Figure 1. Jeronim with his 1070TI GPU, that has fans from aliexpress that don't really fit so he has to reapply the duct tape every now and then.
Hello there, I am Jeronim Matijević
I’m currently koding at a company called Intis
Big fan of CLIP
backprop is the closest thing we have to magic
My ML Blog
On the link above you can find my ML blog + short comments on various deep learning projects i have done over the years, reach out about anything if you have any questions
Slides
I sometimes talk about ML papers. If i told you you can find the slides on my site, here they are. Most of these, but not all are from our paperclub
Scalable Diffusion Models with Transformers
FreeU : Free Lunch in Diffusion U-Net
Patch n’ Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution
Lottery ticket hypothesis, but actually the Han et al. pruning paper
Interesting Deep Learning material
- Very good + free computer vision “basics” lectures from the University of Columbia
- MIT course on python, very good course + material
- Most understandable material on LSTMs
- Letitia making youtube videos about ML papers
- Yannic making youtube videos about ML papers
- Károly making youtube videos about ML papers
- Must read Karpathy blog on RNNs
- Zero to Hero Karpathy videos
- Funny loss functions blog
- Comparisons of recent nvidia GPUs for deep learning
- nvidia-smi blogpost
- blogpost about demystifying RAM usage in multiprocess pytorch dataloaders
- Spark of AGI talk by Sebastian Bubeck - this picture predicted it all
misc stuff on the internet
- manim - very cool library for math visualization, used by 3blue1brown
- dingboard
- jspaint
- Very important research
- Vaisko
- Smile.rip
- marulianus.hr
- Auralnauts
- programemezzz
- How i sometimes feel about ML research
- Have you tried using ffmpeg?
- The informaticar starog kova blog - it was shut down in 2019 but some parts of it are accessible by the wayback machine. He also wrote a book
Life Goals
- To own a small boat
- Hold a computer vision course at Kopilica