Abstract: A gripper includes a body part, a finger base part coupled to the body part, and a finger part coupled to a first side of the body part or the finger base part and coupled to the body part or the finger base part to be reciprocal, wherein the finger part comprises a first link structure and a second link structure, sides of which are coupled to the finger base part, respectively, and wherein, in the first link structure and the second link structure, a first support area of the first link structure and a second support area of the second link structure reciprocate in only one of a plurality of directions that cross a direction in which the finger part reciprocates with respect to the finger base part.

Abstract: A gripper includes a body part, a finger base part coupled to the body part to be rotatable, the finger base part including a first finger base part and a second finger base part configured such that when the first finger base part is rotated in a first direction with respect to the body part, the second finger base part is provided to be rotatable in a second direction opposite the first direction with respect to the body part, and a finger part coupled to a first side of the body part or the finger base part to be reciprocal.

Abstract: A processor-implemented method for recognizing a natural language on a mobile device includes receiving an audio input. The method further includes using a neural network to generate local text corresponding to the audio input. The method still further includes generating a local confidence value for accuracy of the local text. The method includes transmitting, to a remote device, data corresponding to the audio input. The method further includes receiving remote text corresponding to the data, along with a remote confidence score for accuracy of the remote text. The method still further includes outputting the local text in response to the local confidence value being higher than the remote confidence score, and outputting the remote text in response to the remote confidence score being higher than the local confidence value.

Abstract: Certain aspects of the present disclosure provide techniques and apparatus for a training and using machine learning models in multi-device network environments. An example computer-implemented method for network communications performed by a host device includes extracting a feature set from a data set associated with a client device using a client-device-specific feature extractor, wherein the feature set comprises a subset of features in a common feature space, training a task-specific model based on the extracted feature set and one or more other feature sets associated with other client devices, wherein the feature sets associated with the other client devices comprise one or more subsets of features in the common feature space, and deploying, to each respective client device of a plurality of client devices, a respective version of the task-specific model.

Abstract: An embodiment device includes an input module including a motor configured to generate a rotational force, an output module configured to receive power from the input module to be rotatable, and a connection module having a first side coupled to the input module and a second side, opposite the first side, coupled to the output module, wherein the connection module is configured to transmit the power from the input module to the output module.

Abstract: An embodiment joint structure includes a first connection link configured to be fixed to one side of a wearer, a second connection link coupled to the first connection link to be rotatable about a first rotation axis, a third connection link coupled to the first connection link to be rotatable about a second rotation axis spaced apart from the first rotation axis, and a fourth connection link, a first side of which is coupled to the second connection link to be rotatable about a third rotation axis and a second side of which is coupled to the third connection link to be rotatable about a fourth rotation axis spaced apart from the third rotation axis, wherein an imaginary first extension axis, an imaginary second extension axis, an imaginary third extension axis, and an imaginary fourth extension axis intersect each other in an intersection area.

Abstract: A method for operating a neural network includes receiving an input sequence at an encoder. The input sequence is encoded to produce a set of hidden representations. Attention-heads of the neural network calculate attention weights based on the hidden representations. A context vector is calculated for each attention-head based on the attention weights and the hidden representations. Each of the context vectors correspond to a portion of the input sequence. An inference is output based on the context vectors.

Abstract: Embodiments include methods performed by a processor of a computing device for suggesting more efficient action sequences to a user. The methods may include recognizing a user action sequence including one or more user actions performed by the user to achieve a result, determining a first difficulty rating of the user action sequence, determining whether a cluster of multiple system action sequences exists within a cluster database in which each system action sequence of the one or more system action sequences produces the result. Methods may further include comparing the first difficulty rating to one or more difficulty ratings of the one or more system action sequences in response to determining that the cluster of multiple system action sequences exists within the cluster database, and displaying, via a display interface of the computing device, one or more system action sequences with a lower difficulty rating than the first difficulty rating.

Abstract: Imaging systems and techniques are described. An imaging system receives image data representing at least a portion (e.g., a face) of a first user as captured by a first image sensor. The imaging system identifies that a gaze of the first user as represented in the image data is directed toward a displayed representation of at least a portion (e.g., a face) of a second user. The imaging system identifies an arrangement of representations of users for output. The imaging system generates modified image data based on the gaze and the arrangement at least in part by modifying the image data to modify at least the portion of the first user in the image data to be visually directed toward a direction corresponding to the second user based on the gaze and the arrangement. The imaging system outputs the modified image data arranged according to the arrangement.

Abstract: Imaging systems and techniques are described. An imaging system receives image data representing at least a portion (e.g., a face) of a first user as captured by a first image sensor. The imaging system identifies that a gaze of the first user as represented in the image data is directed toward a displayed representation of at least a portion (e.g., a face) of a second user. The imaging system identifies an arrangement of representations of users for output. The imaging system generates modified image data based on the gaze and the arrangement at least in part by modifying the image data to modify at least the portion of the first user in the image data to be visually directed toward a direction corresponding to the second user based on the gaze and the arrangement. The imaging system outputs the modified image data arranged according to the arrangement.

Abstract: In one embodiment, an electronic device includes an input device configured to provide an input stream, a first processing device, and a second processing device. The first processing device is configured to use a keyword-detection model to determine if the input stream comprises a keyword, wake up the second processing device in response to determining that a segment of the input stream comprises the keyword, and modify the keyword-detection model in response to a training input received from the second processing device. The second processing device is configured to use a first neural network to determine whether the segment of the input stream comprises the keyword and provide the training input to the first processing device in response to determining that the segment of the input stream does not comprise the keyword.

Abstract: Embodiment systems and methods for presenting a facial expression in a virtual meeting may include detecting a user facial expression of a user based on information received from a sensor of the computing device, determining whether the detected user facial expression is approved for presentation on an avatar in a virtual meeting, generating an avatar exhibiting a facial expression consistent with the detected user facial expression in response to determining that the detected user facial expression is approved for presentation on an avatar in the virtual meeting, generating an avatar exhibiting a facial expression that is approved for presentation in response to determining that the detected user facial expression is not approved for presentation on an avatar in the virtual meeting, and presenting the generated avatar in the virtual meeting.

Abstract: Embodiments include methods of assisting a user in locating a mobile device executed by a processor of the mobile device. Various embodiments may include a processor of a mobile device obtaining information useful for locating the mobile device from a sensor of the mobile device configured to obtain information regarding surroundings of the mobile device, anonymizing the obtained information to remove private information, and uploading the anonymized information to a remote server in response to determining that the mobile device may be misplaced. Anonymizing the obtained information may include removing speech from an audio input and compiling samples of ambient noise for inclusion in the anonymized information. Anonymizing the obtained information to remove private information includes editing an image captured by the mobile device to make images of detected individuals unrecognizable.

Abstract: Certain aspects of the present disclosure provide techniques for residual normalization. A first tensor comprising a frequency dimension and a temporal dimension is accessed. A second tensor is generated by applying a frequency-based instance normalization operation to the first tensor, comprising, for each respective frequency bin in the frequency dimension, computing a respective frequency-specific mean of the first tensor. A third tensor is generated by: scaling the first tensor by a scale value, and aggregating the scaled first tensor and the second tensor. The third tensor is provided as input to a layer of a neural network.

Abstract: Certain aspects of the present disclosure provide techniques for training a machine learning model. The method generally includes receiving, at a local device from a server, information defining a global version of a machine learning model. A local version of the machine learning model and a local center associated with the local version of the machine learning model are generated based on embeddings generated from local data at a client device and the global version of the machine learning model. A secure center different from the local center is generated based, at least in part, on information about secure centers shared by a plurality of other devices participating in a federated learning scheme. Information about the local version of the machine learning model and information about the secure center is transmitted by the local device to the server.

Abstract: Embodiment systems and methods for presenting a facial expression in a virtual meeting may include detecting a user facial expression of a user based on information received from a sensor of the computing device, determining whether the detected user facial expression is approved for presentation on an avatar in a virtual meeting, generating an avatar exhibiting a facial expression consistent with the detected user facial expression in response to determining that the detected user facial expression is approved for presentation on an avatar in the virtual meeting, generating an avatar exhibiting a facial expression that is approved for presentation in response to determining that the detected user facial expression is not approved for presentation on an avatar in the virtual meeting, and presenting the generated avatar in the virtual meeting.

Abstract: A processor-implemented method for compressing a deep neural network model includes receiving an initial neural network model. The initial neural network is pruned based on a first threshold to generate a pruned network and a set of pruned weights. A quantization process is applied to the pruned network to produce a pruned and quantized network. A teacher model is generated by incorporating the pruned set of weights with the pruned network. In addition, an initial student model is generated from the quantized and pruned network. The initial student model is trained using the teacher model to output a trained student model.

Abstract: A device to process an audio signal representing input sound includes a hand detector configured to generate a first indication responsive to detection of at least a portion of a hand over at least a portion of the device. The device also includes an automatic speech recognition system configured to be activated, responsive to the first indication, to process the audio signal.

Abstract: A computer-implemented method of operating an artificial neural network for processing data having a frequency dimension includes receiving an input. The audio input may be separated into one or more subgroups along the frequency dimension. A normalization may be performed on each subgroup. The normalization for a first subgroup the normalization is performed independently of the normalization a second subgroups. An output such as a keyword detection indication, is generated based on the normalized subgroups.

Abstract: A method for generating a personalized model includes receiving one or more personal data samples from a user. A prototype of a personal identity is generated based on the personal data samples. The prototype of the personal identity is trained to reflect personal characteristics of the user. A network graph is generated based on the prototype of the personal identity. One or more channels of a global network are pruned based on the network graph to produce the personalized model.