convnet
> 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
papers
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
gans
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