Abstract: A wireless signal decoder may include a receiver configured to receive a wireless signal and convert the wireless signal into a digital signal. The wireless signal decoder may further include a processor configured to input the digital signal into a spiking neural network (SNN) and receive at least one predicted data symbol as output from the SNN. The at least one predicted data symbol may include a rate coded output or a latency coded output.

Abstract: Aspects of the present disclosure provide systems, methods, and computer-readable storage media that support automated optimization of product management systems. In embodiments, automated optimization of component tools of the product management system is provided by automated evaluation and optimization of associated rules and metadata. In embodiments, metadata and rules may be associated to each other by an assessment engine. A recommendation engine may then identify non-compliant metadata, may determine a condition of the rule, and/or may generate recommendations for the rules based on the non-compliant metadata. Automated optimization of the product management system may include automated creation and mapping of decomposition relationships between commercial products and technical products. In embodiments, input data may be parsed into a set of object with unique attribute fields, which may then be validated.

Abstract: In some implementations, a user equipment (UE) may determine a set of layer 1 reference signal received power (L1-RSRP) values for a set B of beams. The UE may determine a set of probabilities for a set A of beams based on the set of L1-RSRP measurement values. The set of probabilities may include, for each beam, a respective probability that the beam is in a first group of beams having a higher L1-RSRP measurement value than other beams that are not included in the first group of beams. The UE may compare the first group of beams and a second group of beams, of the set A of beams, from the base station. The UE may determine an accuracy associated with the base station determining the second group of beams based on comparing the first group of beams and the second group of beams.

Abstract: An example apparatus includes: a supply terminal; fuse circuitry having a first terminal, a second terminal, and an enable terminal, the first terminal of the fuse circuitry coupled to the supply terminal; fault circuitry having an enable terminal and a fault terminal, the enable terminal coupled to the supply terminal, the fault terminal coupled to the enable terminal of the fuse circuitry; and converter circuitry having a terminal coupled to the second terminal of the fuse circuitry.

Abstract: A management system may receive a wireless signal transmitted to a receiver. The management system may determine, based on the wireless signal or a set of decoded bits associated with the wireless signal that were determined using an artificial intelligence (AI) receiver module of the receiver, whether a cyclic redundancy check (CRC) associated with the wireless signal is passed. The management system may perform, based on determining whether the CRC associated with the wireless signal is passed, at least one of: a data storage operation associated with the wireless signal, a fallback operation associated with the wireless signal, or an online label recovery operation associated with the wireless signal. The management system may perform, based on determining whether the CRC associated with the wireless signal is passed, a model modification operation to update a neural network (NN) of the AI receiver module of the receiver.

Abstract: Systems, methods, and devices are provided for implementing artificial intelligence (AI) and machine learning (ML)-based model switching techniques for neural network (NN)-based receivers. In one aspect, a system may deploy a plurality of neural network receivers associated with a receiver and trained to operate in different environments, receive sensing data associated with the receiver, and predict, based on the received sensing data, an environment for the receiver from a predetermined set of different environment types. The system may also select a neural network receiver of the plurality of neural network receivers based on a probability of a successful decoding and switch to the selected neural network receiver.

Abstract: A first input of a modulator circuit is coupled to a current feedback terminal. An output of the modulator circuit is coupled to an input of a power stage circuit. A first input, a second input, and an output of a voltage compensation circuit are coupled to a voltage feedback terminal, a voltage reference terminal, and a compensation terminal, respectively. A first input of a summing circuit is coupled to the output of the voltage compensation circuit. An output of the summing circuit is coupled to a second input of the modulator circuit. An output of an offset generation circuit is coupled to a second input of the summing circuit. An input of a filter circuit is coupled to the output of the voltage compensation circuit. An output of the filter circuit is coupled to an input of the offset generation circuit.

Abstract: In some implementations, a first wireless communication device may determine to update a model, wherein the model is configured to determine predicted layer one (L1) reference signal received powers (RSRPs) for beams included in a set A of beams and probabilities associated with the beams included in the set A of beams being included in a set B of beams. The first wireless communication device may collect training data. The first wireless communication device may determine a top-N beam distribution based on the training data. The first wireless communication device may determine the set B of beams based on the top-N beam distribution. The first wireless communication device may synchronize the set B of beams with a second wireless communication device. The first wireless communication device may update a neural network of the model based on the set B of beams.

Abstract: In some embodiments, systems and methods are provided herein useful to generating item recommendations. In some embodiments, a system for item recommendation may include a memory storing an item recommendation model trained using dense representations for items, the dense representations generated based on an item interaction graph including nodes corresponding to items for sale in a retail facility, edges connecting the nodes, and edge weights for the edges, wherein the edge weights are related to item selection sequence of the items, and a control circuit coupled to the memory, the control circuit configured to receive an indication of an item selection by a user in the retail facility, generate a recommendation for a suggested next item based on using the item selection as an input of the item recommendation model, and cause the one or more suggested next best items to be presented to the user for potential selection.

Abstract: A mobile lighting system to integrate multiple power sources into a unified platform for portable, uninterrupted illumination. In various embodiments, the system includes a light source, an AC socket connector, internal rechargeable batteries, and external battery packs to thermally isolate high-temperature LED zones from power storage to reduce risk of thermal runaway. External interfaces include a USB Power Delivery port enabling bidirectional power transfer, dynamic role switching between source and sink, and data communication with mobile devices. Solar panel input may supplement charging. Intelligent switching logic, executed by stored instructions in a controller, manages transitions between AC, internal, and external power sources based on sensor-detected availability, charge levels, and user-defined priorities.

Abstract: In some embodiments, systems and methods are provided herein useful to generating item recommendations. In some embodiments, a system for item recommendation may include a memory storing an item recommendation model trained using dense representations for items, the dense representations generated based on an item interaction graph including nodes corresponding to items for sale in a retail facility, edges connecting the nodes, and edge weights for the edges, wherein the edge weights are related to item selection sequence of the items, and a control circuit coupled to the memory, the control circuit configured to receive an indication of an item selection by a user in the retail facility, generate a recommendation for a suggested next item based on using the item selection as an input of the item recommendation model, and cause the one or more suggested next best items to be presented to the user for potential selection.

Abstract: A management system may receive a wireless signal transmitted to a receiver. The management system may determine, based on the wireless signal or a set of decoded bits associated with the wireless signal that were determined using an artificial intelligence (AI) receiver module of the receiver, whether a cyclic redundancy check (CRC) associated with the wireless signal is passed. The management system may perform, based on determining whether the CRC associated with the wireless signal is passed, at least one of: a data storage operation associated with the wireless signal, a fallback operation associated with the wireless signal, or an online label recovery operation associated with the wireless signal. The management system may perform, based on determining whether the CRC associated with the wireless signal is passed, a model modification operation to update a neural network (NN) of the AI receiver module of the receiver.

Abstract: Transfer learning (TL)-based systems, methods, and devices are provided for neural network and/or neuromorphic network transmitters/receivers with a set of desired modulation orders. In one aspect, a source system trains a full neural net modulation/demodulation model, from which one or more upper/output layers are removed, and the remaining base layers are transferred into a target system. A set of one or more upper/output layers are generated for the set of desired modulation orders, then transferred into, and trained in, the target system. The target system may store the transferred base layers and the trained set of one or more upper/output layers for the set of desired modulation orders, and use them to modulate/demodulate any transmission having one of the set of desired modulation orders.

Abstract: The present disclosure is generally related to systems and methods for generating an indication of a pupillary response deviation. An electronic device in communication with a display and one or more input devices, displays one or more images. Further, the method includes, detecting, one or more first sizes of a pupil of a user. In response to detecting the one or more first sizes of a pupil, the one or more first sizes of the pupil are compared with one or more second sizes of the pupil of the user. Moreover, in accordance with a determination that one or more criteria are satisfied, including a criterion that is satisfied when the one or more first sizes of the pupil deviate from the one or more second sizes of the pupil by one or more pupil size thresholds, generate an indication of a deviation from the expected pupillary response.

Abstract: In some implementations, a base station testing system obtains model information associated with a neural network (NN) of an artificial intelligence (AI) receiver module of a receiver, training information associated with the NN; and the NN. The base station testing system determines one or more test cases for testing the NN and determines respective testing conditions associated with the one or more test cases. The base station testing system generates, based on the respective testing conditions, respective test case data associated with the one or more test cases. The base station testing system determines, based on testing the NN using the respective test case data associated with the one or more test cases, performance information associated with the NN, and generates, based on determining the performance information, a performance report associated with the NN.

Abstract: Various embodiments of a method and apparatus for providing light that is resilient to power outages are disclosed. The apparatus is a device that includes a primary light source, which includes an AC-to-DC converter that converts the AC power from a light socket to DC power. The device includes a secondary power source, as a backup, having a battery and a light source electrically connected in parallel. In some embodiments, the light source resides on a flexible, printed circuit board. In some embodiments, the device includes a sensor that senses the loss of AC power. In some embodiments, in response to the sensor sensing the loss of AC power, the light shuts off or fades out after a predetermined time period. In some embodiments, the user can stop the light from turning off or fading out by pressing a button.

Abstract: The present disclosure provides methods and compositions for adoptive T cell therapy, particularly extracellular binding proteins targeting KRAS peptides, host cells comprising the binding proteins, and methods of use and manufacture thereof.

Abstract: In some implementations, a wireless signal decoder may include a receiver configured to receive a wireless signal and convert the wireless signal into a digital signal. The wireless signal decoder may further include a processor configured to input the digital signal into a spiking neural network (SNN) and receive at least one predicted data symbol as output from the SNN. The at least one predicted data symbol may include a rate coded output or a latency coded output.

Abstract: A wearable device to monitor health data of a user comprises an outer layer, an inner layer, and a middle layer positioned between the outer layer and the inner layer. The middle layer is a PCB housing a plurality of sensors configured to measure health data of the user. The PCB also houses a microcontroller for processing the health data measured by the plurality of sensors. A portion of the outer layer includes a color changing hardware. The microcontroller controls illumination of the color changing hardware when the health data satisfies a predefined condition.