In various examples, a sequential deep neural network (DNN) may be trained using ground truth data generated by correlating (e.g., by cross-sensor fusion) sensor data with image data representative of a sequences of images. In deployment, the sequential DNN may leverage the sensor correlation to compute various predictions using image data alone. The predictions may include velocities, in world space, of objects in fields of view of an ego-vehicle, current and future locations of the objects in image space, and/or a time-to-collision (TTC) between the objects and the ego-vehicle. These predictions may be used as part of a perception system for understanding and reacting to a current physical environment of the ego-vehicle.

A latent code defined in an input space is processed by the mapping neural network to produce an intermediate latent code defined in an intermediate latent space. The intermediate latent code may be used as appearance vector that is processed by the synthesis neural network to generate an image. The appearance vector is a compressed encoding of data, such as video frames including a person's face, audio, and other data. Captured images may be converted into appearance vectors at a local device and transmitted to a remote device using much less bandwidth compared with transmitting the captured images. A synthesis neural network at the remote device reconstructs the images for display.

Distance metrics and clustering in recurrent neural networks. For example, a method includes determining whether topological patterns of activity in a collection of topological patterns occur in a recurrent artificial neural network in response to input of first data into the recurrent artificial neural network, and determining a distance between the first data and either second data or a reference based on the topological patterns of activity that are determined to occur in response to the input of the first data.

The technology disclosed provides a so-called “pointer sentinel mixture architecture” for neural network sequence models that has the ability to either reproduce a token from a recent context or produce a token from a predefined vocabulary. In one implementation, a pointer sentinel-LSTM architecture achieves state of the art language modeling performance of 70.9 perplexity on the Penn Treebank dataset, while using far fewer parameters than a standard softmax LSTM.

Certain aspects of the present disclosure provide techniques for encoding image data for one or more images. In one embodiment, a method includes the steps of downscaling the one or more images, and encoding the one or more downscaled images using an image codec. Another embodiment concerns a computer-implemented method of decoding encoded image data, and a computer-implemented method of encoding and decoding image data.

A system for controlling an operation of a machine including a plurality of actuators assisting one or multiple tools to perform one or multiple tasks, in response to receiving an acoustic mixture of signals generated by the tool performing a task and by the plurality of actuators actuating the tool, submit the acoustic mixture of signals into a neural network trained to separate from the acoustic mixture a signal generated by the tool performing the task from signals generated by the actuators actuating the tool to extract the signal generated by the tool performing the task from the acoustic mixture of signals, analyze the extracted signal to produce a state of performance of the task, and execute a control action selected according to the state of performance of the task.

A method includes receiving a training example that includes audio data representing a spoken utterance and a ground truth transcription. For each word in the spoken utterance, the method also includes inserting a placeholder symbol before the respective word identifying a respective ground truth alignment for a beginning and an end of the respective word, determining a beginning word piece and an ending word piece, and generating a first constrained alignment for the beginning word piece and a second constrained alignment for the ending word piece. The first constrained alignment is aligned with the ground truth alignment for the beginning of the respective word and the second constrained alignment is aligned with the ground truth alignment for the ending of the respective word. The method also includes constraining an attention head of a second pass decoder by applying the first and second constrained alignments.

Systems, methods, and non-transitory computer-readable media are disclosed for selectively rendering augmented reality content based on predictions regarding a user's ability to visually process the augmented reality content. For instance, the disclosed systems can identify eye tracking information for a user at an initial time. Moreover, the disclosed systems can predict a change in an ability of the user to visually process an augmented reality element at a future time based on the eye tracking information. Additionally, the disclosed systems can selectively render the augmented reality element at the future time based on the predicted change in the ability of the user to visually process the augmented reality element.

An electrical panel or an electrical meter may provide improved functionality by interacting with a smart plug. A smart plug may provide a smart-plug power monitoring signal that includes information about power consumption of devices connected to the smart plug. The smart-plug power monitoring signal may be used in conjunction with power monitoring signals from the electrical mains of the building for providing information about the operation of devices in the building. For example, the power monitoring signals may be used to (i) determine the main of the house that provides power to the smart plug, (ii) identify devices receiving power from the smart plug, (iii) improve the accuracy of identifying device state changes, and (iv) train mathematical models for identifying devices and device state changes.

Systems are provided for implementing a hardware accelerator. The hardware accelerator emulate a stochastic neural network, and includes a first memristor crossbar array, and a second memristor crossbar array. The first memristor crossbar array can be programmed to calculate node values of the neural network. The nodes values can be calculated in accordance with rules to reduce an energy function associated with the neural network. The second memristor crossbar array is coupled to the first memristor crossbar array and programmed to introduce noise signals into the neural network. The noise signals can be introduced such that the energy function associated with the neural network converges towards a global minimum and modifies the calculated node values.