Abstract: Methods, apparatus, systems, and articles of manufacture are disclosed to improve convolution efficiency of a convolution neural network (CNN) accelerator. An example hardware accelerator includes a hardware data path element (DPE) in a DPE array, the hardware DPE including an accumulator, and a multiplier coupled to the accumulator, the multiplier to multiply first inputs including an activation value and a filter coefficient value to generate a first convolution output when the hardware DPE is in a convolution mode, and a controller coupled to the DPE array, the controller to adjust the hardware DPE from the convolution mode to a pooling mode by causing at least one of the multiplier or the accumulator to generate a second convolution output based on second inputs, the second inputs including an output location value of a pool area, at least one of the first inputs different from at least one of the second inputs.

Abstract: A lighting apparatus a first group of at least one first solid state emitter, each first solid state emitter including a first light emitting diode (“LED”) that, when excited, emits light having a peak wavelength in a range between about 440 nm and about 475 nm, and a second group of at least one second solid state emitter, each second solid state emitter comprising a second LED that, when excited, emits light having a peak wavelength in a range between about 390 nm and about 415 nm. Between about 2% and about 15% of a spectral power of light emitted from the lighting apparatus is light having wavelengths in the range between about 390 nm and about 415 nm.

Abstract: An DNN accelerator may include a PE array performing MAC operations. The PE array may include PEs capable of MAC operations on quantized values. A PE may include subtractors for subtracting zeropoints from quantized activations and quantized weights to generate intermediate activations and intermediate weights. The intermediate activations and intermediate weights may be stored in data storage units in the PE and maybe used by an MAC unit in the PE. The subtractors may be placed outside the MAC unit but inside the PE. The MAC unit may perform sequential cycles of MAC operations. The MAC unit may include a plurality of multipliers. The intermediate activations and intermediate weights stored in the data storage units may be reused by different multipliers in different cycles of MAC operations. An output of the MAC unit or of the PE may be multiplied with a quantization scale to produce a floating-point value.

Abstract: The present application generally relates to identifying gene clusters from long-read genomic sequencing data. The disclosure provides methods, non-transitory computer readable media, and apparatuses for processing long-read genomic sequencing data, performing error corrections, and identifying gene cluster, e.g. biosynthetic gene clusters. The methods, non-transitory computer readable media, and apparatuses described herein can be employed in broad areas of biological applications, such as drug discovery, industrial chemical discovery and production, and basic biological research.

Abstract: A smart card, including a card with EMV contacts, for determining a person's preferences and for providing services.

Abstract: A vector processor is disclosed including a variety of variable-length instructions. Computer-implemented methods are disclosed for efficiently carrying out a variety of operations in a time-conscious, memory-efficient, and power-efficient manner. Methods for more efficiently managing a buffer by controlling the threshold based on the length of delay line instructions are disclosed. Methods for disposing multi-type and multi-size operations in hardware are disclosed. Methods for condensing look-up tables are disclosed. Methods for in-line alteration of variables are disclosed.

Abstract: A computing system receives a plurality of game files corresponding to a plurality of games across a plurality of seasons. The computing system generates a prediction model configured to generate a possession value for an event. The computing system receives a target event, in real-time or near real-time, from a tracking system monitoring a target game. The computing system generates target features for the target event based on target event data associated with the target event. The computing system generates, via the prediction model, a target possession value for the target event based on the target event data and the target features. The target possession value represents a likelihood that a team with possession will score within a following x-seconds after the target event.

Abstract: A memory array of a compute tile may store activations or weights of a DNN. The memory array may include databanks for storing contexts, context MUXs, and byte MUXs. A databank may store a context with flip-flop arrays, each of which includes a sequence of flip-flops. A logic gate and an ICG unit may gate flip-flops and control whether states of the flip-flops can be changed. The data gating can prevent a context not selected for the databank from inadvertently toggling and wasting power A context MUX may read a context from different flip-flop arrays in a databank based on gray-coded addresses. A byte MUX can combine bits from different bytes in a context read by the context MUX. The memory array may be implemented with bit packing to reduce distance between the context MUX and byte MUX to reduce lengths of wires connecting the context MUXs and byte MUXs.

Abstract: Sparsity processing within a compute block can be done on unpacked data. The compute block includes a sparsity decoder that generates a combined sparsity vector from an activation sparsity vector and a weight sparsity vector. The activation sparsity vector indicates positions of non-zero valued activations in an activation context. The weight sparsity vector indicates positions of non-zero valued weights in a weight context. The combined sparsity vector comprises one or more zero valued bits and one or more non-zero valued bits. The sparsity decoder may determine the position of a non-zero valued bit in the combined sparsity vector and determine an address for the non-zero valued activation and the non-zero valued weight based on the position of the non-zero valued bit. The non-zero valued activation and the non-zero valued weight may be provided to a PE for performing MAC operations.

Abstract: A compute tile includes a WCB that receives a workload of writing an output tensor of a convolution into a local memory of the compute tile. The local memory may be a SRAM. The WCB receives write transactions. A write transaction includes a data block, which is a part of the output tensor, and metadata describing one or more attributes of the data block. The WCB may store write transactions in its internal buffers. The WCB may determine whether to combine two write transactions, e.g., based on an operation mode or metadata in the write transactions. In embodiments where the WCB determines to combine the two write transactions, the WCB may combine the two write transactions into a new write transaction and write the new write transaction into the local memory or an internal memory of the WCB. The total number of write transactions for the workload can be reduced.

Abstract: A method of manufacturing a hypoid gear includes face hobbing a gear blank and forming a green hypoid gear with gear teeth, heat treating the green hypoid gear to form a heat treated hypoid gear with heat treated gear teeth, and hard hobbing the heat treated gear teeth to form a hard finished hypoid gear. Critical non-tooth features on the heat treated hypoid gear are hard finished. Also, the critical non-tooth features on the heat treated hypoid gear can be hard finished prior to hard hobbing the heat treated gear teeth. The heat treating includes at least one of carburizing and induction hardening the green hypoid gear, a surface of the heat treated gear teeth has a hardness greater than or equal to 58 HRC, and the hard hobbing removes heat distortion from the heat treated gear teeth.

Abstract: An DNN accelerator may perform 1×N kernel decomposition to decompose a convolutional kernel into kernel vectors, each of which includes multiple weights. Through the kernel decomposition, a weight operand may be generated from a filter. The DNN accelerator converts an input tensor into input operands. An input operand includes activations and has the same size as the weight operand. The DNN accelerator may read a first activation in the input operand from memory to an internal memory of a first PE and read a second activation in the input operand from the memory to an internal memory of a second PE. The first PE may receive the second activation from the second PE through activation broadcasting between the two PEs and perform MAC operations on the input operand and weight operand. The second PE may perform MAC operations on another input operand in the input tensor and the weight operand.

Abstract: Disclosed are improved methods, systems and devices for color night vision that reduce the number of intensifiers and/or decrease noise. In some embodiments, color night vision is provided in system in which multiple spectral bands are maintained, filtered separately, and then recombined in a unique three-lens-filtering setup. An illustrative four-camera night vision system is unique in that its first three cameras separately filter different bands using a subtractive Cyan, Magenta and Yellow (CMY) color filtering-process, while its fourth camera is used to sense either additional IR illuminators or a luminance channel to increase brightness. In some embodiments, the color night vision is implemented to distinguish details of an image in low light. The unique application of the three-lens subtractive CMY filtering allows for better photon scavenging and preservation of important color information.

Abstract: An integrated linear generator system includes, for example, a generator assembly, a control system, a frame system, an exhaust system, an intake system, a cooling system, a bearing system, one or more auxiliary systems, or a combination thereof. The generator system is configured to generate power, as controlled by the control system. The generator assembly may include an opposed- and free-piston linear generator, configured to operate on a two-stroke cycle. The intake and exhaust systems are configured to provide reactants to and remove products from the generator assembly, respectively. The cooling system is configured to effect heat transfer, material temperature, or both, of components of the integrated linear generator system. The bearing system is configured to constrain the off-axis motion of translators of the generator assembly without applying significant friction forces.

Abstract: A computing system receives a request to project a performance of a first player from a current team on a destination team. The computing system generates, based on the request, player-position features corresponding to the first player. The computing system generates team features corresponding to the first player. The computing system generates rating features for the first player. The computing system generates, via a prediction model, a player box score prediction based on the player-position features, the team features, and the rating features. The player box score prediction includes a plurality of per game metrics of the first player on the destination team.

Abstract: A computing system receives a pre-game lineup against a target opponent. The pre-game lineup includes a representation of each player starting a game against the target opponent. The computing system retrieves a first set of historical data for each player in the pre-game lineup and team-specific information. The computing system retrieves a second set of historical data for each player of the target opponent and target opponent-specific information. The computing system predicts an outcome for the game based on the first set of historical data and the second set of historical data. The computing system projects a future effect of the pre-game lineup on at least one season of play by simulating team and player performance. The computing system generates a graphical output reflecting the predicted outcome of the game and the simulation of team and player performance over the at least one season of play.

Abstract: Methods, apparatus, systems, and articles of manufacture are disclosed to improve convolution efficiency of a convolution neural network (CNN) accelerator. An example hardware accelerator includes a hardware data path element (DPE) in a DPE array, the hardware DPE including an accumulator, and a multiplier coupled to the accumulator, the multiplier to multiply first inputs including an activation value and a filter coefficient value to generate a first convolution output when the hardware DPE is in a convolution mode, and a controller coupled to the DPE array, the controller to adjust the hardware DPE from the convolution mode to a pooling mode by causing at least one of the multiplier or the accumulator to generate a second convolution output based on second inputs, the second inputs including an output location value of a pool area, at least one of the first inputs different from at least one of the second inputs.

Abstract: The present invention relates to methods of treating pancreatic cancer with particular dosage regimes of antibodies that bind colony stimulating factor 1 receptor (CSF1R) (e.g. cabiralizumab) in combination with antibodies that bind programmed cell death 1 (PD-1) (e.g. nivolumab).

Abstract: A computing system retrieves tracking data from a data store. The computing system converts the tracking data into a plurality of graph-based representations. The prediction engine learns to model defensive behavior based on the plurality of graph-based representations. The computing system generates a trained prediction engine based on the learnings. The computing system receives target tracking data for a target event. The target tracking data includes a plurality of target frames. The computing system converts the target tracking data to a plurality of target graph-based representations. The computing system models, via the trained graph neural network, defensive behavior of a team in the target event based on plurality of graph-based representations.

Abstract: A method of treating brown stock in a brown stock washing process is provided. The method includes measuring a refractive index of a brown stock; and dosing an additive to the brown stock according to at least the refractive index of the brown stock. A system for controlling dosing of an additive to a brown stock washing process is also provided. The system includes a refractive index measurement device; a controller configured to receive data provided by the refractive index measurement device and transform the data into additive addition output instructions; and an additive delivery unit configured to receive and execute the additive addition output instructions from the controller.