Kamiel Temmerman
Data Scientist |AI Engineer
Bazel, Belgium
Actions
I work at the intersection of data science and AI engineering. My focus is simple: turning data and AI ideas into systems that work. In practice, that means understanding the problem, building a solution, and making sure the result creates value.
My projects span machine learning, LLM applications, and some data engineering. I have worked on GLM-based pricing models, time-series forecasting, survival analyses, RAG applications, agentic workflows, GenBI prototypes, and dbt-based data engineering. The technical work I enjoy most is building production-grade ML systems end to end: transforming raw data into features, training and validating models, deploying scoring pipelines, and setting up monitoring so outputs stay reliable over time.
My broader life goal is learning. I read and think deeply about AI and machine learning (Why Greatness Cannot Be Planned is fantastic), software engineering, business and technology (I love Nassim Nicholas Taleb’s books, and The Almanack of Naval Ravikant is great), entrepreneurship (Founders and Acquired podcasts, founders’ biographies; James Dyson’s first autobiography is great), science (I love biographies of scientists like Claude Shannon and Edward Thorp; Benjamin Labatut’s The MANIAC is excellent, and David Deutsch’s The Beginning of Infinity is the best non-fiction science book I’ve read), and the economics of technology (The Innovator’s Dilemma by Clayton M. Christensen).
Links
Area of Expertise
Topics
Neural Networks from Scratch
Neural networks power many of today’s most impactful AI applications. Yet most practitioners interact with them through high-level frameworks, making it difficult to truly understand what is happening under the hood.
In this session, we will demystify neural networks by building one from scratch using core Python. Instead of relying on deep learning libraries, we will implement the key building blocks ourselves to see how neural networks learn from data and improve over time. We will translate theory into functional code and develop a clear intuition for forward propagation, backpropagation, gradient descent, and loss optimization.
Beyond theory, we will connect these fundamentals to practical AI development. Once you understand how training works, it becomes much easier to adapt and improve modern AI systems in production. For example, we will explore how techniques such as LoRA (Low-Rank Adaptation) allow companies to efficiently fine-tune large language models without retraining the entire network, dramatically reducing cost and compute requirements.
Having a strong mental model of these mechanisms is extremely valuable in practice. It helps you debug training issues, interpret model behavior, and make better decisions when designing or fine-tuning machine learning systems. By the end of the session, you will understand how a neural network learns step by step, how to implement a simple one yourself, and how these principles can be applied to build and adapt agentic AI solutions that help tackle real-world business problems.
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top