Zero output weights
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.
Pruning · Describe removal of network weights and related error bounds.
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: 6.5 Removing connections
When the second-layer output weights are all zero, their weighted contribution is zero.
This is the trivial zero-output-weight case in the pruning argument.
Source formula example
illustration · This example covers the contribution of these weights; an additional output bias would need to be included separately.
Symbols
- The output weight vector.
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
weights=[0, 0]features=[2, 3]
Calculated here
Result expression: {
weights,
features,
output: weights.reduce((s, w, i) => s + w * features[i], 0),
}
Returns
weights- array (2 items): [0, 0]
features- array (2 items): [2, 3]
output- 0
Read numbers from input and return the result. JavaScript basics.
Result
Technical statement
The numerical values are invented. This example covers the contribution of these weights; an additional output bias would need to be included separately.
Source: Inline notation