communication session, and to receive a session setup response in response to the session setup request, the session setup response including a first Internet Protocol (IP) address and a second IP address assigned to the communication session, and an indication that the first IP address is configured to maintain IP session continuity; and a controller to select to use the first IP address for the communication session, if IP session continuity is to be maintained for the communication session, and to select to use the second IP address for the communication session, if IP session continuity is not to be maintained for the communication session.

Abstract: Some demonstrative embodiments include devices, systems of selectively providing Internet Protocol (IP) session continuity. In one example, a mobile device may include a radio to communicate with a wireless network, the radio to transmit a session setup request to setup a communication session, and to receive a session setup response in response to the session setup request, the session setup response including a first Internet Protocol (IP) address and a second IP address assigned to the communication session, and an indication that the first IP address is configured to maintain IP session continuity; and a controller to select to use the first IP address for the communication session, if IP session continuity is to be maintained for the communication session, and to select to use the second IP address for the communication session, if IP session continuity is not to be maintained for the communication session.

Abstract: Techniques are described to transmit multimedia content to a mobile station using a combination of a mobile/cellular network as well as a TV Whitespace (TVWS) network. Scalable video coding can be used to transmit a baseline layer of multi-media content using the mobile/cellular network and one or more enhancement layers over the TVWS channels. Joint source-channel coding can be used to adjust the transmission scheme used by mobile/cellular and/or TVWS based on end user experience.

Abstract: Embodiments of the present invention provide for downlink resource allocation among a plurality of users. Other embodiments may be described and claimed.

Abstract: Techniques are described to transmit multimedia content to a mobile station using a combination of a mobile/cellular network as well as a TV Whitespace (TVWS) network. Scalable video coding can be used to transmit a baseline layer of multi-media content using the mobile/cellular network and one or more enhancement layers over the TVWS channels. Joint source-channel coding can be used to adjust the transmission scheme used by mobile/cellular and/or TVWS based on end user experience.

Abstract: Embodiments of the present invention provide for downlink resource allocation among a plurality of users. Other embodiments may be described and claimed.

Abstract: Embodiments of the present invention provide for downlink resource allocation among a plurality of users. Other embodiments may be described and claimed.

Abstract: Time-frequency coding in a multi-band ultra-wideband system is generally described. In this regard a hopping code agent is presented to select a frequency hopping code for encoding and decoding from a set of predetermined FHC's for communicating with other devices in a multi-band ultra-wideband (MB-UWB) network, wherein the FHC defines a sequence of two or more pulses over two or more frequencies and wherein the FHC's include a time slot that contains no transmission. Other embodiments are also disclosed and claimed.

Abstract: A sub-banded ultra-wideband (SB-UWB) system may combine aspects of an orthogonal frequency division multiplexing (OFDM) modulation scheme with aspects of an ultra-wideband system. In one embodiment, the system may use orthogonal waveforms to form an ultra-wideband wireless communications system. In another embodiment, an FFT based implementation of the system may be used to generate and detect an SB-UWB waveform.

Abstract: The performance of forward error correction decoders for digital communication systems can be improved if soft information relating the reliability of the value representing the demodulated signal is provided to the decoder with a value for the signal. On the other hand, soft information increases the quantity of information that must be processed, increasing the cost and complexity of the decoder.

Abstract: In a direct sequence spread spectrum data communication system an information bit is mixed with a pseudorandom noise or spreading code to produce modulated codeword for transmission. A method of bandwidth efficient M-ary phase shift key modulation encoding at least 16 bits of data to a single codeword is disclosed for extending the data rate of a spread spectrum system. Interoperability with legacy devices is maximized by maintaining structural similarity between the modulated waveforms of the extended data rate and legacy systems.

Abstract: In a direct sequence spread spectrum receiver an “as received” signal is decoded by correlation. Phase shift key, complementary code key modulated signals are correlated by transforming samples of the signal in a series of butterfly transform processors producing a number of correlations equal to the number of possible transmitted codewords. The largest correlation is selected as the transmitted signal. To reduce the number of processors required to transform a multi-level phase shift key signal, a correlation method and apparatus are disclosed wherein the butterfly transforms are modified with additional twiddle factors selected from a set of twiddle factors. In the alternative, the inputs to the butterfly processors of a correlator can be weighted as a function the additional twiddle factors. A set of signal samples is correlated for each combination of the set of additional twiddle factors and the largest correlation selected as the signal.