A combinatorial approach for supervised neural network learning

Abstract

A technique for machine learning, such as supervised artificial neural network learning includes receiving data and checking the dimensionality of the read data and reducing the dimensionality to enhance machine learning performance using Principal Component Analysis methodology. The technique further includes specifying the neural network architecture and initializing weights to establish a connection between read data including the reduced dimensionality and the predicted values. The technique also includes performing supervised machine learning using the specified neural network architecture, initialized weights, and the read data including the reduced dimensionality to predict values. Predicted values are then compared to a normalized system error threshold value and the initialized weights are revised based on the outcome of the comparison to generate a learnt neural network having a reduced error in weight space. The learnt neural network is validated using known values and is then used for predicting values.

Description

technical field [0001] The present invention generally relates to the field of intelligent information retrieval, and more specifically relates to intelligent information retrieval based on machine learning. Background technique [0002] The future of intelligent information retrieval seems to be based on machine learning techniques such as artificial neural networks (ANN or NN). The ability of ANNs to represent non-linear relationships in data yields better classifications and is best suited for information retrieval applications such as pattern recognition, prediction, and classification. [0003] ANN technology tries to imitate the structure and information representation mode of the human brain. Its structure depends on the purpose to be obtained. Learning in ANNs can be either supervised or unsupervised. In supervised learning (SL), the ANN assumes what the outcome should be (like a teacher instructing a student). In this case, we are given an input, check what the ...

AI Technical Summary

Problems solved by technology

[0004] The current SL method can handle offline (static) or online (dynamic / time series) data, but not both

Furthermore, current SL methods take a long time to learn and require a considerable number of iterations to stabilize

Current SL methods use the conjugated general delta rule (conjugated GDR) for machine learning when using static data and are not guaranteed to find the global optimum

Stochastic approximation based GDR for time series data is complex and unreliable since GDR can only handle offline data

Images