TY - GEN
T1 - Subtractive Perceptrons for Learning Images
T2 - 9th International Conference on Image Processing Theory, Tools and Applications, IPTA 2019
AU - Tizhoosh, H. R.
AU - Kalra, Shivam
AU - Lifshitz, Shalev
AU - Babaie, Morteza
N1 - Publisher Copyright:
© 2019 IEEE.
PY - 2019/11
Y1 - 2019/11
N2 - In recent years, artificial neural networks have achieved tremendous success for many vision-based tasks. However, this success remains within the paradigm of weak AI where networks, among others, are specialized for just one given task. The path toward strong AI, or Artificial General Intelligence, remains rather obscure. One factor, however, is clear, namely that the feed-forward structure of current networks is not a realistic abstraction of the human brain. In this preliminary work, some ideas are proposed to define a subtractive Perceptron (s-Perceptron), a graph-based neural network that delivers a more compact topology to learn one specific task. In this preliminary study, we test the s-Perceptron with the MNIST dataset, a commonly used image archive for digit recognition. The proposed network achieves excellent results compared to the benchmark networks that rely on more complex topologies.
AB - In recent years, artificial neural networks have achieved tremendous success for many vision-based tasks. However, this success remains within the paradigm of weak AI where networks, among others, are specialized for just one given task. The path toward strong AI, or Artificial General Intelligence, remains rather obscure. One factor, however, is clear, namely that the feed-forward structure of current networks is not a realistic abstraction of the human brain. In this preliminary work, some ideas are proposed to define a subtractive Perceptron (s-Perceptron), a graph-based neural network that delivers a more compact topology to learn one specific task. In this preliminary study, we test the s-Perceptron with the MNIST dataset, a commonly used image archive for digit recognition. The proposed network achieves excellent results compared to the benchmark networks that rely on more complex topologies.
UR - http://www.scopus.com/inward/record.url?scp=85077963981&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85077963981&partnerID=8YFLogxK
U2 - 10.1109/IPTA.2019.8936079
DO - 10.1109/IPTA.2019.8936079
M3 - Conference contribution
AN - SCOPUS:85077963981
T3 - 2019 9th International Conference on Image Processing Theory, Tools and Applications, IPTA 2019
BT - 2019 9th International Conference on Image Processing Theory, Tools and Applications, IPTA 2019
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 6 November 2019 through 9 November 2019
ER -