How neural networks turn inputs into predictions, how they learn with gradient descent, and how to train one in PyTorch.
Neural networks power modern AI, from image recognition to language models. This course builds the core ideas from a single neuron up to a trained network, then puts them into practice with PyTorch on the wine quality dataset from the hub.
Install with pip install torch pandas scikit-learn.
4 lessons · 1 hr 6 min
Weighted sums, activation functions and layers.
Loss functions, gradients, backpropagation and the learning rate.
A complete training loop on the wine quality data.
Overfitting, dropout, early stopping and when to use a pretrained model.
No ratings yet.
Sign in to leave a rating. Sign in
Use @handle to bring somebody in, and #tag to file it.
Nothing here yet. Ask a question, or say how you used it.
Sign in to join the discussion. Sign in
2 min read
2 min read
2 min read
2 min read
Build, compare and evaluate a real classifier end to end, predicting penguin species from their measurements.
Google's free, fast-paced introduction to machine learning, with videos, visualisations and exercises.
A free, code-first course by Jeremy Howard that has you training state-of-the-art models from the first lesson.