AI with Catherine Ordun

Sign in Subscribe

Catherine Ordun

Catherine Ordun

PhD Student at UMBC - Healthcare AI and Computer Vision

"How transferable are features in deep neural networks"

"How transferable are features in deep neural networks"

> A paper review of Yosinski, Jason, et al. "How transferable are features in deep neural networks?." Advances in neural information processing systems. 2014. [https://proceedings.neurips.cc/paper/2014/file/375c71349b295fbe2dcdca9206f20a06-Paper.pdf] Slides available here [https://docs.google.com/presentation/d/1uZuEPV_Y3apUpZ6DGUkHwpW9m5RwF2QOfqYpKxnzRFk/edit?usp=sharing] . Summary

"Reinforcement learning with deep energy-based policies"

"Reinforcement learning with deep energy-based policies"

It's been a very long time since I've last posted, and at last I've come up for some air after writing a few papers and a lot of code. One thing I've come to appreciate in my PhD studies is the frequent

What is AutoGAN?

What is AutoGAN?

AutoGAN is an architecture search strategy developed by Gong, et al. in 2019 to find the most optimal Generator network architecture using reinforcement learning, trained to generate images from CIFAR-10 and STL-10. To understand how AutoGAN works requires an understanding of the basics of Neural Architecture Search (NAS). This post

Survey of Object Detection

Survey of Object Detection

Several years ago I implemented GoogLeNet on the Jetson TX2. Since then I've been dealing with object detection problems both from a data scientist side, and also team leader side. > Finally got the #Jetsontx2 [https://twitter.com/hashtag/Jetsontx2?src=hash&ref_src=twsrc%5Etfw] up

Haarcascades to filter out non-Frontally Aligned Faces

Haarcascades to filter out non-Frontally Aligned Faces

I'm sure many of you have used OpenCV for a variety of work. Most of the time, in the case of face detection, we want to know if the classifier has a detected a face. Here, I actually want to know the reverse - where has it NOT

Using brokenaxes to plot discontinuous time

Using brokenaxes to plot discontinuous time

I've been plotting the results of some Covid19 Twitter data analysis, but it's on discontinuous corpora of time. I was making so many plots to capture distinct chunks of time that my paper was getting more and more difficult to read! My advisor suggested I check

Faster, more Pythonic

Faster, more Pythonic

I've been working on a paper analyzing Covid-19 tweets. I've finally hit a wall where I've successfully generated a variety of topic models. However, now I have to assign/predict the topics to each of my tweets. We're talking dozens of millions.