Abstract: Methods and apparatuses for compression of feature tensors of a neural network are provided. One or more encoding parameters for encoding the channels of a feature tensor are selected according to the importance of the channels. This enables unequal bit allocation according to the importance. Furthermore, the deployed neural network may be trained or fine-tuned considering the effect of encoding noise applied to the intermediate feature tensors. According to the present disclosure, the encoding and modified training methods are advantageous at least for employment in a collaborative intelligence framework.

Abstract: The present disclosure relates to methods and apparatuses for modifying a quantizer. In particular, within a preliminary set of quantization levels, at least one quantization level is modified based on optimization involving distortion for a predetermined set of input values. At least one another quantization level out of the preliminary set is not modified. The not modified (non-modifiable) quantization level is the minimum clipping value or the maximum clipping value. The modification may facilitate increasing the dynamic range of the quantized/inverse-quantized data. Such modified quantizer may be advantageous for employment in neural networks to compress their data such as feature maps or the like. It may improve accuracy of the neural network.

Abstract: The present disclosure relates to scalable encoding and decoding of pictures. In particular, a picture is processed by one or more network layers of a trained module to obtain base layer features. Then, enhancement layer features are obtained, e.g. by a trained network processing in sample domain. The base layer features are for use in computer vision processing. The base layer features together with enhancement layer features are for use in picture reconstruction, e.g. for human vision. The base layer features and the enhancement layer features are coded in a respective base layer bitstream and an enhancement layer bitstream. Accordingly, a scalable coding is provided which supports computer vision processing and/or picture reconstruction.

Abstract: Systems and methods for dynamic management of energy usage in local grids are provided. An example method is performed by a load distribution controller coupled to a power source and an energy storage device configured to accumulate power. The method includes acquiring reference levels of using energy of the power source at time slots within a time period and cost values corresponding to the reference levels, dynamically determining, based on the reference levels and the cost values, a schedule indicating charge levels of the energy storage device at the time slots within the time period, and configuring the energy storage device to charge or discharge the power the power according to the schedule. The reference levels are obtained using the Viterbi algorithm based on costs of the energy of power source at past times slots of a past time period and rates of charging and discharging the energy storage device.

Abstract: A method and system for digitally coloring, compositing, selecting, or segmenting, anti-aliased or grayscale or multi-color line art or graphics, uses a set of acquired “image points” with properties such as coordinates, color, “paint” and “flow” status, etc. According to preferred embodiments of the invention, “unpainted” and “painted” “image points” are acquired by a processing device, which iterates through an ordered set of “reference colors”, in descending order. For each “reference color”, the device determines “unpainted image points” for which: the point's color is “greater than or equal to” the current “reference color”, except for “lesser flow” or “list” status, and: the point is “threshold adjacent” to a “painted image point”. The point's status thus changes to “painted”, and the point takes the color or “segment affiliation” of the “threshold adjacent” point, with optional prioritization. The user can adjust “image point” properties, e.g. when performing color flatting.

Abstract: A method and system for arbitrary-resolution and parallelizable data processing, reconstruction, and deconstruction, uses arbitrary frequency-space (FS) or inverse frequency-space (IFS, such as image, audio, or video space) sample points in N dimensions. According to a preferred embodiment of the invention, a subset of optionally pre-processed and/or pre-conditioned N-dimensional FS data (or IFS data) is acquired (102) by a processing device (360), the data is optionally transformed (115) by “region scaling factors”, and the data is optionally reduced (116) in numerical significant digits. A “horizontal key” of data elements is calculated (120) on a processor (361), preferably in parallel, for each of an arbitrary set of x-coordinates in IFS (or FS). IFS “color” data (or FS data) are calculated (130) on a processor (361), preferably in parallel, at the x-coordinates corresponding to the horizontal keys.

Abstract: A method and system for arbitrary-resolution and parallelizable data processing, reconstruction, and deconstruction, uses arbitrary frequency-space (FS) or inverse frequency-space (IFS, such as image, audio, or video space) sample points in N dimensions. According to a preferred embodiment of the invention, a subset of optionally pre-processed and/or pre-conditioned N-dimensional FS data (or IFS data) is acquired (102) by a processing device (360), the data is optionally transformed (115) by “region scaling factors”, and the data is optionally reduced (116) in numerical significant digits. A “horizontal key” of data elements is calculated (120) on a processor (361), preferably in parallel, for each of an arbitrary set of x-coordinates in IFS (or FS). IFS “color” data (or FS data) are calculated (130) on a processor (361), preferably in parallel, at the x-coordinates corresponding to the horizontal keys.

Abstract: A method and system for high-resolution and parallelizable data processing, reconstruction, and deconstruction, uses arbitrary frequency-space (FS) or inverse frequency-space (IFS, such as image, audio, or video space) sample points in N dimensions. According to a preferred embodiment of the invention, a subset of optionally pre-processed and/or pre-conditioned N-dimensional FS data (or IFS data) is acquired (102) by a processing device (360), the data is optionally transformed (115) by “region scaling factors”, and the data is optionally reduced (116) in numerical significant digits. A “horizontal key” of data elements is calculated (120) on a processor (361), preferably in parallel, for each of an arbitrary set of x-coordinates in IFS (or FS). IFS “color” data (or FS data) are calculated (130) on a processor (361), preferably in parallel, at the x-coordinates corresponding to the horizontal keys.

Abstract: A method and system for high-resolution and parallelizable data processing, reconstruction, and deconstruction, uses arbitrary frequency-space (FS) or inverse frequency-space (IFS, such as image, audio, or video space) sample points in N dimensions. According to a preferred embodiment of the invention, a subset of optionally pre-processed and/or pre-conditioned N-dimensional FS data (or IFS data) is acquired (102) by a processing device (360), the data is optionally transformed (115) by “region scaling factors”, and the data is optionally reduced (116) in numerical significant digits. A “horizontal key” of data elements is calculated (120) on a processor (361), preferably in parallel, for each of an arbitrary set of x-coordinates in IFS (or FS). IFS “color” data (or FS data) are calculated (130) on a processor (361), preferably in parallel, at the x-coordinates corresponding to the horizontal keys.

Abstract: A method and system for data processing and reconstruction, uses arbitrary frequency-space or image/audio/video-space (inverse frequency-space) sample points in N dimensions. According to a preferred embodiment of the invention, a subset of optionally pre-processed and pre-conditioned N-dimensional frequency-space (or image/audio/video-space) data is acquired (102) by a processing device (360), the data is optionally transformed (115) by region scaling factors, and the data is optionally reduced (116) in numerical significant digits. A “horizontal key” of data elements is calculated (120) on a processor (361), preferably in parallel, for each of an arbitrary set of x-coordinates in image/audio/video-space (or frequency-space). Image/audio/video-space “color” data (or frequency-space data) are calculated (130) on a processor (361), preferably in parallel, at the x-coordinates corresponding to the horizontal keys.

Abstract: A method and system for data processing and reconstruction, uses arbitrary frequency-space or image/audio/video-space (inverse frequency-space) sample points in N dimensions. According to a preferred embodiment of the invention, a subset of optionally pre-processed and pre-conditioned N-dimensional frequency-space (or image/audio/video-space) data is acquired (102) by a processing device (360), the data is optionally transformed (115) by region scaling factors, and the data is optionally reduced (116) in numerical significant digits. A “horizontal key” of data elements is calculated (120) on a processor (361), preferably in parallel, for each of an arbitrary set of x-coordinates in image/audio/video-space (or frequency-space). Image/audio/video-space “color” data (or frequency-space data) are calculated (130) on a processor (361), preferably in parallel, at the x-coordinates corresponding to the horizontal keys.

Abstract: In accordance with one embodiment, an intelligent supplemental search engine optimization tool may generate keywords relating to content based on additional content collected from one or more data sources, wherein the data sources are selected based on initial input relating to the initial content. Data sources may include one or more third-party resources. A variety of processes may be employed to recommend keywords, including frequency-based and probabilistic-based recommendation processes.