lesson1Title

lesson2Title

lesson3Title

lesson4Title

lesson5Title

lesson6Title

lesson7Title

lesson8Title

lesson9Title

lesson10Title

lesson11Title

lesson12Title

lesson13Title

lesson14Title

lesson15Title

lesson16Title

lesson17Title

aiFundamentalsDeepLearningChapter1Title

aiFundamentalsDeepLearningChapter2Title

aiFundamentalsDeepLearningChapter3Title

aiFundamentalsDeepLearningChapter4Title

aiFundamentalsDeepLearningChapter5Title

# Comparison of Activation Functions - Sigmoid, ReLU, and Softmax  

Activation functions transform input values in an artificial neural network and transmit them to the next layer.

The `Sigmoid`, `ReLU (Rectified Linear Unit)`, and `Softmax` functions that you have learned so far each have their own characteristics, advantages, and disadvantages.

<br />  

## Comparison of Activation Functions  

| Function    | Output Range    | Features and Advantages                           | Disadvantages and Limitations  |
|-------------|-----------------|------------------------------------------------|--------------------------------|
| Sigmoid     | (0, 1)          | Probabilistic interpretation, suitable for binary classification | Vanishing gradient problem for large values |
| ReLU        | (0, ∞)          | Alleviates vanishing gradient problem, simple to compute | Neuron deactivation for values ≤ 0 |
| Softmax     | (0, 1)          | Suitable for multi-class classification, provides probability values | One class value can influence other classes |

<br />  

Activation functions have a significant impact on the performance of neural network models. 

It's important to choose the appropriate activation function based on the problem's characteristics.

In the next lesson, we will take a brief quiz to review what we've learned so far.

소프트맥스 함수는 다중 클래스 분류 문제에 적합하며, 각 클래스의 확률 값을 제공합니다. 이로 인해 여러 클래스 중 하나를 선택할 수 있는 분류 문제에서 유용합니다.

Function	Output Range	Features and Advantages	Disadvantages and Limitations
Sigmoid	(0, 1)	Probabilistic interpretation, suitable for binary classification	Vanishing gradient problem for large values
ReLU	(0, ∞)	Alleviates vanishing gradient problem, simple to compute	Neuron deactivation for values ≤ 0
Softmax	(0, 1)	Suitable for multi-class classification, provides probability values	One class value can influence other classes

Comparison of Activation Functions - Sigmoid, ReLU, and Softmax

Comparison of Activation Functions

다음 중 다중 클래스 분류에 가장 적합한 활성화 함수는 무엇인가요?