Learn how to identify activation functions like ReLU, sigmoid, tanh, and ELU in CNNs with this detailed explanation. Perfect for your Convolutional Neural Network certification exam preparation!
Table of Contents
Question
What activation function is it?
A. sigmoid
B. tanh
C. ReLU
D. ELU
Answer
C. ReLU
Explanation
The graph in the image represents the Rectified Linear Unit (ReLU) activation function. Here’s why:
Behavior of ReLU
- For inputs x<0, the output is 0, resulting in a flat line along the x-axis.
- For inputs x≥0, the output is x, producing a linear increase.
Key Characteristics
- The graph transitions sharply at x=0, where the slope changes from 0 (for negative inputs) to 1 (for non-negative inputs).
- This matches the mathematical definition of ReLU: f(x)=max(0,x)
Comparison with Other Options
Sigmoid (A): Produces an S-shaped curve ranging from 0 to 1, not flat or linear.
Tanh (B): Outputs values between −1 and 1 with an S-shaped curve.
ELU (D): Similar to ReLU but smooths negative values with exponential decay, unlike the flat line seen here.
Thus, the graph perfectly aligns with the properties of the ReLU activation function.
Convolutional Neural Network CNN certification exam assessment practice question and answer (Q&A) dump including multiple choice questions (MCQ) and objective type questions, with detail explanation and reference available free, helpful to pass the Convolutional Neural Network CNN exam and earn Convolutional Neural Network CNN certification.