An exemplary computing environment having a DNN module can maintain one or more bandwidth throttling mechanisms. Illustratively, a first throttling mechanism can specify the number of cycles to wait between transactions on a cooperating fabric component (e.g., data bus). Illustratively, a second throttling mechanism can be a transaction count limiter that operatively sets a threshold of a number of transactions to be processed during a given transaction sequence and limits the number of transactions such as multiple transactions in flight to not exceed the set threshold. In an illustrative operation, in executing these two exemplary calculated throttling parameters, the average bandwidth usage and the peak bandwidth usage can be limited. Operatively, with this fabric bandwidth control, the processing units of the DNN are optimized to process data across each transaction cycle resulting in enhanced processing and lower power consumption.

Disclosed are an encoder signal sampling method and device. According to the method and device, a data frequency of the encoder is obtained, a clock frequency is determined according to the data frequency, a high-frequency clock signal is generated based on the clock frequency, an input signal of the encoder is sampled based on the high-frequency clock signal to obtain a sampled signal, and finally denoising processing is performed on the sampled signal based on a preset algorithm by a processer.

A method of encoding data values where the data values are arranged into words, each word comprising a plurality of input values and one or more padding bits. A word is encoded by determining whether more than half of bits in a portion of the word are ones, where the portion may comprise some or all of the bits of the input values in the word, and in response to determining that more than half of bits in the portion are ones, inverting all the bits in the portion and setting a corresponding padding bit to a value to indicate the inversion.

Provided is an encoding/decoding technique according to which it is possible to perform encoding with a small average bit count, even for a series of integer values with a distribution that is significantly biased to a small value, including small values that are not zero values. The present invention includes an integer encoding unit that, for an input series of non-negative values x.sub.n, n∈{1, 2, . . . , N} (hereinafter referred to as “integer series”), obtains a one-bit code with a bit value of “x” as a code corresponding to L consecutive integer values 0 included in the integer series, L being an integer that is 2 or more, and obtains a K×x.sub.n-bit or a K×x.sub.n+1-bit code that includes at least one bit value “x” and at least one bit value “y” in the first bit to the K-th bit and in which the bit values of the K×(x.sub.n−1) bits from the end are “y”, as a code corresponding to a set composed of 0 to L−1 consecutive integer values 0 included in the integer series and one integer value x.sub.n other than 0.

A method for adapting a trained neural network is provided. Input data is input to the trained neural network and a plurality of filters are applied to generate a plurality of channels of activation data. Differences between corresponding activation values in the plurality of channels of activation data are calculated and an order of the plurality of channels is determined based on the calculated differences. The neural network is adapted so that it will output channels of activation data in the determined order. The ordering of the channels of activation data is subsequently used to compress activation data values by taking advantage of a correlation between activation data values in adjacent channels.

Certain aspects of the present disclosure generally relate to wireless communications and, more particularly, to methods and apparatus for dynamic frozen polar codes, for example, for control channels. An exemplary method may be performed at the encoder. The method generally includes encoding a stream of bits using a polar code. The encoding includes selecting a first set of channel indices for encoding information bits. The encoding includes selecting a second set of the channel indices smaller than a channel index for a first information bit for encoding fixed frozen bits. The encoding includes selecting remaining channel indices for dynamic frozen (PCF) bits having values based on one or more of the information bits. The method includes transmitting the encoded stream of bits.

Methods and devices for encoding or decoding a point cloud. A bit sequence signaling an occupancy pattern for sub-volumes of a volume is coded using entropy coding. For a current sub-volume, probabilities of respective entropy coders for entropy coding the occupancy pattern may be selected based on occupancy data for a plurality of neighbouring sub-volumes of the current sub-volume and on occupancy data for subdivisions of the neighbouring sub-volumes.

The present invention provides a computer-implemented method, computer system and computer program product for data compression. According to the computer-implemented method, one or more data blocks on a data source to be replicated to a data target may be detected. Then, compression performance of a first compression dictionary may be evaluated. The first compression dictionary may be previously used to compress existing data on the data target. If the compression performance is lower than a preset performance threshold, a second compression dictionary may be generated based on the existing data on the data target. The data target may be updated based on the existing data and the one or more data blocks using the second compression dictionary.

A method of data compression in which the total size of the compressed data is determined and based on that determination, the bit depth of the input data may be reduced before the data is compressed. The bit depth that is used may be determined by comparing the calculated total size to one or more pre-defined threshold values to generate a mapping parameter. The mapping parameter is then input to a remapping element that is arranged to perform the conversion of the input data and then output the converted data to a data compression element. The value of the mapping parameter may be encoded into the compressed data so that it can be extracted and used when subsequently decompressing the data.

An apparatus for encoding directional audio coding parameters including diffuseness parameters and direction parameters includes: a parameter calculator for calculating the diffuseness parameters with a first time or frequency resolution and for calculating the direction parameters with a second time or frequency resolution; and a quantizer and encoder processor for generating a quantized and encoded representation of the diffuseness parameters and the direction parameters.