Now showing items 1-2 of 2
Pluggable Properties for Program Understanding: Ontic Type Checking and Inference
(University of Waterloo, 2018-04-26)
Pluggable type systems is a powerful approach to add additional information on types, which can facilitate the understanding of programs. This thesis presents our work on three pluggable type systems for helping both ...
Convolutional Neural Networks for Land-cover Classification Using Multispectral Airborne Laser Scanning Data
(University of Waterloo, 2018-09-21)
With the spread of urban culture, urbanisation is progressing rapidly and globally. Accurate and update land cover (LC) information becomes increasingly critical for protecting ecosystems, climate change studies and ...