Pruning 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
Keep selected output weights and replace the others with zero.
Pruning removes some connections or units from a network.
Source formula example
illustration · This manually chosen mask illustrates pruning. It does not establish the source error bound or choose an optimal mask.
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.
You choose
input.first= 1
Initial values in code
keep=[true, false, true]
Calculated here
Result expression: { before: weights, after: weights.map((weight, i) => (keep[i] ? weight : 0)) }
weights=[input.first, 2, -1]Uses:input.first
Returns
before- array (3 items): [1, 2, -1]
after- array (3 items): [1, 0, -1]
Read numbers from input and return the result. JavaScript basics.
Result
Technical statement
Change the input and run the same code again. The displayed result uses the values shown above.
Source: Pruned weights