https://bergstrom.org/tags/pytorch/PyTorch - Tag - Jorgen BergstromHugo -- gohugo.ioen-usJorgen BergstromSat, 26 Sep 2026 00:00:00 -0500https://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/nn_hammer_distance_pytorch/Wed, 29 May 2024 00:00:00 -0500Jorgen Bergstromhttps://bergstrom.org/posts/nn_hammer_distance_pytorch/Summary In this example I have used a “Sequential” neural network model to solve the regression problem of how far a hammer will fly given an initial velocity and angle. A sequential model is linear stack of layers, and allows you to create a Neural Network (NN) by simply adding layers sequentially. Both PyTorch and Keras are popular frameworks for building these NN models. Compared to Kears, the PyTorch approach is exposes more details which makes it more flexible and suitable for complex and dynamic models.