A nonzero activation
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.
Prediction rules and layers · Describe or apply prediction rules, layers and parameters.
The project uses a linear rule with two features. The fitted weights produce scores or normalized mass.
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: 1.2.2 Can the network express the answer?
ϱ ≠ 0 means the activation is not identically zero: it has a nonzero value for at least one input.
A constant neuron can then be chosen with nonzero output.
Source formula example
illustration · ReLU supplies one example; a general nonzero activation can have different values.
Symbols
- An activation 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
x=1
Calculated here
Result expression: { x, value: rho(x), nonzero: rho(x) !== 0 }
Returns
x- 1
value- 1
nonzero- true
Read numbers from input and return the result. JavaScript basics.
Result
Technical statement
The numerical values are invented. ReLU supplies one example; a general nonzero activation can have different values.
Source: Inline notation