7.10: Quantitative Problems

Principles of Data Science · LibreTexts

0%

Contents

    Text

    Size
    100%
    Theme
    Typeface
    Line length
    Spacing

    From LibreTexts, under CC BY 4.0, as the source states it; its equations are written in TeX, which the PDF shows typeset. This page at LibreTexts.

    1.
    a.
    Suppose that a neural network has been trained to classify students as likely to graduate or not likely to graduate based on various input parameters. There is a single output neuron having four inputs, and one output, . The output is used to make the classification. The weights of the three inputs of this neuron are , , and . The bias of the neuron is . Find the output if and if the activation function is:
    1. ReLU
    2. Leaky ReLU defined by max⁡ (0.2x,x)
    3. Sigmoid
    4. Softplus
    b.
    Which of the four activation functions, applied at the output layer, would be best suited for this classification task? Using this activation function, how would the neural network classify the student?
    2.
    The output of a neural network on data points are given in the table.
    Data point Predicted Actual(target)
    1
    2
    3
    4
    5
    Table 7.4
    Compute the average loss using the following loss functions.
    a.
    MSE
    b.
    Hinge loss

    This page titled 7.10: Quantitative Problems was last modified on Tue, 22 Apr 2025 14:35:01 GMT and is shared under a CC BY 4.0 license and was authored, remixed, and/or curated by OpenStax via source content that was edited to the style and standards of the LibreTexts platform.