All interactives
Deep Learning · Lecture 2 ReLU Function Lab

ONE-DIMENSIONAL WITNESS

Build a function from ReLU hinges.

Construct an interpolant that is guaranteed by its knots, then train the same kind of network from a deterministic random start. Keep existence and optimization as separate claims.

CONSTRUCTED WITNESS

Sine · fixed-knot interpolation

Grid gap ≥ ε
Training-sample MSEnot trained
Dense-grid MSE0.0000401 evaluation points
Max grid gap0.000max of 401 gaps
Gradient steps019 parameters

TARGET + MODEL

Can the blue curve stay inside the ε band?

ĝ(x) = c + Σ vⱼ ReLU(wⱼx + bⱼ)

Target f(x) Approximation ĝ(x) f(x) ± ε Interpolation knots

Drag an orange interior knot left or right; endpoint knots stay fixed.

ERROR

Pointwise gap |f(x) − ĝ(x)|

max at x = 0.00

MODEL CONTRACT

One input → six ReLUs → one output

Source
Fixed knots
Output bias c
0.000
Objective
No optimization
Evaluation
401-point grid

This construction is a witness for this target and width. It does not show that gradient descent would discover the same weights.

SIGNED HINGE FUNCTIONS

The output is the bias plus every contribution below.

Shared vertical scale ±1.00

All cards use the same zero-centred y-scale. A small curve is genuinely a small contribution.

USE IN CLASS

Change one thing. Predict first.

  1. Capacity: add hinges; predict where the largest gap will move.
  2. Optimization: keep width fixed; compare two initialization seeds.
  3. Theorem: say what existence promises, then name what this optimizer run does not prove.