About me
Hello. My name is Nikola Janjušević. I am a third year PhD candidate in Electrical Engineering at New York University under the advisory of Professor Yao Wang at the NYU VideoLab. I received my Bachelors in Electrical Engineering from The Cooper Union for Advancement of Science and Art.
My current interests are in interpretable deep-learning models for linear inverse-problems and low-level computer-vision/image-processing tasks. My background is in signal-processing and non-smooth, convex optimization. Outside of academia, I go skateboarding with my friends 🛹.
Update
December 2021: Journal article preprint, "CDLNet: Noise-Adaptive Convolutional Dictionary Learning Network for Blind Denoising and Demosaicing", avilable: https://arxiv.org/abs/2112.00913.
Recent blog posts
Welcome to an attempt at simultaneous learning, where I learn to separate skills (Julia programming and TV denoising) without prior knowledge of either! Starring Fabio, and Masa. 
...
Zathura + latexmk -> :). Latest update: 17th January 2021. ...
I often find my downloads folder filling up with tons of research papers with nondescript (ID) names, such as "1909.05742.pdf". Keeping these PDFs open allows me to keep track of them, but once I close those windows they seem as good as lost. To remedy this, I've written a short Python script employing a wrapper for the arXiv.org API. ...
The iterative soft thresholding algorithm is one of the simplest algorithms for sparse coding (in this case, solving the basis-pursuit denoising functional). Understanding its derivation as a special case of the Proximal Gradient Method is a great introduction into the world of proximal methods. ...
© Nikola Janjušević. Last modified: 0001-01-01. Website built with Franklin.jl and the Julia programming language.