Method and system for deep learning automation parameter adjustment based on Keras

Abstract

The present invention discloses a method and system for deep learning automation parameter adjustment based on the Keras. A preset parameter initial value list is employed to perform adjustment of batch size and training epoch of a deep learning model; after an optimal batch size and a training epoch parameter value are found, the weight initialization method is adjusted; after the optimal weight initialization method is obtained, the algorithm learning rate is adjusted according to the optimal batch size and the training epoch; after the adjustment of the algorithm learning rate is completed, an optimal learning rate parameter value is obtained, an activation function is adjusted, and the optimal activation function type of the model is found; and according to the optimal batch size, the optimal training epoch, the optimal weight initialization method, the optimal learning rate and the optimal activation function, the Dropout parameter is adjusted to find out an optimal Dropout parameter value, and the training epoch is subjected to fine tuning to obtain final parameter combination. The method and system for deep learning automation parameter adjustment based on the Keras can greatly reduce the deep learning model parameter adjustment and encoding workload and improve the efficiency of the deep learning development.

Description

technical field [0001] The invention belongs to the technical field of deep learning and artificial intelligence, and more specifically relates to a Keras-based deep learning automatic parameter adjustment method and system. Background technique [0002] Deep learning is the intersection of neural network, graph modeling, optimization theory, pattern recognition, signal processing and other multidisciplinary fields. The main structure of deep learning is artificial neural network. Its basic feature is to try to imitate the transmission between neurons in the brain. Mode of processing information. Inspired by neuroscience research on the structure of the human brain, in order to make machines have human-like intelligence, artificial neural networks are proposed to simulate the process of human brain processing data. The neural network model with multi-hidden layer structure is very flexible and expressive, and can be used to build more complex mathematical models. The multi...

AI Technical Summary

Problems solved by technology

[0006] Aiming at the above defects or improvement needs of the prior art, the present invention provides a Keras-based deep learning automatic parameter adjustment method and system, based on the Keras library for batch size, training cycle, algorithm learning rate, and activation function in the artificial neural network. , Weight initialization, Dropout and other parameters are automatically tuned, thereby solving the technical problem in the prior art that requires a large amount of work to individually tune the complex and numerous parameters of deep learning

Images