Research and implementation of NN based on TensorFlow

DOI: 10.31673/2412-9070.2020.062025

Abstract

TensorFlow is Google’s open-source machine learning and deep learning framework, which is convenient and flexible to build the current mainstream deep learning model. Convolutional neural network is a classical model of deep learning, the advantage lies in its powerful feature extraction capabilities of convolutional blocks. A neural network in the simplest case is a mathematical model consisting of several layers of elements that perform parallel calculations. Initially, such an architecture was created by analogy with the small computing elements of the human brain — neurons. The minimal computing elements of an artificial neural network are also called neurons. Neural networks typically consist of three or more layers: an input layer, a hidden layer (or layers), and an output layer. An important feature of the neural network is its ability to learn by example, this is called learning with a teacher. The neural network is trained on a large number of examples consisting of input-output pairs (corresponding to each other input and output). In object recognition problems, such a pair will be the input image and the corresponding label — the name of the object. Neural network learning is an iterative process that reduces the deviation of the network output from a given «teacher response» — a label that corresponds to a given image. This process consists of steps called epochs of learning (they are usually calculated in thousands), each of which is the adjustment of the «weights» of the neural network — the parameters of the hidden layers of the network. Upon completion of the learning process, the quality of the neural network is usually good enough to perform the task for which it was trained, although the optimal set of parameters that perfectly recognizes all the images, it is often impossible to choose. Based on the TensorFlow platform, a convolutional neural network model with two-convolution-layers was built. The model was trained and tested with the MNIST data set. The test accuracy rate could reach 99,15%, and compared with the rate of 98,69% with only one-convolution-layer model, which shows that the two-convolution-layers convolutional neural network model has a better ability of feature extraction and classification decision-making.

Keywords: neural network; deep learning; convolution layers; tensorflow.

References
1. Zheng Z. TensorFlow actual Google deep learning framework // Electronic Industry Press. 2018. 287 р.
2. Jing T., Zhang Y. Digital recognition based on deep learning under the TensorFlow platform. 2018. 37(04). 78 р.
3. Xiao J. The application prospect of clustering algorithm in TensorFlow platform is discussed // Digital technology and applications. 2018. №36. Р. 203.
4. Goodfellow I., Bengio Y., Aaron Courville A. DEEP LEARNING // Posts and Telecom Press. 2018. Р. 203.
5. He Y. Python works with machine learning // Electronic Industry Press. 2017. №200. Р. 222.
6. Han S., Tan S. Design and implementation of a deep learning model for stock forecasting based on TensorFlow // Computer applications and software. 2018. №35. Р. 291.
7. Xu Y. Application of deep learning in handwritten numeral recognition // Suzhou University. 2017. №255. Р. 136.
8. Xu Y., Li Z. Handwritten numeral recognition in convolutional neural network and TensorFlow // Shanghai electric technology. 2018. №11. Р. 61.
9. Handwritten numeral recognition system based on TensorFlow / H. Chen, H. Guo, D. Liu, J. Zhang. // Information communication. 2018. №3. Р. 110.
10. Zheng P., Guo L., Ding L. Research and implementation of convolutional neural network based on TensorFlow // Electronic technology and software engineering. 2018. №18. Р. 22.
11. Jin Z. Comparison and analysis of different deep convolutional neural networks based on TensorFlow // Electronics World. 2018. №6. Р. 26.
12. Hou Y., Ding S., Sun T. The mixed depth learning model C-RF and its application in handwritten numeral recognition // Data acquisition and processing. 2018. №33. Р. 350.
13. Ertam F., Aydin G. Data classification with deep learning using Tensorflow // International Conference on Computer Science and Engineering (UBMK) Antalya, 2017. 758 р.
14. Analogizing time complexity of KNN and CNN in recognizing handwritten digits / T. Makkar, Y. Kumar, A. K. Dubey, A. Rocha // Fourth International Conference on Image Information Processing (ICIIP) Shimla, 2017. 1256 р.
15. Alif M., Ahmed S., Hasan M. Isolated Bangla handwritten character recognition with convolutional neural network // 20th International Conference of Computer and Information Technology (ICCIT) Dhaka, 2017. 523 р.
16. Iamsa S., Horata P. Handwritten Character Recognition Using Histograms of Oriented Gradient Features in Deep Learning of Artificial Neural Network // International Conference on IT Convergence and Security (ICITCS) Macao, 2013. 312 р.