Developing a Deep Learning Model to Implement Rosenblatt’s Experiential Memory Brain Model

  • Abu KamruzzamanEmail author
  • Yousef Alhwaiti
  • Charles C. Tappert
Conference paper
Part of the Lecture Notes in Networks and Systems book series (LNNS, volume 70)


This paper describes initial work to develop a Deep Learning model for long-term sequential memory storage to implement Rosenblatt’s experiential memory Perceptron architecture brain model. In recent years, deep learning techniques have solved many problems in the area of computer vision, language modeling, speech recognition, and audio/video processing. Further, CNN based models are considered state-of-the-art algorithms to solve perceptron related problems. However, can Deep Learning models store the learned knowledge representation to make better use of classifying and recognizing images and other patterns? The Deep Learning models explored here include CNNs pre-trained models (ResNet50, VGG16, InceptionV3, and MobileNet) on ImageNet datasets and trained model on MNIST datasets.


Convolutional neural network Pre-trained models Handwritten character recognition Deep learning Brain model Machine learning Perceptron 


  1. 1.
    Zhu, W., Lan, C., Xing, J., Zeng, W., Li, Y., Shen, L., Xie, X.: Co-occurrence feature learning for skeleton based action recognition using regularized deep LSTM networks. AAAI 2(5), 6 (2016)Google Scholar
  2. 2.
    Mastin, L. : Types of Memory-The Human Memory. Human-Memory.Net. (2010)Google Scholar
  3. 3.
    Karayev, S., Jia, Y., Shelhamer, E., Donahue, J., Long, J., Girshick, R., Guadarrama, S., Darrell, T.: Caffe: convolutional architecture for fast feature embedding. In: Proceedings of the 22nd ACM International Conference on Multimedia, pp. 675–678. ACM (2014)Google Scholar
  4. 4.
    LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436 (2015)CrossRefGoogle Scholar
  5. 5.
    Cires, D., Meier, U., Schmidhuber, J.: Multi-column Deep Neural Networks for Image Classification. IDSIA/USI-SUPSI, Manno, Switzerland (2012)Google Scholar
  6. 6.
    Schwarz, M., Schulz H., Behnke, S.: RGB-D object recognition and pose estimation based on pre-trained convolutional neural network features. In: IEEE International Conference on Robotics and Automation, Seattle (2015)Google Scholar
  7. 7.
    Amaratunga, T.: Build Deeper: Deep Learning Beginners’ Guide (2017)Google Scholar
  8. 8.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)Google Scholar
  9. 9.
  10. 10.
    Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818–2826 (2016)Google Scholar
  11. 11.
    Rosenblatt, F.: A Model for Experiential Storage in Neural Networks. Spartan Books, Washington, DC (1964)zbMATHGoogle Scholar
  12. 12.
    CNN workflow image,, last accessed 2018/04/20
  13. 13.
    ImageNet Image, (2016)
  14. 14.
    Bottou, L., Cortes, C., Denker, J.S., Drucker, H., Guyon, I., Jackel, L.D., LeCun, Y., Muller, U.A., Sackinger, E., Simard, P., Vapnik, V.: Comparison of classifier methods: a case study in handwritten digit recognition. In: Proceedings of the 12th IAPR International Conference on Pattern Recognition, 1994. Vol. 2-Conference B: Computer Vision & Image Processing, vol. 2, pp. 77–82. IEEE (1994)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Abu Kamruzzaman
    • 1
    Email author
  • Yousef Alhwaiti
    • 1
  • Charles C. Tappert
    • 1
  1. 1.Seidenberg School of Computer Science and Information SystemsPace UniversityPleasantvilleUSA

Personalised recommendations