Optical Compute Engine Using Deep CNN

  • Authors

    • Zainab Zaveri
    • Dhruv Gosain
    • Arul Prakash M
    2018-04-25
    https://doi.org/10.14419/ijet.v7i2.24.12157
  • Deep Convolutional Neural Network, feature extractor, R-CNN, SVNH
  • We present an optical compute engine with implementation of Deep CNNs. CNNs are designed in an organized and hierarchical manner and their convolutional layers, subsampling layers alternate with each other, thus   the intricacy of the data per layer escalates as we traverse in the layered structure, which gives us more efficient results when dealing with complex data sets and computations. CNNs are realised in a distinctive way and vary from other neural networks in how their convolutional and subsampling layers are organised. DCNNs bring us very proficient results when it comes to image classification tasks. Recently, we have understood that generalization is more important when compared to the neural network’s depth for more optimised image classification. Our feature extractors are learned in an unsupervised way, hence the results get more precise after every backpropagation and error correction.

  • References

    1. [1] Dan C.Ciresan, Ueli Meirer,Jonathan Masci,Luca M.Gambardella,Jorgen Schmidhuber, “Flexible,High Performance Convolutional Neural Networks for Image Classification,†IDSIA,USI andSUPSI.

      [2] Alex Krizhevsky,Ilya Sutskever,Geoffrey E.Hinton,â€ImageNet Classification with Deep Convolutiinal Neural Networksâ€, University of Toronto.

      [3] Andeas Kolsch, Muhammad Zeshan Afzal ,Markus Ebbecke,Marcus Liwicki,“Real-Time Document Image Classification using Deep CNN and Extreme Learning Machines,†in 2017 14th IAPR International Conference on Doocument Analysis and Recognition.

      [4] URL:â€https://mattmazur.com/2015/03/17/a-step-by-step-backpropagation-example/.â€

      [5] Ross Girshick, Jeff Donahue,Trevor Darrell, Jitendra Malik,â€Rich feature heirarchies for accurate object detection and semantic segmentationâ€

      [6] URL: “ http://cs231n.github.io/neural-networks-1/â€

      [7] Max Jaderberg,Karen Simonyan,Andrew Zisserman,Koray Kavukcuoglu,â€Spatial Transformer Networksâ€.

      [8] Christian Szegedy,Wei Liu,Yangqing Jia,Pierre Sermanet,Scott Reed,Dragomir Anguelov,Dumitru Erhan,Vincent Vanhoucke,Andrew Rabinovich,â€GoogleNet:Going Deeper with Convolutionâ€,ILSVRC 2014

      [9] URL:â€https://hackernoon.com/deep-learning-cnns-in-tensorflow-with-gpus-cba6efe0acc2â€

      [10] Ian J.Goodfellow, Jean Pouget-Abadie,Mehdi Mirza, Bing Xu,David Warde-Farley,Sherjil Ozair,Aron Courville,Yoshua Bengio,â€Generative Adversial Netsâ€,University of Montreal.

      [11] URL: “https://www.quora.com/What-is-max-pooling-in-convolutional-neural-networksâ€

      [12] Andej Karpathy,Li Fei-Fei,â€Deep Visual –Semantic Allignments for Generating Image Descriptionsâ€,Stanford University

  • Downloads

  • How to Cite

    Zaveri, Z., Gosain, D., & Prakash M, A. (2018). Optical Compute Engine Using Deep CNN. International Journal of Engineering & Technology, 7(2.24), 541-544. https://doi.org/10.14419/ijet.v7i2.24.12157