Neural Nets·Course
Neural Networks & Deep Learning
Neural networks: perceptron, backpropagation, CNNs and RNNs, transformers, and modern architectures
Part of the Mathematics track — finish it for a verifiable diploma →
§ 01 — Orientation
New here?
What you'll be able to do, who this is for, how long it takes, and where to begin.
By the end, you will be able to
- 01Understand how a neural network learns.
- 02Build with CNNs and RNNs.
- 03Explain how transformers work.
- 04Understand the generative models behind modern AI.
- 05Read a deep-learning paper without drowning.
Who this is for
How long it takes
- Quick orientationSkim the opening module and the cheatsheet to get the shape of it.~2 h
- Full read-throughRead every article once, in order.~2 h
- Mastery pathRead, take the quizzes, and space out your reviews.~2 weeks
- APA
Stoa. (2026). Neural Networks & Deep Learning [Online course]. Stoa. https://stoa.school/course/neural-systems
- MLA
Stoa. “Neural Networks & Deep Learning.” Stoa, 2026, https://stoa.school/course/neural-systems.
- Chicago
Stoa. “Neural Networks & Deep Learning.” Stoa. Accessed September 1, 2026. https://stoa.school/course/neural-systems.
§ 02 — Curriculum
5 modules.
Each module is a small unit. Most read in sequence — but a determined reader can begin anywhere.
- M IFundamentals of Neural NetworksPerceptrons, multilayer networks, and the backpropagation algorithm3 articles
18 minBegin → - M IIDeep Learning: Theory and PracticeOptimization, normalization, and advanced architectures3 articles
18 minBegin → - M IIIRecurrent Neural NetworksLSTM, GRU, sequence modeling, and NLP3 articles
18 minBegin → - M IVGenerative ModelsGANs, VAEs, diffusion models, and data generation3 articles
18 minBegin → - M VTransformers and Large Language ModelsThe attention mechanism, BERT, GPT, and the LLM era3 articles
18 minBegin →
§ 03 — Learning outcomes
4 outcomes.
Understand neural network architectures, activation functions, and backpropagation
Design and apply convolutional and recurrent architectures
Understand the attention mechanism and transformer architectures
Work with autoencoders, GANs, and diffusion models
§ 04 — Practices