Dr. Heuna Kim Mathematics and Computer Science

Satellite Analysis Pitch - Applying Depth Estimation Network

I have given this talk on 8th November 2017.

This talk was given before I started working professionally on satellite data - by then I didn’t know many critical concepts, for example, orthorectification and more.

This talk contains:

  • playing with Sentinel and Landsat imagery via direct access through AWS
  • RGB stacking and manipulation of imagery with ImageMagick
  • playing with open NRW LiDAR data
  • planning of applying depth estimation

The slides: here

Please contact me if you have any followup questions.

You can find my other technical talks in the github repo hahey/Talks.

Normalization Techniques in Deep Neural Networks

The note contains the concept of covariance shift and compares the following normalization techniques in deep learning.

  • batch normalization
  • dropout
  • layer normalization
  • weight normalization
  • skip connection

here is the handwritten note