Abstract: A novel and useful system and method of improved power performance and lowered memory requirements for an artificial neural network based on packing memory utilizing several structured sparsity mechanisms. The invention applies to neural network (NN) processing engines adapted to implement mechanisms to search for structured sparsity in weights and activations, resulting in a considerably reduced memory usage. The sparsity guided training mechanism synthesizes and generates structured sparsity weights A compiler mechanism within a software development kit (SDK), manipulates structured weight domain sparsity to generate a sparse set of static weights for the NN. The structured sparsity static weights are loaded into the NN after compilation and utilized by both the structured weight domain sparsity mechanism and the structured activation domain sparsity mechanism.

Abstract: A novel and useful system and method of improved power performance and lowered memory requirements for an artificial neural network based on packing memory utilizing several structured sparsity mechanisms. The invention applies to neural network (NN) processing engines adapted to implement mechanisms to search for structured sparsity in weights and activations, resulting in a considerably reduced memory usage. The sparsity guided training mechanism synthesizes and generates structured sparsity weights A compiler mechanism within a software development kit (SDK), manipulates structured weight domain sparsity to generate a sparse set of static weights for the NN. The structured sparsity static weights are loaded into the NN after compilation and utilized by both the structured weight domain sparsity mechanism and the structured activation domain sparsity mechanism.

Abstract: A novel and useful system and method of improved power performance and lowered memory requirements for an artificial neural network based on packing memory utilizing several structured sparsity mechanisms. The invention applies to neural network (NN) processing engines adapted to implement mechanisms to search for structured sparsity in weights and activations, resulting in a considerably reduced memory usage. The sparsity guided training mechanism synthesizes and generates structured sparsity weights A compiler mechanism within a software development kit (SDK), manipulates structured weight domain sparsity to generate a sparse set of static weights for the NN. The structured sparsity static weights are loaded into the NN after compilation and utilized by both the structured weight domain sparsity mechanism and the structured activation domain sparsity mechanism.

Abstract: A novel and useful system and method of improved power performance and lowered memory requirements for an artificial neural network based on packing memory utilizing several structured sparsity mechanisms. The invention applies to neural network (NN) processing engines adapted to implement mechanisms to search for structured sparsity in weights and activations, resulting in a considerably reduced memory usage. The sparsity guided training mechanism synthesizes and generates structured sparsity weights A compiler mechanism within a software development kit (SDK), manipulates structured weight domain sparsity to generate a sparse set of static weights for the NN. The structured sparsity static weights are loaded into the NN after compilation and utilized by both the structured weight domain sparsity mechanism and the structured activation domain sparsity mechanism.

Abstract: A novel and useful artificial neural network that incorporates emphasis and focus techniques to extract more information from one or more portions of an input image compared to the rest of the image. The ANN recognizes that valuable information in an input image is typically not distributed throughout the image but rather is concentrated in one or more regions. Rather than implement CNN layers sequentially (i.e. row by row) on the input domain of each layer, the present invention leverages the fact that valuable information is focused in one or more regions of the image where it is desirable to apply more attention and for which it is desired to apply more elaborate evaluation. Precision dilution can be applied to those portions of the input image that are not the center of focus and emphasis. A spatial aware function determines the location(s) of the ears of focus and is applied to the first convolutional layer.

Abstract: A novel and useful neural network (NN) processing core adapted to implement artificial neural networks (ANNs). The NN processor is constructed from self-contained computational units organized in a hierarchical architecture. The homogeneity enables simpler management and control of similar computational units, aggregated in multiple levels of hierarchy. Computational units are designed with minimal overhead as possible, where additional features and capabilities are aggregated at higher levels in the hierarchy. On-chip memory provides storage for content inherently required for basic operation at a particular hierarchy and is coupled with the computational resources in an optimal ratio. Lean control provides just enough signaling to manage only the operations required at a particular hierarchical level. Dynamic resource assignment agility is provided which can be adjusted as required depending on resource availability and capacity of the device.

Abstract: A novel and useful system and method of data driven quantization optimization of weights and input data in an artificial neural network (ANN). The system reduces quantization implications (i.e. error) in a limited resource system by employing the information available in the data actually observed by the system. Data counters in the layers of the network observe the data input thereto. The distribution of the data is used to determine an optimum quantization scheme to apply to the weights, input data, or both. The mechanism is sensitive to the data observed at the input layer of the network. As a result, the network auto-tunes to optimize the instance specific representation of the network. The network becomes customized (i.e. specialized) to the inputs it observes and better fits itself to the subset of the sample space that is applicable to its actual data flow. As a result, nominal process noise is reduced and detection accuracy improves.

Abstract: A novel and useful neural network (NN) processing core adapted to implement artificial neural networks (ANNs) and incorporating processing circuits having compute and local memory elements. The NN processor is constructed from self-contained computational units organized in a hierarchical architecture. The homogeneity enables simpler management and control of similar computational units, aggregated in multiple levels of hierarchy. Computational units are designed with minimal overhead as possible, where additional features and capabilities are aggregated at higher levels in the hierarchy. On-chip memory provides storage for content inherently required for basic operation at a particular hierarchy and is coupled with the computational resources in an optimal ratio. Lean control provides just enough signaling to manage only the operations required at a particular hierarchical level.

Abstract: A novel and useful neural network (NN) processing core adapted to implement artificial neural networks (ANNs) and incorporating configurable and programmable sliding window based memory access. The memory mapping and allocation scheme trades off random and full access in favor of high parallelism and static mapping to a subset of the overall address space. The NN processor is constructed from self-contained computational units organized in a hierarchical architecture. The homogeneity enables simpler management and control of similar computational units, aggregated in multiple levels of hierarchy. Computational units are designed with minimal overhead as possible, where additional features and capabilities are aggregated at higher levels in the hierarchy. On-chip memory provides storage for content inherently required for basic operation at a particular hierarchy and is coupled with the computational resources in an optimal ratio.

Abstract: A novel and useful system and method of accessing multi-dimensional data in memory. The invention is applicable to neural network (NN) processing engines adapted to implement artificial neural networks (ANNs). The NN processor is constructed from self-contained computational units organized in a hierarchical architecture. The homogeneity enables simpler management and control of similar computational units, aggregated in multiple levels of hierarchy. Computational units are designed with minimal overhead as possible, where additional features and capabilities are aggregated at higher levels in the hierarchy. On-chip memory provides storage for content inherently required for basic operation at a particular hierarchy and is coupled with the computational resources in an optimal ratio. Lean control provides just enough signaling to manage only the operations required at a particular hierarchical level.

Abstract: A novel and useful artificial neural network that incorporates emphasis and focus techniques to extract more information from one or more portions of an input image compared to the rest of the image. The ANN recognizes that valuable information in an input image is typically not distributed throughout the image but rather is concentrated in one or more regions. Rather than implement CNN layers sequentially (i.e. row by row) on the input domain of each layer, the present invention leverages the fact that valuable information is focused in one or more regions of the image where it is desirable to apply more attention and for which it is desired to apply more elaborate evaluation. Precision dilution can be applied to those portions of the input image that are not the center of focus and emphasis. A spatial aware function determines the location(s) of the ears of focus and is applied to the first convolutional layer.

Abstract: A novel and useful neural network (NN) processing core incorporating inter-device connectivity and adapted to implement artificial neural networks (ANNs). A chip-to-chip interface spreads a given ANN model across multiple devices in a seamless manner. The NN processor is constructed from self-contained computational units organized in a hierarchical architecture. The homogeneity enables simpler management and control of similar computational units, aggregated in multiple levels of hierarchy. Computational units are designed with minimal overhead as possible, where additional features and capabilities are aggregated at higher levels in the hierarchy. On-chip memory provides storage for content inherently required for basic operation at a particular hierarchy and is coupled with the computational resources in an optimal ratio. Lean control provides just enough signaling to manage only the operations required at a particular hierarchical level.

Abstract: A novel and useful neural network (NN) processing core adapted to implement artificial neural networks (ANNs) and incorporating strictly separate control and data planes. The NN processor is constructed from self-contained computational units organized in a hierarchical architecture. The homogeneity enables simpler management and control of similar computational units, aggregated in multiple levels of hierarchy. Computational units are designed with minimal overhead as possible, where additional features and capabilities are aggregated at higher levels in the hierarchy. On-chip memory provides storage for content inherently required for basic operation at a particular hierarchy and is coupled with the computational resources in an optimal ratio. Lean control provides just enough signaling to manage only the operations required at a particular hierarchical level. Dynamic resource assignment agility is provided which can be adjusted as required depending on resource availability and capacity of the device.

Abstract: A novel and useful augmented artificial neural network (ANN) incorporating an existing artificial neural network (ANN) coupled to a supplemental ANN and a FIFO for storing historical output values of the network. The augmented ANN exploits the redundant nature of information present in an input data stream. The addition of the supplemental ANN along with a FIFO enables the augmented network to look back into the past in making a decision for the current frame. It provides context aware object presence as well as lowers the rate of false detections and misdetections. The output of the existing ANN is stored in a FIFO to create a lookahead system in which both past output values of the supplemental ANN and ‘future’ values of the output of the existing ANN are used in making a decision for the current frame. In addition, the mechanism does not require retraining the entire neural network nor does it require data set labeling.