The Modern Mathematics of Deep Learning

Noise in the polynomial example

Penguin learning project

The project uses 342 complete Palmer penguin records: 240 training-pool and 102 held-out rows. The selected training rows determine feature scaling and model parameters. Source CSV

This project trains weights with softmax, unlike the homepage lab, which uses nearest species averages. Same penguin measurements; different classification methods. Predictions can differ.

Probability and expectation · Describe random variables and their averages under a law.

Project vectors have two features; the training matrix has n rows and two columns. Mathematical tools may operate on these values when their assumptions apply.

Consider this concept alongside the project; its source assumptions may differ. These observations do not prove a theorem.

Input: 12 × 2; Held-out evaluation: 102 · #58 · 40.6 mm, 193 mm. Known answer: Adélie; Prediction: Adélie · [≈0.7383, ≈0.2444, ≈0.01737].

Used in these source sections: 1.3 The questions ahead

The source specifies a normal noise variable ν with mean 0 and variance 0.01.

The noise distribution is part of the example data model.

Source formula example

\nu\sim{\mathcal{N}}(0,0.01)

illustration · This computes a distribution parameter; it does not draw noise or reproduce the figure.

Symbols

$ν$: A normally distributed noise variable.
$𝒩(0,0.01)$: The normal law with mean 0 and variance 0.01.

Source formula example

This source example uses its own inputs and assumptions. Editing it does not change the project.

Edit a value or the code, then run the example. This is a finite demonstration, not a proof of the paper’s theorem.

This example’s data flow

Initial values in code

mean = 0
variance = 0.01

Calculated here

Result expression: { mean, variance, standardDeviation: Math.sqrt(variance) }

Returns

Example result

mean: 0
variance: 0.01
standardDeviation: 0.1

JavaScript

Read numbers from input and return the result. JavaScript basics.

Result

Enable JavaScript to run this example.

Technical statement

The numerical values are invented unless the source values are stated. This computes a distribution parameter; it does not draw noise or reproduce the figure.

Source: Inline notation