Neural Systems from Computation Graphs

Connect affine maps and nonlinearities to representation capacity.

Concept labFoundation80 min estimateArtifact: Neuron representation audit

Represent forward values, dependencies, and local derivatives explicitly.

Build labIntermediate90 min estimateArtifact: Computation graph trace validator

Derive reverse-mode autodiff as small, testable vector-Jacobian products rather than one mysterious global formula.

Build labIntermediate120 min estimateArtifact: Tiny autodiff engine and tests

Use loss curves, gradient statistics, and parameter updates to separate data, optimization, and capacity failures.

Failure labIntermediate105 min estimateArtifact: Optimization dynamics diagnostic

Understand why signal and gradient paths shape trainability in deep networks.

Concept labAdvanced105 min estimateArtifact: Signal path contract

Build a convolution and connect weight sharing to images, audio, and structured grids.

Build labIntermediate105 min estimateArtifact: Convolution equivariance audit

Trace a realistic failure through inputs, precision, activations, gradients, and optimizer state.

Failure labAdvanced110 min estimateArtifact: Neural training incident runbook