https://bergstrom.org/tags/ml/ML - Tag - Jorgen BergstromHugo -- gohugo.ioen-usJorgen BergstromSat, 26 Sep 2026 00:00:00 -0500https://bergstrom.org/posts/scalar_autograd_nn/Sat, 26 Sep 2026 00:00:00 -0500Jorgen Bergstromhttps://bergstrom.org/posts/scalar_autograd_nn/Introduction In the previous article we built engine.py: a complete reverse-mode automatic differentiation engine in about 80 lines, built around a single Value class. That engine knows how to record arithmetic on scalars and hand back the gradient of the final result with respect to every scalar that fed into it. This article builds the next layer on top: nn.py, a small neural-network library in roughly 60 lines (heres the repo).https://bergstrom.org/posts/cancer_prediction/Sat, 26 Sep 2026 00:00:00 -0500Jorgen Bergstromhttps://bergstrom.org/posts/cancer_prediction/Introduction In the first two articles of this series we built a reverse-mode autograd engine (engine.py) and a small neural-network library on top of it (nn.py). Together they are about 140 lines of pure Python with no numerical dependencies beyond the standard library. This article puts them to work on a real problem: predicting whether a breast tumor is malignant from measurements taken from a digitized image. The script is cancer_prediction.https://bergstrom.org/posts/scalar_autograd/Thu, 24 Sep 2026 00:00:00 -0500Jorgen Bergstromhttps://bergstrom.org/posts/scalar_autograd/Introduction engine.py is a complete reverse-mode automatic differentiation engine in about 80 lines (heres the repo). It has a single class, Value, that wraps one scalar and remembers how that scalar was computed, so that calling .backward() fills in the derivative of the final value with respect to every value that fed into it. It’s the same core idea as PyTorch’s autograd, just small enough to read in one sitting. The code is also strongly influenced by Karpathy’s micrograd repo.https://bergstrom.org/posts/set_up_python_for_ml/Sun, 17 Mar 2024 00:00:00 -0500Jorgen Bergstromhttps://bergstrom.org/posts/set_up_python_for_ml/Background You can use any computer language for learning, coding, and solving Machine Learning (ML) problems. The most common language to use is Python. The main reason for this is that there are many high quality libraries of ML algorithms already written and freely available for Python (e.g. PyTorch, TensorFlow, and Keras). This makes it really easy to get started and to try things out. One main design feature of Python is that the core language is relatively small, and additional features are added through external packages.