COMPUTER SCIENCE AND ENGINEERING
MACHINE LEARNING
|
Question
[CLICK ON ANY CHOICE TO KNOW THE RIGHT ANSWER]
|
We are given a 2-class classification problem with 0/1 output labels. We plan to use a neural network to implement the classifier. Which of the following functions is a suitable choice for the output neurons?
|
|
Hyperbolic Tangent Neuron
|
|
|
Linear Neuron
|
|
|
Arctangent Neuron
|
|
|
Logistic Sigmoid Neuron
|
Explanation:
Detailed explanation-1: -A two layer (one input layer, one output layer; no hidden layer) neural network can represent the XOR function.
Detailed explanation-2: -Advantages of using this activation function are: The output of the tanh activation function is Zero centered; hence we can easily map the output values as strongly negative, neutral, or strongly positive.
Detailed explanation-3: -ReLU (Rectified Linear Unit) Activation Function The ReLU is the most used activation function in the world right now. Since, it is used in almost all the convolutional neural networks or deep learning.
Detailed explanation-4: -One of the most widely used sigmoid functions is the logistic function, which maps any real value to the range (0, 1).
There is 1 question to complete.