Posts
-
Thought of the Day 18 01 2025
In Physics deepeste levels of reality are described by tensors and probability.
It is no wonder that our artificial intelligence models are the same.
Jan 18, 2025 -
Elements of Local LLM Running & Inferrence
Locally run Large Language Models (LLM) are Neural Networks for Natural Language Processing usually based on Transformers model architecture. Major breakthrough was publishing of “Attention is all you need” paper on arXiv.
Due to comparatively small size of models published for local inference it has led to proliferation of Large Language Models and further introduction to all users who run them worldwide.
These models come in various shapes (model architectures) and sizes.
Jan 17, 2025 -
Machine Learning Using YOLOv5
One of the finer examples for acessible and powerful Machine Learning frameworks is YOLO (You Only Look Once) in particular YOLOv5.
This framework enables for Neural Network based Computer Vision system for object detection and real time frame analysis.
(<GitHub - ultralytics/yolov5: YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite>)
Some of YOLOv5 feature include:
Training custom vision models, multi-gpu training, multi-stream inference, custom training datasets, specialized models for specific or custom object classes and detailed logging and analytics.
Jan 16, 2025 -
Basic Ethics
It is important to note basic ethical considerations when dealing with Machine Learning, Artificial Intelligence and advanced prospects for its development in the future.
I firmly belive in the future where AI can and will be a useful tool for advancing humanity’s efforts in education, (software) development and even research.
It is important that the use of high quality and high level technology is ethical, actively engineered to avoid any bias, successful at performing tasks and generally benefical and benevolent.
Jan 16, 2025 -
Taking AI prospects as seriously inspiring
The beginning of my AI/ML journey started with Tensorflow running on my computer 5 years ago.
I have attempted some similar algorithms in the past, even in the distant past like finding the optimal path for a skier to go down the slope of a mountain, flood fill in assembly so that I could develop my own efficient way to fill shapes for an interface I was building on my 386 computer.
Jan 16, 2025 -
How it all began
My first experiences understanding that AI might be available for human interaction in the future formed when I was 7-10 years old.
The year was 1991.
I was fortunate enough to have a Commodore 64 8 bit computer when I was about to start elementary school.
At first I though of using the for games but I discovered that you can use it as a calculator and make it print stuff, create loops, use oneliners like:
Jan 16, 2025 -
Copyright
© 2025 Marko Radojčić. All rights reserved.
We’re glad you’re enjoying this creation! Feel free to share and reference it, but please respect the effort and love that went into it. If you’d like to use it in your own work, just reach out for permission—we’re happy to collaborate and keep things fair. 😊
Thank you for being awesome and for supporting creativity!
Jan 16, 2025 -
Introduction
This is my first blog post about my AI adventures.
Website is up.
More content coming soon.
Jan 15, 2025