# Overview — 6.7960

https://deeplearning6-7960.github.io/materials/demos/approximation/index.html

(made with Claude Code and ChatGPT)
[All demos](https://deeplearning6-7960.github.io/materials/demos/index.html)[Overview](https://deeplearning6-7960.github.io/materials/demos/approximation/index.html)[01 Approximation](https://deeplearning6-7960.github.io/materials/demos/approximation/relu-approx.html)[02 Effect of ReLU on Kinks](https://deeplearning6-7960.github.io/materials/demos/approximation/bias.html)[03 Width vs Depth](https://deeplearning6-7960.github.io/materials/demos/approximation/width-depth.html)[04 Sinusoidal Positional Encoding](https://deeplearning6-7960.github.io/materials/demos/approximation/posenc.html)
MIT 6.7960 — Approximation Theory
# Overview
From one ReLU to learned functions, network shape, and richer inputs.
  * [ 01 — Approximation Fit a 1D target with a two-layer ReLU MLP. Slide H to see how more hidden units improve the piecewise-linear approximation. ](https://deeplearning6-7960.github.io/materials/demos/approximation/relu-approx.html)
  * [02 — Effect of ReLU on Kinks Shift different functions with bias and see how ReLU creates or removes kinks, including on the Telgarsky sawtooth.](https://deeplearning6-7960.github.io/materials/demos/approximation/bias.html)
  * [ 03 — Width vs Depth Fix the total neuron budget N, then vary the aspect ratio (width/depth). Compare wide-shallow vs narrow-deep networks on the same task. ](https://deeplearning6-7960.github.io/materials/demos/approximation/width-depth.html)
  * [ 04 — Sinusoidal Positional Encoding Side-by-side: plain MLP vs pos-enc MLP fitting a noisy scatter plot. Drag H and L to see how encoding unlocks high-frequency fitting. ](https://deeplearning6-7960.github.io/materials/demos/approximation/posenc.html)