nerdexam
Amazon

MLS-C01 · Question #49

A Machine Learning Specialist is building a convolutional neural network (CNN) that will classify 10 types of animals. The Specialist has built a series of layers in a neural network that will take…

The correct answer is C. Softmax. The Softmax function is the standard output activation for multi-class classification. It takes a vector of raw scores (logits) from the final dense layer and normalizes them into a probability distribution: each output value is between 0 and 1, and all 10 values sum to exactly…

Modeling

Question

A Machine Learning Specialist is building a convolutional neural network (CNN) that will classify 10 types of animals. The Specialist has built a series of layers in a neural network that will take an input image of an animal, pass it through a series of convolutional and pooling layers, and then finally pass it through a dense and fully connected layer with 10 nodes. The Specialist would like to get an output from the neural network that is a probability distribution of how likely it is that the input image belongs to each of the 10 classes. Which function will produce the desired output?

Options

  • ADropout
  • BSmooth L1 loss
  • CSoftmax
  • DRectified linear units (ReLU)

How the community answered

(28 responses)
  • A
    4% (1)
  • B
    7% (2)
  • C
    89% (25)

Explanation

The Softmax function is the standard output activation for multi-class classification. It takes a vector of raw scores (logits) from the final dense layer and normalizes them into a probability distribution: each output value is between 0 and 1, and all 10 values sum to exactly 1.0. This directly answers 'how likely is the image to belong to each of the 10 classes.' Dropout is a regularization technique that randomly zeros out neurons during training - it is not an output activation. Smooth L1 loss is a loss/cost function used during training (common in object detection), not an activation function. ReLU (Rectified Linear Unit) is used in hidden layers to introduce non-linearity; it does not produce a probability distribution and its outputs can be any non-negative value.

Topics

#Softmax activation#Output layer#Multi-class classification#Probability distribution

Community Discussion

No community discussion yet for this question.

Full MLS-C01 Practice