Abstract: In an example, an apparatus comprises a plurality of execution units; and logic, at least partially including hardware logic, to determine a sub-graph of a network that can be executed in a frequency domain and apply computations in the sub-graph in the frequency domain. Other embodiments are also disclosed and claimed.

Abstract: In an example, an apparatus comprises logic, at least partially including hardware logic, to implement a lossy compression algorithm which utilizes a data transform and quantization process to compress data in a convolutional neural network (CNN) layer. Other embodiments are also disclosed and claimed.

Abstract: Technologies for optimization of machine learning training include a computing device to train a machine learning network with a training algorithm that is configured with configuration parameters. The computing device may perform many training instances in parallel. The computing device captures a time series of partial accuracy values from the training. Each partial accuracy value is indicative of machine learning network accuracy at an associated training iteration. The computing device inputs the configuration parameters to a feed-forward neural network to generate a representation and inputs the representation to a recurrent neural network. The computing device trains the feed-forward neural network and the recurrent neural network against the partial accuracy values. The computing device optimizes the feed-forward neural network and the recurrent neural network to determine optimized configuration parameters.

Abstract: Methods and systems are disclosed for dynamic detection of fraudulent client connections to a server, in which, for example, the connection is made using an internet protocol (IP) tunneling technology such as networking on a virtual private network (VPN) and making the connection via a VPN tunnel in order to obfuscate the client IP address, in which a user of a client device may employ spoofing of IP-geo location mechanisms and IP classification on the server side. Such a user may have various motivations for obfuscating the client device's geo-location by using an IP tunnel when connecting to a server such as gaining access to services that are not allowed in certain locations (e.g., certain movie and television content providers); browsing server data while maintaining a higher level of anonymity; and performing fraudulent actions on the server.

Abstract: An optimization of running time for performing a machine learning algorithm on a processor architecture may be performed and include determining a plurality of parameters to be configured in the machine learning algorithm, and initiating, in the optimization, a plurality of iterations of performance of the machine learning algorithm by the processor architecture. Each of the iterations may include detecting a running time of an immediately preceding one of the iterations, changing a value of one of the parameters used in the immediately preceding iteration to form a new set of values, where the value is changed based on the detected running time of the immediately preceding iteration and according to a downhill simplex algorithm. An optimal set of values for the parameters may be determined based on the plurality of iterations to realize a minimum running time to complete performance of the machine learning algorithm by the processor architecture.

Abstract: A method and apparatus for assigning tasks to processor cores, based on usage history, to have tasks executed at the highest frequency with the lowest power consumption are described. In one embodiment, the apparatus comprises processor cores, an interconnect coupled to the processor cores, at least one memory module coupled to the interconnect, and a task assigning module to assign a first task, based the usage history, to one processor core for execution at maximum frequency with minimum power usage in comparison to other processor cores of the plurality, the usage history being based on monitored core temperature, frequency and power usage for a first set of tasks previously executed by the plurality of processor cores.

Abstract: A method and apparatus for assigning tasks to processor cores, based on usage history, to have tasks executed at the highest frequency with the lowest power consumption are described. In one embodiment, the apparatus comprises processor cores, an interconnect coupled to the processor cores, at least one memory module coupled to the interconnect, and a task assigning module to assign a first task, based the usage history, to one processor core for execution at maximum frequency with minimum power usage in comparison to other processor cores of the plurality, the usage history being based on monitored core temperature, frequency and power usage for a first set of tasks previously executed by the plurality of processor cores.

Abstract: Examples of systems and methods for multisensory change detection are generally described herein. A method may include receiving a first set of signals from a first combination of sensors and a second set of signals from a second combination of sensors in a plurality of sensors, and determining a first distribution for the first set of signals and a second distribution for the second set of signals. The method may include estimating a divergence between the first and second distributions using the first and second combinations of sensors, a count of the plurality of sensors, and distances from a plurality of signals in the second set of signals to a first plurality of nearest neighbor signals in the first set of signals and a second plurality of nearest neighbor signals in the second set of signals. The method may include determining whether the divergence exceeds a threshold.

Abstract: Methods and systems are disclosed for dynamic detection of fraudulent client connections to a server, in which, for example, the connection is made using an internet protocol (IP) tunneling technology such as networking on a virtual private network (VPN) and making the connection via a VPN tunnel in order to obfuscate the client IP address, in which a user of a client device may employ spoofing of IP-geo location mechanisms and IP classification on the server side. Such a user may have various motivations for obfuscating the client device's geo-location by using an IP tunnel when connecting to a server such as gaining access to services that are not allowed in certain locations (e.g., certain movie and television content providers); browsing server data while maintaining a higher level of anonymity; and performing fraudulent actions on the server.

Abstract: Evaluating error sources associated with a mask involves: (i) receiving data representative of multiple images of the mask that were obtained at different exposure conditions; (ii) calculating, for multiple sub-frames of each image of the mask, values of a function of intensities of pixels of each sub-frame to provide multiple calculated values; and (iii) detecting error sources in response to calculated values and in response to sensitivities of the function to each error source.

Abstract: A method for edge detection, the method includes: obtaining an image of an area of a lithographic mask; wherein the image is generated by an optical system that is partially coherent; calculating a gradient of the image and a second derivative of the image in a direction of the gradient of the image; calculating a function that is proportional to the second derivative of the image in the direction of the gradient of the image and is inversely proportional to a ratio between a square of the gradient of the image and the image; and detecting at least one edge of at least one feature of the area in response to values of the function.

Abstract: Evaluating error sources associated with a mask involves: (i) receiving data representative of multiple images of the mask that were obtained at different exposure conditions; (ii) calculating, for multiple sub-frames of each image of the mask, values of a function of intensities of pixels of each sub-frame to provide multiple calculated values; and (iii) detecting error sources in response to calculated values and in response to sensitivities of the function to each error source.

Abstract: A method for edge detection, the method includes: obtaining an image of an area of a lithographic mask; wherein the image is generated by an optical system that is partially coherent; calculating a gradient of the image and a second derivative of the image in a direction of the gradient of the image; calculating a function that is proportional to the second derivative of the image in the direction of the gradient of the image and is inversely proportional to a ratio between a square of the gradient of the image and the image; and detecting at least one edge of at least one feature of the area in response to values of the function.