Everyone's talking about AI adoption. Almost nobody has the real numbers. Help us change that — and get the full report 👉 Engineers | Leaders

latent patterns pricing login

Backpropagation

The algorithm that computes gradients by propagating error signals backward through a computation graph using the chain rule.

Latent Patterns is a new platform that teaches AI concepts to developers — through screencasts, technical deep dives, interactive playgrounds, and hands-on courses.

We haven't launched yet. Sign up below and we'll notify you when we open the doors.

[→] RELATED CONTENT

courses

Understanding Micrograd Build a neural network from scratch — Karpathy's autograd engine, neurons, layers, and training — in pure Python with zero dependencies.
Understanding microGPT Walk through Karpathy's 200-line GPT implementation — from autograd and tokenization to multi-head attention, training, and text generation.
Understanding Makemore Build character-level language models from scratch — from bigram counting through MLPs, batch normalization, and WaveNet — generating new names with PyTorch.

lessons

Training and Generating Text Understanding GPT / The Bigram Baseline
Softmax and Weighted Aggregation Understanding GPT / Self-Attention
Feedforward Networks and Residual Connections Understanding GPT / Building the Transformer
Gradient Flow Understanding Makemore / Activations and Batch Normalization
Manual Backpropagation Understanding Makemore / Becoming a Backprop Ninja
The Full Backward Pass Understanding Makemore / Becoming a Backprop Ninja
What Is microGPT? Understanding microGPT / The Big Picture
The Value Class Understanding microGPT / Automatic Differentiation
Backpropagation Understanding microGPT / Automatic Differentiation
Embeddings: Tokens and Positions Understanding microGPT / The Transformer Architecture
RMSNorm: Stabilizing Activations Understanding microGPT / The Transformer Architecture
Multi-Head Attention Understanding microGPT / The Transformer Architecture
The MLP and Residual Connections Understanding microGPT / The Transformer Architecture
Loss and Next-Token Prediction Understanding microGPT / Training
The Adam Optimizer Understanding microGPT / Training
What Is Micrograd? Understanding Micrograd / The Big Picture
Derivatives and Intuition Understanding Micrograd / The Big Picture
Wrapping Scalars Understanding Micrograd / The Value Class
Backward Propagation Understanding Micrograd / The Value Class
The Loss Function Understanding Micrograd / Training
Gradient Descent Understanding Micrograd / Training

learn more?

Subscribe and we'll send new content to your inbox.

learn

courses glossary blog newsletter knuth checks verify

for

enterprise startups consultants bootcamps trainers university government

company

about principles careers press security privacy terms status

connect

x youtube instagram linkedin bluesky discord

© 2026 Latent Patterns