Described herein are computer-implemented methods for analyzing an input image of a mouth region from a user to provide information regarding a disease or condition of the mouth region, a computing device configured to receive the input images from a user; and a trained machine learning system. In some embodiments, the computing device is configured to transmit an oral health score to the user.

A device for machine learning is provided, including a first neural network layer, a second neural network layer with a normalization layer arranged in between. The normalization layer is configured to, when the device is undergoing training on a batch of training samples, receive multiple outputs of the first neural network layer for a plurality of training samples of the batch, each output comprising multiple data values for different indices on a first dimension and a second dimension; group the outputs into multiple groups based on the indices on the first and second dimensions; form a normalization output for each group which are provided as input to the second neural network layer. According to the application, the training of a deep convolutional neural network with good performance that performs stably at different batch sizes and is generalizable to multiple vision tasks is achieved, thereby improving the performance of the training.

A method of modulating a depth of a hologram, the method includes: obtaining hologram data; determining a scale factor based on a hardware specification of a holographic display to display a three-dimensional (3D) hologram image in a space by using the hologram data; and modulating depth information of the hologram data based on the scale factor.

A parameter optimization device 800 optimizes input CNN structure information and outputs optimized CNN structure information, and includes stride and dilation use layer detection means 811 for extracting stride and dilation parameter information for each convolution layer from the input CNN structure information, and stride and dilation use position modification means 812 for changing the stride and dilation parameter information of the convolution layer.

This disclosure relates to implementing a configuration portfolio having a compact set of model configurations that are predicted to perform well with respect to a wide variety of input tasks. Systems described herein involve evaluating machine learning models with respect to a set of training tasks to generate a regret matrix based on accuracy of the machine learning models in connection with predicting outputs for the training tasks. The systems described herein can identify a subset of model configurations from a plurality of model configurations based on the subset of model configurations having lower associated metrics of regret with respect to the training tasks. This ensures that each model configuration within the configuration portfolio will perform reasonably well for a given input task and provides a mechanism for selecting an output model configuration using significantly fewer processing resources than conventional model selection systems.

Systems and techniques are disclosed for a blockchain network based on machine learning-based proof of work. One of the methods includes accessing a blockchain associated with a blockchain network, and obtaining a first error value specified in a block of the blockchain, the first error value being associated with a machine learning model identified in the block, and the blockchain recording machine learning models. A new machine learning model associated with a second error value is determined, with the second error value being less than the first error value. A block proposal identifying the new machine learning model is generated, the block proposal specifying the first error value. Transmission of the block proposal to other entities is caused. In response to greater than a threshold percentage of the entities approving the block proposal, inclusion of the block proposal in the blockchain is caused.

A method for training a neural network, including: determining a neural network; training the neural network at a first learning rate according to a first optimization mode, where the first learning rate is updated each time the neural network is trained; mapping the first learning rate of the first optimization mode to a second learning rate of a second optimization mode in the same vector space; determining the second learning rate satisfies a preset update condition; and continuing to train the neural network at the second learning rate according to the second optimization mode.

A data processing method related to the field of artificial intelligence includes adding an architecture parameter to each feature interaction item in a first model, to obtain a second model, where the first model is a factorization machine (FM)-based model, and the architecture parameter represents importance of a corresponding feature interaction item; performing optimization on architecture parameters in the second model to obtain the optimized architecture parameters; and obtaining, based on the optimized architecture parameters and the first model or the second model, a third model through feature interaction item deletion.

This application discloses an identity authentication method, a method and an apparatus for training an identity authentication model, and a computer-readable medium in the artificial intelligence field to improve accuracy of identity authentication. The identity authentication method includes: obtaining first operation behavior data and second operation behavior data of a to-be-authenticated user; obtaining, by using a first authentication model by inputting the first operation behavior data, a first recognition result output by the first authentication model; obtaining, by using a second authentication model by inputting the second operation behavior data, a second recognition result output by the second authentication model, where the first authentication model and the second authentication model are an anomaly detection model and a classification model respectively; and inputting the first recognition result and the second recognition result into a decision fusion model to obtain an output identity authentication result.

A method for creating a machine learning system, which is configured for segmentation and object detection. The method includes: providing a directed graph, selecting a path through the graph, at least one additional node being selected from a subset and a path being selected through the graph from the input node along the edges via the additional node up to the output node, the path initially being drawn as a function of probabilities of the edges, which defines a drawing probability of all architectures within the graph, creating a machine learning system as a function of the selected path and training the created machine learning system.