In this thesis capsule networks are investigated, both theoretically and empirically. The properties of the dynamic routing [42] algorithm proposed for capsule networks, as well as a routing algorithm in a follow-up paper by Wang et al. [50] are thoroughly investigated. It is conjectured that there are three key attributes that are needed for a good routing algorithm, and these attributes are then related to previous algorithms. A novel routing algorithm EntMin is proposed based on the observations from the investigation of previous algorithms. A thorough evaluation of the performance of different aspects of capsule networks is conducted, and it is shown that EntMin outperforms both dynamic routing and Wang routing. Finally, a capsule network using EntMin routing is compared to a very deep Convolutional Neural Network and it is shown that it achieves comparable performance.
Identifer | oai:union.ndltd.org:UPSALLA1/oai:DiVA.org:liu-166925 |
Date | January 2020 |
Creators | Edstedt, Johan |
Publisher | Linköpings universitet, Datorseende |
Source Sets | DiVA Archive at Upsalla University |
Language | English |
Detected Language | English |
Type | Student thesis, info:eu-repo/semantics/bachelorThesis, text |
Format | application/pdf |
Rights | info:eu-repo/semantics/openAccess |
Page generated in 0.3315 seconds