SebastianRaschka.com is the personal blog of Sebastian Raschka, PhD, an LLM research engineer whose work bridges academia and industry in AI and machine learning. On his blog and notes section he publishes deep, well-documented articles on topics such as LLMs (large language models), reasoning models, machine learning in Python, neural networks, data science workflows, and deep learning architecture. Recent posts explore advanced themes like “reasoning LLMs”, comparisons of modern open-weight transformer architectures, and guides for building, training, or analyzing neural networks and model internals.
110 articles from this blog
A professor reflects on teaching new Machine Learning and Deep Learning courses at UW-Madison and showcases impressive student projects.
Research on using semi-adversarial neural networks to generate gender-neutral face images, enhancing privacy while preserving biometric utility.
A guide to model evaluation, selection, and algorithm comparison in machine learning to ensure models generalize well to new data.
Author shares the journey and process of writing 'Python Machine Learning,' a technical book for aspiring machine learning practitioners.
A scientist explains why Python is their preferred language for machine learning and data analysis, arguing for productivity over language wars.
An introduction to single-layer neural networks, covering the Perceptron and Adaline models, with Python implementations and gradient descent.
A tutorial explaining Principal Component Analysis (PCA), a dimensionality reduction technique used in machine learning and data analysis.
A guide to implementing a weighted majority rule ensemble classifier in scikit-learn to combine different ML models and improve prediction accuracy.
A developer shares their experience building a machine learning model to classify song moods (happy/sad) based on lyrics using Python and NLP.
A Python tutorial showing how to download your Twitter timeline and visualize it as a word cloud using data science libraries.
An introduction to Naive Bayes classifiers, focusing on their theory and application in text classification tasks like spam filtering.
A guide to performing nonlinear dimensionality reduction using RBF Kernel PCA, including theory, implementation, and examples.
An overview of predictive modeling, supervised machine learning, and pattern classification concepts, workflows, and applications.
A technical guide to Linear Discriminant Analysis (LDA) for dimensionality reduction and classification in machine learning, including a Python implementation.
A guide to feature scaling and normalization in machine learning, covering standardization, Min-Max scaling, and their implementation in scikit-learn.
A Python tutorial covering essential tools and techniques for machine learning, including data visualization, PCA, LDA, and classification.
Learn how to use Python's multiprocessing module for parallel programming to overcome the GIL and utilize multiple CPU cores effectively.
A technical guide to the Parzen-Rosenblatt window method for non-parametric kernel density estimation, including implementation and applications.
A cheat sheet comparing matrix operations across MATLAB/Octave, Python (NumPy), R, and Julia for scientific computing and data analysis.
A guide explaining the key differences between Python 2.7.x and Python 3.x, covering syntax changes, features, and common pitfalls.
