ReLU 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 Learning from examples · 1.3 The questions ahead · 3.2 Simple pieces, many layers · More source sections
ReLU returns zero for negative inputs and the input itself otherwise.
Nonlinear activations allow networks to represent more than linear maps.
Source formula example
exact · The result is exact for these finite toy inputs, apart from ordinary computer rounding.
Symbols
- A real number.
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.x= -2
Calculated here
Result expression: { input: input.x, output: Math.max(0, input.x) }
Returns
input- -2
output- 0
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: ReLU