Skip to content
View mark-antal-csizmadia's full-sized avatar
🔥
making things lit with ML
🔥
making things lit with ML

Highlights

  • Pro
Block or Report

Block or report mark-antal-csizmadia

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse

Hello there!

MSc Embedded Systems Engineering BSc Electrical and Electronic Engineering

I am Márk Antal Csizmadia, a machine learning engineer at Sellpy. I graduated in 2022 at KTH Royal Institute of Technology in Stockholm, Sweden with a Master of Science degree in Machine Learning, and in 2020 from the University of Manchester with a Bachelor of Engineering in Electronic Engineering degree. I'm originally from Budapest, Hungary .

My goal is to use my knowledge of machine learning, deep learning, IoT, and cloud computing to work on solving exciting problems and to positively influence our future. While doing so, I enjoy learning new technologies and tools, and getting to know like-minded, motivated people on the way.

🙏 Selected Projects

Readme Card Readme Card Readme Card Readme Card Readme Card Readme Card Readme Card Readme Card

👐 Other Projects

Readme Card Readme Card Readme Card Readme Card Readme Card Readme Card

🔧 Tech Stack

📈 Stats

💯 My Dataset

I built and published an annotated object detection dataset titled Object Detection: Batteries, Dice, and Toy Cars. The annotated objects in the dataset include six-sided board game dice, AAA, AA, and 9 V batteries, toy cars, spoons, highlighters, and tea candles. The dataset was built through different means that included scraping images off the Internet with the Bing Image Search API, remixing existing datasets from the public domain, extracting video frames from videos downloaded from YouTube in line with its fair-use policy, and manually taking photographs. There are in overall 1644 images in the dataset that contain 2815 objects. I shared a starter notebook for exploring the dataset on Kaggle. The dataset Usability Score is 8.8 / 10.0.

📨 Contact

Pinned

  1. DD2434-VAE-Project DD2434-VAE-Project Public

    Replication of the research paper titled Auto-Encoding Variational Bayes.

    Python 1

  2. nn-blocks nn-blocks Public

    A neural network library built from scratch, without dedicated deep learning packages. Training and testing deep neural networks and utilizing deep learning best practices for multi-class classific…

    Jupyter Notebook 1

  3. dcgan-fake-faces dcgan-fake-faces Public

    Deep convolutional generative adversarial networks (DCGANs) for generating fake faces with Tensorflow and Keras.

    Jupyter Notebook

  4. re-sln re-sln Public

    Re-implementation of the paper titled "Noise against noise: stochastic label noise helps combat inherent label noise" from ICLR 2021.

    Python 1

  5. slp-mlp slp-mlp Public

    Single Layer Perceptrons (SLPs) and Multi-Layer Perceptrons (MLPs) from scratch, only with numpy, for classification and regression. MLPs with Keras for time-series prediction.

    Jupyter Notebook

  6. som som Public

    Kohonen Self-Organizing Maps (SOMs) for dimensionality reduction, data embedding, and solving a variant of the travelling salesman problem.

    Jupyter Notebook 1