Abstract: A fully-connected neural network may be configured for execution by a processor as a fully-fused neural network by limiting slow global memory accesses to reading and writing inputs to and outputs from the fully-connected neural network. The computational cost of fully-connected neural networks scale quadratically with its width, whereas its memory traffic scales linearly. Modern graphics processing units typically have much greater computational throughput compared with memory bandwidth, so that for narrow, fully-connected neural networks, the linear memory traffic is the bottleneck. The key to improving performance of the fully-connected neural network is to minimize traffic to slow “global” memory (off-chip memory and high-level caches) and to fully utilize fast on-chip memory (low-level caches, “shared” memory, and registers), which is achieved by the fully-fused approach.

Abstract: A high efficiency positive Displacement Heat Machines, for applications such as engines with external heating, Internal Combustion Engines with reduced dirty emissions, heat pumps for ecology clear coolers or heaters, working with air from any source of mechanical energy, thermal processes with approximately constant pressure using an external High and Low Pressure Chambers (HPC and LPC that may be the Atmosphere) that are connecting to a Working Chamber (WC) correspondingly at the end of compression and expansion stages. The disclosed engines and heat pumps operate with displacing at least a part of the WF between said WC and HPC, without changing volume of the WC; with Pulse Pause Modulation of crankshaft speed; with remote expander for engine or compressor for heat pump. The expander or compressor are arranged without transferring mechanical work from another parts of the heat machine. The expander is used as power output from the engine, and the compressor is used as power input to the heat pump.

Abstract: The task of relevance score assignment to a set of items onto which an artificial neural network is applied is obtained by redistributing an initial relevance score derived from the network output, onto the set of items by reversely propagating the initial relevance score through the artificial neural network so as to obtain a relevance score for each item. In particular, this reverse propagation is applicable to a broader set of artificial neural networks and/or at lower computational efforts by performing same in a manner so that for each neuron, preliminarily redistributed relevance scores of a set of downstream neighbor neurons of the respective neuron are distributed on a set of upstream neighbor neurons of the respective neuron according to a distribution function.

Abstract: Method for the automatic analysis of an image of a biological sample with respect to a pathological relevance, wherein a)local features of the image are aggregated to a global feature of the image using a bag of visual word approach, b) step a) is repeated at least two times using different methods resulting in at least two bag of word feature datasets, c) computation of at least two similarity measures using the bag of word features obtained from a training image dataset and bag of word features from the image, d) the image training dataset comprising a set of visual words, classifier parameters, including kernel weights and bag of word features from the training images, e) the computation of the at least two similarity measures is subject to an adaptive computation of kernel normalization parameters and/or kernel width parameters, f) for each image one score is computed depending on the classifier parameters and kernel weights and the at least two similarity measures, the at least one score being a measure

Abstract: Method for the automatic analysis of an image (1, 11, 12, 13) of a biological sample with respect to a pathological relevance, wherein fj local features of the image (1, 11, 12, 13) are aggregated to a global feature of the image (1, 11, 12, 13) using a bag of visual word approach, g) step a) is repeated at least two times using different methods resulting in at least two bag of word feature datasets, h) computation of at least two similarity measures using the bag of word features obtained from a training image dataset and bag of word features from the image (1, 11, 12, 13) i) the image training dataset comprising a set of visual words, classifier parameters, including kernel weights and bag of word features from the training images, j) the computation of the at least two similarity measures is subject: to an adaptive computation of kernel normalization parameters and/or kernel width parameters, f) for each image (1, 11, 12, 13) one score is computed depending on the classifier parameters and kernel weights