The feeder neural network is one of the widely used neural networks. It can transfer input data from the input layer to the output layer without feedback. The feeder neural network is improved by using different techniques and many network models with different functions are obtained. In this thesis, the improvement of the performance of the power supply nervous network is studied and applied. This thesis analyzes two types of neural network feeders, namely neural network and self-coded neural network. Then the algorithm is used to solve the two problems of slow convergence and easy to fall to the local minima in the algorithm of the feeder neural network, and the performance comparison experiment with other depth algorithms is carried out. According to the experimental results, the improved chopped feedforward neural network in this paper is an effective deep learning framework.

Haoxian Zhan. Multilayer Performance Improvement of Feedforward Neural Networks. International Journal of Neural Network (2020), Vol. 1, Issue 1: 17-23. https://doi.org/10.38007/NN.2020.010103.

[1] Jansenwinkeln B, Barberio M, Chalopin C, et al. Feedforward Artificial Neural Network-Based Colorectal Cancer Detection Using Hyperspectral Imaging: A Step towards Automatic Optical Biopsy. Cancers, 2020, 13(5):967. https://doi.org/10.3390/cancers13050967

[2] Hardy N F, Buonomano D V. Encoding Time in Feedforward Trajectories of a Recurrent Neural Network Model. Neural Computation, 2018, 30(2):378-396. https://doi.org/10.1162/neco_a_01041

[3] Alfahady N H, Abbo K K, Mahmood E. Development a new conjugate gradient algorithm for improvement feedforward artificial neural networks for predicting the numbers of the Iraqi. Journal of Physics: Conference Series, 2020, 1999(1):012089 (11pp). https://doi.org/10.1088/1742-6596/1999/1/012089

[4] Renisha G, Jayasree T. Cascaded Feedforward Neural Networks for speaker identification using Perceptual Wavelet based Cepstral Coefficients. Journal of Intelligent & Fuzzy Systems, 2019, 37(1):1141-1153. https://doi.org/10.3233/JIFS-182599

[5] Musikawan P, Sunat K, Kongsorot Y, et al. Parallelized Metaheuristic-Ensemble of Heterogeneous Feedforward Neural Networks for Regression Problems. IEEE Access, 2019, 7(1):26909-26932. https://doi.org/10.1109/ACCESS.2019.2900563

[6] Saleem N, Khattak M I, Al-Hasan M, et al. On Learning Spectral Masking for Single Channel Speech Enhancement Using Feedforward and Recurrent Neural Networks. IEEE Access, 2020, PP(99):1-1. https://doi.org/10.1109/ACCESS.2020.3021061

[7] R, Santhoshkumar, M, et al. Deep Learning Approach for Emotion Recognition from Human Body Movements with Feedforward Deep Convolution Neural Networks - ScienceDirect. Procedia Computer Science, 2019, 152(C):158-165. https://doi.org/10.1016/j.procs.2019.05.038

[8] Malmstrm M, Skog I, Axehill D, et al. Asymptotic Prediction Error Variance for Feedforward Neural Networks. IFAC-PapersOnLine, 2020, 53(2):1108-1113. https://doi.org/10.1016/j.ifacol.2020.12.1310

[9] Fedchenko V, Neglia G, Ribeiro B. Feedforward Neural Networks for Caching. Acm Sigmetrics Performance Evaluation Review, 2019, 46(3):139-142. https://doi.org/10.1145/3308897.3308958

[10] Medus L D, Iakymchuk T, Frances-Villora J V, et al. A Novel Systolic Parallel Hardware Architecture for the FPGA Acceleration of Feedforward Neural Networks. IEEE Access, 2019, PP(99):1-1. https://doi.org/10.1109/ACCESS.2019.2920885

[11] Muir D R. Feedforward Approximations to Dynamic Recurrent Network Architectures. Neural Computation, 2018, 30(2):546-567. https://doi.org/10.1162/neco_a_01042

[12] Murti I. Improvement accuracy of recognition isolated Balinese characters with Deep Convolution Neural Network. Journal of Applied Intelligent System, 2019, 4(1):22-27. https://doi.org/10.33633/jais.v4i1.2289

[13] Gianto R. Neural network-based stabilizer for electric power system stability improvement. Journal of Theoretical and Applied Information Technology, 2017, 95(19):4983-4991.

[14] Herawati S, Negara Y, Latif M. Complete ensemble empirical mode decomposition with adaptive noise integrating feedforward neural network for tourist arrival forecasting. Journal of Physics: Conference Series, 2020, 2193(1):012049. https://doi.org/10.1088/1742-6596/2193/1/012049

[15] [1]Etsuro, Nakamura, Tsuyoshi, et al. Automatic Extraction of Lip Shape Using Feedforward Neural Network. IEEJ Transactions on Electronics, Information and Systems, 2018, 138(12):1604-1612. https://doi.org/10.1541/ieejeiss.138.1604

[16] Alghifari M F, Gunawan T S, Kartiwi M. Speech emotion recognition using deep feedforward neural network. Indonesian Journal of Electrical Engineering and Computer Science, 2018, 10(2):554-561. https://doi.org/10.11591/ijeecs.v10.i2.pp554-561

[17] Kozlenko M, Zamikhovska O, Zamikhovskyi L. Software implemented fault diagnosis of natural gas pumping unit based on feedforward neural network. Eastern-European Journal of Enterprise Technologies, 2020, 2(2 (110)):99-109. https://doi.org/10.15587/1729-4061.2020.229859

[18] Krape P, Vidmar M, Munih M. Distance Measurements in UWB-Radio Localization Systems Corrected with a Feedforward Neural Network Model. Sensors, 2020, 21(7):2294. https://doi.org/10.3390/s21072294