Compression of data that permits direct reconstruction of arbitrary portions of the uncompressed data. Also, the direct reconstruction of arbitrary portions of the uncompressed data. Conventional compression is done such that decompression has to begin either at the very beginning of the data, or at particular intervals (e.g., at block boundaries—every 64 kilobytes) within the data. However, the principles described herein permit decompression to begin at any point within the compressed data, without having to decompress any prior portion of the file. Thus, the principles described herein permit random access of the compressed data. In accordance with the principles described herein, this is accomplished by using an index that correlates positions within the uncompressed data with positions within the compressed data.

A computer-executable method and system for querying sensor data of a plurality of sensors is provided. Sensor data is received that comprising sensor data values sampled by a first sensor of said plurality of sensors according to a first compressive sampling scheme. The first compressive sampling scheme can be applied by the first sensor within a sampling time window and the received sensor data corresponds to samples of a signal within the sampling time window. The sensor data is stored in a first database. A frequency decomposition of the signal is computed based on a sparsifying transform associated with the first compressive sampling scheme and the received sensor data. The frequency decomposition comprises one or more frequency components. The one or more frequency components are stored in a second database. A query is received from a client. The query specifies an event that indicates a critical signal condition of a signal. It is detected whether the event exists using the received sensor data or the one or more frequency components.

A computer-executable method and system for querying sensor data of a plurality of sensors is provided. Sensor data is received that comprising sensor data values sampled by a first sensor of said plurality of sensors according to a first compressive sampling scheme. The first compressive sampling scheme can be applied by the first sensor within a sampling time window and the received sensor data corresponds to samples of a signal within the sampling time window. The sensor data is stored in a first database. A frequency decomposition of the signal is computed based on a sparsifying transform associated with the first compressive sampling scheme and the received sensor data. The frequency decomposition comprises one or more frequency components. The one or more frequency components are stored in a second database. A query is received from a client. The query specifies an event that indicates a critical signal condition of a signal. It is detected whether the event exists using the received sensor data or the one or more frequency components.

The performance of a neural network (NN) and/or deep neural network (DNN) can limited by the number of operations being performed as well as memory data management of a NN/DNN. Using vector quantization of neuron weight values, the processing of data by neurons can be optimize the number of operations as well as memory utilization to enhance the overall performance of a NN/DNN. Operatively, one or more contiguous segments of weight values can be converted into one or more vectors of arbitrary length and each of the one or more vectors can be assigned an index. The generated indexes can be stored in an exemplary vector quantization lookup table and retrieved by exemplary fast weight lookup hardware at run time on the fly as part of an exemplary data processing function of the NN as part of an inline de-quantization operation to obtain needed one or more neuron weight values.

Provided are a method and device for storing time series data with adaptive length encoding, including: acquiring data values corresponding to timestamps according to a sequential order of timestamps; using a ratio of storage space values required to pre-store the previous n data values to storage space values required to pre-store rule information of a preset encoding rule and encoding data according to the previous n data values as a storage gain corresponding to the time at which the n-th data value is acquired; storing the rule information of the preset encoding rule and the encoding data corresponding to a previous n−1 data values when the storage gain corresponding to the time at which the n-th data value is acquired is less than that corresponding to the time at which the (n−1)-th data value is acquired.

A deep neural network (DNN) processor is configured to execute layer descriptors in layer descriptor lists. The descriptors define instructions for performing a forward pass of a DNN by the DNN processor. The layer descriptors can also be utilized to manage the flow of descriptors through the DNN module. For example, layer descriptors can define dependencies upon other descriptors. Descriptors defining a dependency will not execute until the descriptors upon which they are dependent have completed. Layer descriptors can also define a “fence,” or barrier, function that can be used to prevent the processing of upstream layer descriptors until the processing of all downstream layer descriptors is complete. The fence bit guarantees that there are no other layer descriptors in the DNN processing pipeline before the layer descriptor that has the fence to be asserted is processed.

A deep neural network (DNN) processor is configured to execute descriptors in layer descriptor lists. The descriptors define instructions for performing a pass of a DNN by the DNN processor. Several types of descriptors can be utilized: memory-to-memory move (M2M) descriptors; operation descriptors; host communication descriptors; configuration descriptors; branch descriptors; and synchronization descriptors. A DMA engine uses M2M descriptors to perform multi-dimensional strided DMA operations. Operation descriptors define the type of operation to be performed by neurons in the DNN processor and the activation function to be used by the neurons. M2M descriptors are buffered separately from operation descriptors and can be executed at soon as possible, subject to explicitly set dependencies. As a result, latency can be reduced and, consequently, the neurons can complete their processing faster. The DNN module can then be powered down earlier than it otherwise would have, thereby saving power.

An electronic device includes a coding module that determines whether a parameter of an artificial neural network is an outlier, depending on a value of the parameter and compresses the parameter by truncating a first bit of the parameter when the parameter is a non-outlier and truncating a second bit of the parameter when the parameter is the outlier, and a decoding module that decodes a compressed parameter.

An electronic device for compressing sampled data comprises a memory element and a processing element. The memory element is configured to store sampled data points and sampled times. The processing element is in electronic communication with the memory element and is configured to receive a plurality of sampled data points, a slope for each sampled data point in succession, the slope being a value of a change between the sampled data point and its successive sampled data point, and store the sampled data point in the memory element when the slope changes in value from a previous sampled data point.

Provided herein may be a memory controller having a data compressor and a method of operating the same. A storage device having improved response speed may include a memory controller that compresses data requested to be written by a host, temporarily stores a larger amount of data requested to be written in a buffer having a limited capacity, decompresses the compressed data, and provides the decompressed data to a memory device.