TL;DR This blogpost focusses on ML Design and Architecture and tries to give some intuition and hints for deciding between one generalized and multiple specialized models for the same business requriement and dataset. Consider it a nudge to dive deeper into the topic Why should i care? Transparency in machine learning is crucial for business stakeholders because it fosters trust and informed decision-making. Business Stakeholders need to understand not only the potential benefits but also the limitations and risks associated with machine learning models....

What are Transformers Transformers are a type of neural network architecture that was introduced in the paper “Attention is All You Need” by Vaswani et al. in 2017. Since then, it has become one of the most popular and successful models in natural language processing (NLP) tasks such as language translation, summarization, and text classification. Furthermore it is the foundation for Language Models and their application. The key innovation of the Transformer architecture is the use of attention mechanisms....

I enlisted for the free Get Certified Program from Google in June 2023 which offers a 10 week curated curriculum to prepare for the Data Engineer exam. Unfortunately the content is restricted and cannot be shared. Following article should summarize all additional sources which were helpful for me in preparation of the certification exam. If you are interested in how the exam is actually happening there are plenty of other articles on medium or at other places....

TL;DR A short summary on (Large) Language Models: What are the ideas and concepts behind Language Models? What are Language Models Large Language Models are rapidly transforming natural language processing tasks and have led to a huge hype around Artificial Intelligence and associated tasks. Especially with the introduction of GPT3.5(ChatGPT) in 2022 many people are interested in the capabilities of ML. But what is the foundation for the products that could impact our future world significantly?...

TL;DR Learn how to train a Reinforcement Learning Agent to play GameBoy games in a Python written Emulator. With PyBoy, Q-Learning and Super Mario. Train your own RL Agent to play Super Mario Recently i stumbled upon my old GameBoy an immediately started it and tried to start where i left off 20 years ago. Unfortunately my hand eye coordination is not what it used to be so i died a few fast deaths....