Random initial parameters
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.
Initialization · Describe initial parameters and their distributions.
The current objective supplies a gradient; training updates the model parameters.
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: 2.1 A view through similarity
Θ₀ is the random parameter vector at initialization. A realization fixes one concrete parameter vector and thereby one network function.
Initialization determines the network before training.
Source formula example
illustration · The example fixes one realization; the source specifies independent normal initial entries.
Symbols
- A random initial parameter vector.
- The corresponding network function.
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
theta0=[1, -1]
Calculated here
Result expression: { theta0, input: 2, output: f(2) }
Returns
theta0- array (2 items): [1, -1]
input- 2
output- 1
Read numbers from input and return the result. JavaScript basics.
Result
Technical statement
The numerical values are invented. The example fixes one realization; the source specifies independent normal initial entries.
Source: Inline notation