Want to share your content on R-bloggers? click here if you have a blog, or here if you don't.
Its been a while since I last posted anything on my blog, so I thought I would share an update. Recently, I had the opportunity to present for my midterm examination a deep learning framework of my choosing. I chose to give a talk on (you guessed it!) convolutional neural networks (CNNs) and their application in the space of computer vision.
For the technical background I took the introductory material from the paper “Convolutional neural networks: an overview and application in radiology” by Yamashita, Nishio, Do and Togashi from the Journal “Insights into Imaging” (Published June 27, 2018). For the applications I produced some original analysis using some of the toy data sets provided by keras (MNIST numbers and the CFAIR-10 datasets) and compared how convolutional neural networks preformed relative to simple feed forward networks.
Concluding remarks were based on the publicly available jupyter notebook written by well known python-programming Youtuber Tech with Tim here (if you are reading this – thank you for the resource Tim!)
As far as the actual Jupyter Notebook with the code I used, when I get some time I hope to reformat it and have it available to see!
Below are the slides I used for this talk. Let me know what you think!
R-bloggers.com offers daily e-mail updates about R news and tutorials about learning R and many other topics. Click here if you're looking to post or find an R/data-science job.
Want to share your content on R-bloggers? click here if you have a blog, or here if you don't.