Patents
Literature
Hiro is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.
Hiro

100 results about "Cognitive learning" patented technology

Cognitive learning. 1 learning that is concerned with acquisition of problem-solving abilities and with intelligence and conscious thought. 2 a theory that defines learning as a behavioral change based on the acquisition of information about the environment.

An image recognition and recommendation method based on neural network depth learning

The invention provides an image recognition and recommendation method based on neural network depth learning. The method obtains pictures and classification from an image database, inputs to a convolution neural network, trains the neural network through repeated forward and backward propagation, improves image recognition accuracy, and extracts a 20-layer neural network model. By using this model, the object recognition and classification is carried out by collecting static pictures. Results are recognized, and by combining with the personalized characteristics of the input, the input probability of interest is analyzed. By using the machine learning model based on the effective recognition and classification of the material cloud database, and using the recommendation system algorithm, the predicted content material is pushed to the image inputter for cognitive learning. The method of the invention has the advantages of high image recognition rate, multiple recognition types and accurate content recommendation, and can be applied to the electronic products of a computer with a digital camera, a mobile phone, a tablet and an embedded system, so that people can photograph and recognize the objects seen in the eyes and actively learn the knowledge of recognizing the objects.
Owner:广州四十五度科技有限公司

Cascade reservoir optimal scheduling method based on self-adaptive improved particle swarm optimization algorithm

The invention discloses a cascade reservoir optimal scheduling method based on a self-adaptive improved particle swarm optimization algorithm, and belongs to the field of water conservancy and hydropower. The cascade reservoir optimal scheduling method comprises the steps: obtaining basic information of a cascade reservoir system; constructing a cascade reservoir optimal scheduling model taking the water level of each time period in the reservoir scheduling period as a decision variable and the maximum generating capacity as an objective function, and determining constraint conditions; initializing particle swarm parameters according to basic information and constraint conditions of the cascade reservoir system; calculating the relative progress of each particle, updating the inertia weight, cognitive learning factor and social learning factor of each particle according to the relative progress, and further updating the speed and position of each particle; and calculating the optimal adaptive value after the particle swarm updating is completed, and obtaining the power generation capacity, the month end water level and the reservoir outlet flow of the cascade reservoir system in each month. According to the cascade reservoir optimal scheduling method, the particle swarm parameters are adaptively adjusted by using the particle relative progress, and the defect that the traditional particle swarm algorithm is easy to fall into local optimum is overcome, and the power generation benefit of the cascade reservoir is improved.
Owner:HUAZHONG UNIV OF SCI & TECH +1

A time sequence prediction method and device based on an intuitive cyclic fuzzy neural network

The invention discloses a time sequence prediction method and device based on an intuitive cyclic fuzzy neural network, and the method comprises the steps: receiving a time sequence data sample, and dividing the time sequence data sample into a plurality of groups of sub-samples; sequentially inputting the plurality of groups of sub-samples into an interval II type intuitive fuzzy inference systemfor fuzzy processing and learning prediction; after a group of samples are input into the system network, updating the system network by adopting a meta-cognitive learning algorithm according to thegenerated prediction error and the spherical situation; the interval II type intuitive fuzzy inference system comprises an input layer, a fuzzification layer, a space emission layer, a time trigger layer and an output layer. The fuzzification layer uses a TSK type fuzzification rule; wherein the spatial emission layer is used for obtaining the membership degree and the non-membership degree of input data, the spatial emission layer is used for carrying out dimension reduction processing on the membership degree and the non-membership degree, the time trigger layer is used for establishing a time relation for the data by using LSTM recursion, and the output layer is used for carrying out defuzzification processing based on a center to output the data.
Owner:SHANDONG NORMAL UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products