8 results about "Learning methods" patented technology

The invention discloses a depth learning method based on a block chain platform and an electronic device. The method comprises: a receiving task publisher selects a depth learning model on the block chain platform; a receiving task publisher selects a depth learning model on the block chain platform. Receiving a training set input by the task publisher; generating a depth learning task according to the training set and the depth learning model; distributing the depth learning task to a computing node in the block chain platform; depth learning is performed on the depth learning task by a computing node to which the depth learning task is distributed. The scheme solves the existing technical problems of high cost of deep learning and low training efficiency, and achieves the technical effect of reducing training cost and improving training efficiency.

A controller that makes an electric motor efficiently operate in accordance with an ambient temperature. The controller includes a machine learning apparatus learning an operating command to the electric motor. The machine learning apparatus includes a status observing part and learning part. The status observing part observes an ambient temperature of an electric motor apparatus and a cycle time of the electric motor as status variables. The learning part learns an operating command to the electric motor in accordance with a training data set prepared based on a combination of the judgment data acquired by a judgment data acquiring part and the status variables.

The invention discloses a command learning method based on an internet of things. The method is characterized by comprising the following steps of 1, the parameter definition of a learning command; 2, the parameter entering of the learning command; 3, the parameter passing of the learning command; 4, the parameter storage of the learning command; 5, the update judgment of the learning command; 6, the parameter analysis of the learning command; 7, the transmission of the learning command; 8, the storage and transmission of the learning command; 9, the binding of the learning command. According to the command learning method based on the internet of things, a command learning system can be standardized, a user can conveniently expand command functions, and the development cost can be reduced.

The invention discloses an unmanned aerial vehicle air combat threat assessment method based on deep learning. The method comprises the following steps: firstly training a support vector machine network structure through a battlefield environment database to achieve the division of different air combat environments, and calibrating the different air combat environments into N modes; then, trainingN deep learning network structures based on a deep belief network by using air combat situation databases in different air combat environments; during evaluation, inputting actual battlefield environment data, and performing environment classification according to the trained support vector machine network, and determining an air combat situation mode in which the unmanned aerial vehicle is located; and finally, inputting the actual air combat situation data into the trained deep belief network in the corresponding mode to perform threat assessment. A double-layer evaluation network mode is adopted, the evaluation accuracy is improved, and a deep learning method is used for pre-training, so the evaluation rapidity is improved, and the threat evaluation problem in the air combat environment of the unmanned aerial vehicle is solved.

The invention relates to the field of big data, and provides a federated learning method, which comprises the following steps: sending a plurality of corresponding ID intersection requests to a plurality of data providers; receiving corresponding sample data returned by each data provider according to the corresponding ID intersection request to obtain a plurality of sample data, and uploading theplurality of sample data to the block chain; judging whether each piece of sample data has a corresponding federation model or not; if the corresponding federation model does not exist in the sampledata, sending the sample data to a target federation model for training; and if the corresponding federation model exists in the sample data, sending the sample data to the corresponding federation model for training. According to the invention, the precision and the business effect of the federated learning model are effectively improved.

The invention belongs to the technical field of artificial intelligence, and discloses a dynamic width-depth neural network for hyperspectral classification and a learning method thereof. According to the network, an iterative least square method is used when an EWSWS layer carries out extended learning on advanced features in the width direction and the depth direction, a plurality of EWSWS networks are added into the network one by one, and more learning ability is obtained in an increment mode. When training data learning is sufficient, the growth process automatically stops. In the process, training data are segmented in a feature domain and a sample domain, so that the method can be used for hyperspectral image data with high feature dimensions and a large number of training samples. Another advantage of the network is that when a proper system structure is gradually and automatically searched, the learning process is more stable, and very specific hyper-parameters and trained weights can be given in a full connection layer.