Hello. My name is Nikola Janjušević. I am a fourth year **PhD candidate in Electrical Engineering** at *New York University* under the advisory of Professor Yao Wang, NYU VideoLab. I received my Bachelors in Electrical Engineering from *The Cooper Union for Advancement of Science and Art* in 2019.

My current interests are in *interpretable deep-learning* models for solving *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 biking and skateboarding with my friends.

August 2023:

*"Self-Supervised Low-Field MRI Denoising via Spatial Noise Adaptive CDLNet"*abstract accepted to NYU CAI2R i2i Workshop.August 2023: SSIMLoss.jl, differentiable SSIM loss functions for neural network training, package published.

June 2023: Joined NYU Langone Department of Radiology as a Non-Traditional Volunteer Intern, working on unsupervised learning for MRI denoising and CS-MRI reconstruction.

June 2023:

*"Fast and Interpretable Nonlocal Neural Networks for Image Denoising via Group-Sparse Convolutional Dictionary Learning"*submitted to IEEE Transactions on Image Processing. Preprint available on arxiv.

TLDR: employing the multi-dimensional chain-rule means writing matrix-multiplication. ...

Convolutional Neural Networks' building blocks aren't just performing the convolution you learned in DSP. In my opinion, the best way to think of these layers is as a channel-wise matrix-vector multiplication of convolutions. ...

So-called interpretably constructed deep neural networks often sell their methods by showing near state-of-the-art performance for only a fraction of the parameter count of black-box networks. However, can we consider these fair comparisons when the number of learned parameter counts are not matched? ...

A walkthrough of implementing Total Variation color image denoising in the Julia programming language, starring Fabio and Masa. ...

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**. ...

Zathura + latexmk -> :). Latest update: 17th January 2021. ...