Methods, systems and apparatus, including computer programs encoded on computer storage medium, for training a neurosymbolic data imputation system on training data inputs in a domain to impute missing data in a data input from the data domain. In one aspect a method includes, for each training data input, adding random noise to missing fields of the training data input;

generating an embedding data input for the training data input using concept embeddings from the domain; processing the noisy data input and the embedding data input through a correlation network to obtain correlation data; applying attention to the noisy training data input and the correlation data to generate a combined data input; processing, by an autoencoder, the combined data input to obtain a decoded data output; computing a difference between the decoded data output and the training data input; and updating parameters of the data imputation system using the difference.

Numerous embodiments of output circuitry for an analog neural memory in a deep learning artificial neural network are disclosed. In some embodiments, a common mode circuit is used with differential cells, W+ and W−, that together store a weight, W. The common mode circuit can utilize current sources, variable resistors, or transistors as part of the structure for introducing a common mode voltage bias.

Systems, computer program products, and methods are described herein for preserving image and acoustic sensitivity using reinforcement learning. The present invention is configured to initiate a file editing engine on the audiovisual file to separate the audiovisual file into a video component and an audio component; initiate a convolutional neural network (CNN) algorithm on the video component to identify one or more sensitive portions in the one or more image frames; initiate an audio word2vec algorithm on the audio component to identify one or more sensitive portions in the audio component; initiate a masking algorithm on the one or more image frames and the audio component; generate a masked video component and a masked audio component based on at least implementing the masking action policy; and bind, using the file editing engine, the masked video component and the masked audio component to generate a masked audiovisual file.

A neural transformer model with attention is trained to predict candidates to complete a line of source code with a zero-inference capability. The model is trained on an unsupervised training dataset that includes features from source code written in multiple programming languages. The features include a file-level context and a local context, where the file-level context includes a global context, a class context, a function context, and/or a method context for each class, function and/or method of the source code programs used in the training dataset. The local context includes method bodies, function bodies, and/or stand-alone code of main method routines. From these features, the model is able to learn to predict an ordered sequence of code elements that complete a line of source code in a programming language seen and not seen during training.

An audio encoding bit rate prediction model training method is performed by a computer device. The method includes: obtaining a sample audio feature parameter corresponding to each of sample audio frames in a first sample audio; performing encoding bit rate prediction on the sample audio feature parameter through an encoding bit rate prediction model, to obtain a sample encoding bit rate for each of the sample audio frames; performing audio encoding on the sample audio frames based on the corresponding sample encoding bit rates to generate sample audio data corresponding to the sample audio frames; performing audio decoding on the sample audio data, to obtain a second sample audio corresponding to the sample audio data; and training the encoding bit rate prediction model based on the first sample audio and the second sample audio until a sample encoding quality score reaches a target encoding quality score.

A computer-implemented method for predicting properties of a plurality of objects in a vicinity of a vehicle includes multiple steps that can be carried out by computer hardware components. The method includes determining a grid map representation of road-users perception data, with the road-users perception data including tracked perception results and/or untracked sensor intermediate detections. The method also includes determining a grid map representation of static environment data based on data obtained from a perception system and/or a pre-determined map. The method further includes determining the properties of the plurality of objects based on the grid map representation of road-users perception data and the grid map representation of static environment data.

The present disclosure relates to neural network optimization methods and apparatuses in the field of artificial intelligence. One example method includes sampling preset hyperparameter search space to obtain multiple hyperparameter combinations. Multiple iterative evaluations are performed on the multiple hyperparameter combinations to obtain multiple performance results of each hyperparameter combination. Any iterative evaluation comprises obtaining at least one performance result of each hyperparameter combination, and if a hyperparameter combination meets a first preset condition, re-evaluating the hyperparameter combination to obtain a re-evaluated performance result of the hyperparameter combination. An optimal hyperparameter combination is determined. If the optimal hyperparameter combination does not meet a second preset condition, a preset model is updated, based on the multiple performance results of each hyperparameter combination, for next sampling. Or if the optimal hyperparameter combination meets a second preset condition, the optimal hyperparameter combination is used as a hyperparameter combination of a neural network.

A video recording method and a video recording device are provided. The method includes: obtaining video data to be recorded; dividing, based on the video data, each frame of the video data into a region of interest and a background region by using a preset neural network model; and encoding the region of interest of the video data based on a first encoding bit rate, and the background region based on a second bit rate, and storing the encoded video data into a storage device through a video buffer.

System and method for using and managing artificial intelligence (AI) inference platform (AIP) and/or model orchestrators according to certain embodiments. For example, a method includes receiving sensor data via a data interface of a model orchestrator, the model orchestrator including an indication of a model pipeline, the model pipeline including a plurality of models; loading the plurality of models according to the model pipeline; applying the model pipeline to the received sensor data; receiving a model output from the model pipeline via a model interface of the model orchestrator; and generating an insight based at least in part on the model output.

An audio sample including speech and ambient sounds is transmitted to a vehicle computer. Recorded audio is received from the vehicle computer, the recorded audio including the audio sample broadcast by the vehicle computer and recorded by the vehicle computer and recognized speech from the recorded audio. The recognized speech and text of the speech are input to a machine learning program that outputs whether the recognized speech matches the text. When the output from the machine learning program indicates that the recognized speech does not match the text, the recognized speech and the text are included in a training dataset for the machine learning program.