Moderate DL Question 218 of 223

Why do we use activation functions in neural nets?

AI & Data Analytics · Speak this in 60–90 seconds · Faridabad & Delhi NCR

PICTURE THIS: TINY NEURAL NET

InputFeatures
HiddenWeights + activation
OutputScore / class

Simple meaning

Without non-linearities, stacked layers collapse to one linear map.

1

WHY — DL instead of guessing?

Why interviewers care about DL:

They are checking judgment

on DL.

A good answer names

the situation, the default choice, and one exception - that reads as experience.

Stay structured

Name the idea, why it exists, then one short example.

Close cleanly

End with when you use it and one common pitfall.

2

STEPS — What happens step by step?

Before you speak the answer, walk the interviewer through these steps:

  1. 1
    Without non-linearities, stacked layers

    collapse to one linear map.

  2. 2
    Why it exists

    ReLU is a common default.

  3. 3
    Choice affects vanishing gradients

    and sparsity.

  4. 4
    Give an example

    One tiny concrete case you can say aloud.

  5. 5
    Common mistake

    What juniors usually get wrong.

  6. 6
    Close

    When you pick this over the alternative.

3

EXAMPLE — See it in action

Here's a short line you can speak, broken into clear beats:

Say this line
“ReLU is a common default.”
Break into beats
ReLUisacommondefault
Speaking order
298740833747163290

Note: Adapt this scaffold to your own project — keep it under 60–90 seconds.

Key takeaway

Without non-linearities, stacked layers collapse to one linear map. ReLU is a common default.

Chat with us