Parameters and depth product
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: 2.2 Weight size and room to decide
P(N)L multiplies the network parameter count by its depth.
This factor occurs in an architecture complexity estimate.
Source formula example
illustration · This evaluates one product; it does not establish a complexity bound.
Symbols
- The number of network parameters.
- The network depth.
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
Code changed. Reset to restore this example’s data flow.
Initial values in code
P=13L=2
Calculated here
Result expression: { parameterCount: P, L, product: P * L }
Returns
parameterCount- 13
L- 2
product- 26
Read numbers from input and return the result. JavaScript basics.
Result
Technical statement
The numerical values are invented. This evaluates one product; it does not establish a complexity bound.
Source: Inline notation