Hey there, my name is Daniel,
a full-blooded musician 
jodaas
SoundCloud Artist
Music Producer from Hamburg, Germany
and master student in the fields of AI and Data Science as well as a student AI & Data Scientist at Statista+.
jodaas
SoundCloud Artist
About Me and my Research Interests
I am mostly focused on deep learning for time series data of physical systems, especially in the fields of audio. My research started around transformer architectures, but has since shifted towards how generative models like diffusion and flow matching can be trained to simulate the solutions of ODEs and PDEs, rather than solving them in the classical sense.
Latest Posts
All posts
Ordinary Differential Equations and Neural ODEs
From the mathematics of change to neural networks that learn dynamics — understanding ODEs, numerical solvers, and how modern generative models are ODEs in disguise.
The Mathematics Behind Flow and Diffusion Models
A deep dive into the mathematical foundations of flow-based models and diffusion processes in deep learning.
Context-Parametric Inversion
A controlled faithfulness study on how QASPER fine-tuning affects context reliance across a RAG pipeline for NLP research papers.
Dual-Midi Transformer
A recap of my work on the Dual-Midi Transformer project, which aims to generate music from MIDI data.
An introduction into Artificial Music Generation
A comprehensive overview of the current state of music generation techniques
Introduction to Gradient Descent
An introduction into Neural Networks, Gradient Descent and Backpropagation.
Recent Projects
All projectsDual MIDI Transformer
A MIDI Event based transformer architecture, utilizing two seperate transformers operating on the global MIDI events and local event parameters.
Basic MIDI Transformer
A basic transformer architecture for MIDI generation, utilizing a single decoder to enable faster training and inference speed.
MoodWave
A real-time streaming pipeline correlating German news sentiment (GDELT) with Spotify Top 200 musical features, using Kafka and Spark Streaming for dual-stream aggregation.
Want to collaborate?
Always open to talk, feel free to leave me a message!