Thesis Details
Zjednodušené násobení v konvolučních neuronových sítích
This thesis provides an introduction to classical and convolutional neural networks. It describes how hardware multiplication is conventionally performed and optimized. A simplified multiplication method is proposed, namely multiplierless multiplication. This method is implemented and integrated into the TypeCNN library. The cost of the hardware solution of both conventional and simplified multipliers is estimated. The thesis also introduces software tools developed to work with convolutional neural networks and datasets used to test them in the image classification task. Test architectures and experimentation methodology are proposed. The results are evaluated, and both the classification accuracy and cost of the hardware solution are discussed.
artificial intelligence, soft computing, neuron, neural networks, convolutional neural networks, multiplication, optimization, simplified multiplication, multiplierless multiplication
Češka Milan, doc. RNDr., Ph.D. (DITS FIT BUT), člen
Grégr Matěj, Ing., Ph.D. (DIFS FIT BUT), člen
Hrdina Jaroslav, doc. Mgr., Ph.D. (DADM FME BUT), člen
Malinka Kamil, Mgr., Ph.D. (DITS FIT BUT), člen
Vašíček Zdeněk, doc. Ing., Ph.D. (DCSY FIT BUT), člen
@mastersthesis{FITMT21476, author = "Pavel Juha\v{n}\'{a}k", type = "Master's thesis", title = "Zjednodu\v{s}en\'{e} n\'{a}soben\'{i} v konvolu\v{c}n\'{i}ch neuronov\'{y}ch s\'{i}t\'{i}ch", school = "Brno University of Technology, Faculty of Information Technology", year = 2019, location = "Brno, CZ", language = "czech", url = "https://www.fit.vut.cz/study/thesis/21476/" }