The Modern Mathematics of Deep Learning

Larger image dimensions

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.

Model classes and structure · Describe families of rules, their size and structural properties.

The project supplies finite observations and fitted parameters. A held-out sample does not establish population bounds or prove a theorem.

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

A 256 × 256 image has 256 rows and 256 columns.

Multiplying dimensions gives the number of spatial positions.

Source formula example

256\times 256

illustration · The result counts spatial positions without any extra color channels.

Symbols

$256 × 256$: The source image dimensions.

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

side = 256

Calculated here

Result expression: { rows: side, columns: side, positions: side * side }

Returns

Example result

rows: 256
columns: 256
positions: ≈65540

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. The result counts spatial positions without any extra color channels.

Source: Inline notation