Search ETDs:
Convolutional Neural Network Optimization Using Genetic Algorithms
Reiling, Anthony J.

2017, Master of Science in Computer Engineering, University of Dayton, Electrical and Computer Engineering.
This thesis proposes the use of a genetic algorithm (GA) to optimize the accuracy of a convolutional neural network (CNN). The GA modifies the structure of the CNN such as the number of convolutional filters, strides, kernel size, nodes, learning parameters, etc. Each modification of the network is trained and evaluated. Mutation of evolved networks create more successful networks over multiple generations. The final evolved network is 4.77% more accurate than a network pro- posed in the previous literature. Additionally, the evolved network is 13.4% less computationally complex.
Eric Balster (Advisor)
Tarek Taha (Committee Member)
Frank Scarpino (Committee Member)
42 p.

Recommended Citations

Hide/Show APA Citation

Reiling, A. (2017). Convolutional Neural Network Optimization Using Genetic Algorithms. (Electronic Thesis or Dissertation). Retrieved from https://etd.ohiolink.edu/

Hide/Show MLA Citation

Reiling, Anthony . "Convolutional Neural Network Optimization Using Genetic Algorithms." Electronic Thesis or Dissertation. University of Dayton, 2017. OhioLINK Electronic Theses and Dissertations Center. 21 Jul 2018.

Hide/Show Chicago Citation

Reiling, Anthony "Convolutional Neural Network Optimization Using Genetic Algorithms." Electronic Thesis or Dissertation. University of Dayton, 2017. https://etd.ohiolink.edu/

Files

Reiling thesis-9__final format approved LW 12-4-17.pdf (297.31 KB) View|Download