A learning device includes one or more processors. The processors generate a plurality of pieces of learning data to be used in a plurality of learning processes, respectively, to learn a parameter of a neural network using an objective function. The processors calculate a first partial gradient using a partial data and the parameter added with noise, with respect to at least a part of the learning data out of the plurality of pieces of learning data. The partial data is obtained by dividing the learning data. The first partial gradient is a gradient of the objective function relating to the parameter for the partial data. The noise is calculated based on a second partial gradient calculated for another piece of the learning data. The processors update the parameter using the first partial gradient.

Provided is a reservoir computing system including a reservoir having a random laser for emitting a non-linear optical signal with respect to an input signal. The reservoir computing system also includes a converter for converting the non-linear optical signal into an output signal by applying a conversion function. The conversion function is trained by using a training input signal and a target output signal.

The method of labeling an image of cells of a patient, in particular an immunocytochemistry image comprises the following steps. First, a digital image of a stained immunocytochemistry biological sample of the patient is received. Following by the step that a computerized classification of cells in the digital image based on color, shape or texture in the digital image, the digital image is labeled by application of a trained neural network on at least one portion of the digital image which comprises a digital image of one cell classified under a first category during the computerized classification.

Examples relate to an apparatus, a method and a computer program for detecting an anomaly in input data, to a camera device and a system comprising such an apparatus, and to a method and computer program for training a sequence of machine-learning models for use in anomaly detection. The apparatus for detecting an anomaly in input data is configured to process the input data using a sequence of machine-learning models. The sequence of machine-learning models comprising a first machine-learning model configured to pre-process the input data to provide pre-processed input data and a second machine-learning model configured to process the pre-processed input data to provide output data. The first machine-learning model is trained to transform the input data such, that the pre-processed input data comprises a plurality of sub-components being statistically independent with a known probability distribution. The second machine-learning model is an auto-encoder. The apparatus is configured to determine a presence of an anomaly within the input data based on the output of the second machine-learning model.

Embodiments of the present disclosure provide a method and apparatus for training an image recognition model based on a semantic enhancement, a method and apparatus for recognizing an image, an electronic device, and a computer readable storage medium. The method for training an image recognition model based on a semantic enhancement comprises: extracting, from an inputted first image being unannotated and having no textual description, a first feature representation of the first image; calculating a first loss function based on the first feature representation; extracting, from an inputted second image being unannotated and having an original textual description, a second feature representation of the second image; calculating a second loss function based on the second feature representation, and training an image recognition model based on a fusion of the first loss function and the second loss function.

A processor-implemented method with image analysis includes: receiving a test image; generating a plurality of augmented images by augmenting the test image; determining classification prediction values for the augmented images using a classifier; determining a detection score based on the classification prediction values; and determining whether the test image corresponds to anomaly data based on the detection score and a threshold.

A method of training a model, an electronic device, and a readable storage medium are provided, which relate to a field of artificial intelligence, in particular to computer vision and deep learning technologies, and specifically used in smart city and intelligent transportation scenarios. The method includes: determining a target pre-trained model; and performing an unsupervised training and/or a semi-supervised training on the target pre-trained model based on an image acquired by the target terminal, so as to obtain a first target trained model.

A method is provided for hyperspectral inversion of a phosphorus content of rubber tree leaves. The method includes: acquiring hyperspectral data of to-be-detected rubber tree leaves; extracting key wavelengths of the rubber tree leaves according to the hyperspectral data and a pre-established wavelength extraction model, where the key wavelengths are related to the phosphorus content of the rubber tree leaves, and the pre-established wavelength extraction model is obtained by learning and training hyperspectral sample data and sample phosphorus content data pairs in a pre-established sample database by adopting a competitive adaptive reweighted sampling (CARS) algorithm and a successive projection algorithm (SPA); and inputting the key wavelengths into a pre-established phosphorus content prediction model to calculate the phosphorus content of the to-be-detected rubber tree leaves. Moreover, the CARS algorithm and the SPA are comprehensively applied to extract the key wavelengths closely related to the phosphorus content of the rubber tree leaves.

A device may receive image data that includes an image of a document and lexicon data identifying a lexicon, and may perform an extraction technique on the image data to identify at least one field in the document. The device may utilize form segmentation to automatically generate label data identifying labels for the image data, and may process the image data, the label data, and data identifying the at least one field, with a first model, to identify visual features. The device may process the image data and the visual features, with a second model, to identify sequences of characters, and may process the image data and the sequences of characters, with a third model, to identify strings of characters. The device may compare the lexicon data and the strings of characters to generate verified strings of characters that may be utilized to generate a digitized document.

An image-recognition method is provided. The method includes the following steps: receiving structured data, wherein the structured data includes training-set data and testing-set data, and the structured data includes a plurality of groups, and each group includes one or more types, and each type includes a plurality of check-point images; training an artificial-intelligence (AI) model using the training-set data; inputting the testing-set data into the AI model to obtain a model evaluation of the AI model; and determining one or more first types with a lower overall recognition rate or a lower confidence level in the structured data, and deletes or corrects the check-point images in the one or more first types to update the structured data.