Chapter 5: Deep neural networks
Classical algorithms — linear regression, SVM, boosting — work well on tabular data. But a 224×224 image is 150 thousand features. A word in text is a vector with thousands of dimensions. Deep neural networks were built for such problems: hierarchical functions that learn the right features. This chapter is built around PyTorch — from the perceptron to modern optimizers. Each lesson is one fundamental building block.
Content is available with subscription.
Get full access to all courses on the platform for one year with a single payment.
▼
Unlike other platforms that charge per course, here you get everything for one price, and after one year of use there will be no automatic charge for the following year.