An Efficient Approach for Neural Network Architecture

Neural network is one of the main concepts used in machine learning applications. The hardware realization of neural network requires a large area to implement a network with many hidden layers. This paper presents a novel design of a neural network to reduce the hardware area. The proposed approach reduces the number of physical hidden layers from N to N/2 while maintaining full accuracy with a minimal increase in time complexity. The proposed approach adopts the concept of multiplexing input and output layers of the neural network. The approach is implemented based on Tensorflow framework and Xilinx Virtex-7 FPGA. The simulation results show the accuracy of the proposed approach is the same as expected from traditional network, which uses N layers, while using only N/2 hardware layers. The hardware implementation results show the proposed approach saves 42% area.

[1]  Fei-Fei Li,et al.  Large-Scale Video Classification with Convolutional Neural Networks , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[2]  Jitendra Malik,et al.  Region-Based Convolutional Networks for Accurate Object Detection and Segmentation , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  Gheorghe Serban,et al.  Mobile system with real time route learning using Hardware Artificial Neural Network , 2015, 2015 7th International Conference on Electronics, Computers and Artificial Intelligence (ECAI).

[4]  Alex Krizhevsky,et al.  Learning Multiple Layers of Features from Tiny Images , 2009 .

[5]  Rauf Izmailov,et al.  Knowledge transfer in SVM and neural networks , 2017, Annals of Mathematics and Artificial Intelligence.

[6]  Mike Shuo-Wei Chen,et al.  A time multiplexed network architecture for large-scale neuromorphic computing , 2017, 2017 IEEE 60th International Midwest Symposium on Circuits and Systems (MWSCAS).

[7]  Jefersson Alex dos Santos,et al.  Towards better exploiting convolutional neural networks for remote sensing scene classification , 2016, Pattern Recognit..

[8]  Stephen Balaban,et al.  Deep learning and face recognition: the state of the art , 2015, Defense + Security Symposium.

[9]  Prabhat,et al.  Artificial Neural Network , 2018, Encyclopedia of GIS.

[10]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

[11]  Che-Wei Huang,et al.  Deep convolutional recurrent neural network with attention mechanism for robust speech emotion recognition , 2017, 2017 IEEE International Conference on Multimedia and Expo (ICME).

[12]  Arash Bahrammirzaee,et al.  A comparative survey of artificial intelligence applications in finance: artificial neural networks, expert system and hybrid intelligent systems , 2010, Neural Computing and Applications.

[13]  Abdullah M. Zyarah,et al.  Invited paper: Resource sharing in feed forward neural networks for energy efficiency , 2017, 2017 IEEE 60th International Midwest Symposium on Circuits and Systems (MWSCAS).