Abstract: A computing system can include an embedding model and a clustering model. The computing system input each of the plurality of inputs into the embedding model and receiving respective embeddings for the plurality of inputs as outputs of the embedding model. The computing system can input the respective embeddings for the plurality of inputs into the clustering model and receiving respective cluster assignments for the plurality of inputs as outputs of the clustering model. The computing system can evaluate a clustering loss function that evaluates a first average, across the plurality of inputs, of a respective first entropy of each respective probability distribution; and a second entropy of a second average of the probability distributions for the plurality of inputs. The computing system can modify parameter(s) of one or both of the clustering model and the embedding model based on the clustering loss function.

Abstract: A computing system can include an embedding model and a clustering model. The computing system input each of the plurality of inputs into the embedding model and receiving respective embeddings for the plurality of inputs as outputs of the embedding model. The computing system can input the respective embeddings for the plurality of inputs into the clustering model and receiving respective cluster assignments for the plurality of inputs as outputs of the clustering model. The computing system can evaluate a clustering loss function that evaluates a first average, across the plurality of inputs, of a respective first entropy of each respective probability distribution; and a second entropy of a second average of the probability distributions for the plurality of inputs. The computing system can modify parameter(s) of one or both of the clustering model and the embedding model based on the clustering loss function.

Abstract: The disclosure includes a system and method for detecting fine grain copresence between users. The system includes a processor and a memory storing instructions that when executed cause the system to: transmit a wakeup signal to a plurality of devices based on coarse grain location information; send a request to a first device of the plurality of devices to transmit a token using a first communication technology to determine fine grain copresence; receive a first token acknowledgment from a first subset of the plurality of devices; send a request to a second device of the first subset of the plurality of devices to transmit the token using a second communication technology to determine fine grain copresence; receive a second token acknowledgment from a second subset of the plurality of devices; and refine copresence based on receiving the first and second token acknowledgment.

Abstract: Implementations include systems and methods for scoring candidates for set recommendation problems. An example method includes repeating, for each code in code arrays for items in a set of items, determining a most common value for the code. In some implementations, the method includes determining that the most common value occurs with a frequency that meets an occurrence threshold and adding the code and the most common value to set-inclusion criteria. In other implementations, the method includes determining a value for the code from a code array for a seed item and adding the code and the most common value to set-inclusion criteria when the value for the code from the code array for the seed item matches the most common value. The method may also include evaluating a similarity with a candidate item based on the set-inclusion criteria and basing a recommendation regarding the candidate item on the similarity.

Abstract: Implementations include systems and methods for scoring candidates for set recommendation problems. An example method includes repeating, for each code in code arrays for items in a set of items, determining a most common value for the code. In some implementations, the method includes determining that the most common value occurs with a frequency that meets an occurrence threshold and adding the code and the most common value to set-inclusion criteria. In other implementations, the method includes determining a value for the code from a code array for a seed item and adding the code and the most common value to set-inclusion criteria when the value for the code from the code array for the seed item matches the most common value. The method may also include evaluating a similarity with a candidate item based on the set-inclusion criteria and basing a recommendation regarding the candidate item on the similarity.

Abstract: Implementations generally relate to providing data transmission between devices over audible sound. In some implementations, a method includes mapping each symbol of data to a frequency combination, where each frequency combination includes one or more frequencies. The method further includes generating a sine wave for each frequency. The method further includes adding sine waves for a given symbol to obtain a resulting sine wave. The method further includes applying a window function to the resulting sine wave to obtain a data signal.

Abstract: The present disclosure provides techniques for improving IMU-based gesture detection by a device using ultrasonic Doppler. A method may include detecting the onset of a gesture at a first device based on motion data obtained from an IMU of the first device. An indication of the detection of the onset of the gesture may be provided to a second device. Next, a first audio signal may be received from the second device. As a result, the gesture may be identified based on the motion data and the received first audio signal. In some cases, a first token encoded within the first audio signal may be decoded and the first token may be provided to a third coordinating device. A confirmation message may be received from the third coordinating device based on the first token provided and identifying the gesture may be further based on the confirmation message.

Abstract: The disclosure includes a system and method for detecting fine grain copresence between users. The system includes a processor and a memory storing instructions that when executed cause the system to: process one or more signals to determine coarse grain location information of a first device and a second device; determine whether the first device and the second device are copresent based on the coarse grain location information; in response to determining that the first device and the second device are copresent based on the coarse grain location information, transmit a signal to the second device to alert the second device to listen for a fine grain copresence token from the first device; and refine copresence based on receiving an indication that the second device has received the fine grain copresence token.

Abstract: Implementations generally relate to ultrasonic communication between devices. In some implementations, a method includes receiving a data signal, where the data signal is transmitted and received in an indoor environment. The method further includes demodulating the data signal based on direct sequence spread spectrum.

Abstract: The present disclosure provides techniques for improving IMU-based gesture detection by a device using ultrasonic Doppler. A method may include detecting the onset of a gesture at a first device based on motion data obtained from an IMU of the first device. An indication of the detection of the onset of the gesture may be provided to a second device. Next, a first audio signal may be received from the second device. As a result, the gesture may be identified based on the motion data and the received first audio signal. In some cases, a first token encoded within the first audio signal may be decoded and the first token may be provided to a third coordinating device. A confirmation message may be received from the third coordinating device based on the first token provided and identifying the gesture may be further based on the confirmation message.

Abstract: An asymmetric system for obtaining recommendations is disclosed. A reference magnitude may be obtained from a seed and/or a user model. The reference magnitude may be utilized to adjust the magnitude of candidate vectors that represent one or more items in a multi-dimensional vector space. This permits an item to receive credit for a popularity up to a certain point. The dot products between the adjusted candidate vectors and the seed vector may be obtained and, in some configurations, ranked. The highest dot products may correspond to items that are preferred to be recommended according to an implementation.

Abstract: A user model may be generated using affinity and exposure values for each item a user interacts with in an embedded space. The user model may include exemplars which may refer to representative items in the embedded space. Based on the user model, a recommendation of items may be provided to the user. A truncated form of the user model and/or the recommended items may be sent to the user's mobile device.

Abstract: The disclosure includes a system and method for detecting fine grain copresence between users. The system includes a processor and a memory storing instructions that when executed cause the system to: process one or more signals to determine coarse grain location information of a first device and a second device; determine whether the first device and the second device are copresent based on the coarse grain location information; in response to determining that the first device and the second device are copresent based on the coarse grain location information, transmit a signal to the second device to alert the second device to listen for a fine grain copresence token from the first device; and refine copresence based on receiving an indication that the second device has received the fine grain copresence token.