How do I approach Machine Learning interview questions?

Machine Learning questions require understanding of core concepts and practice. PracHub provides solutions with explanations to help you master machine learning interviews.

What difficulty level is this interview question?

This is a medium difficulty Machine Learning question, commonly asked during Onsite rounds at Apple.

What role is this question designed for?

This question is commonly asked for Data Scientist candidates at Apple during technical interviews.

Explain CNN shapes, params, and trade-offs

Quick Overview

This question evaluates understanding of convolutional neural network tensor shapes, parameter counts and multiply–accumulate (MAC) calculations, receptive field analysis, and architectural trade-offs including depthwise separable convolutions and normalization placement.

CNN Shapes, Compute, and Design Trade-offs

Context

You are given an input tensor X with shape H×W×C = 64×64×3. Consider the following convolutional neural network (CNN):

L1: Conv 3×3, stride=1, padding=1, 32 filters
L2: MaxPool 2×2, stride=2
L3: Conv 3×3, dilation=2, stride=1, padding=2, 64 filters
L4: Depthwise separable conv: depthwise 3×3 (stride=1, padding=1) + pointwise 1×1 to 128 channels

Tasks

(a) Compute the output shape H×W×C after each layer.

(b) Compute parameter counts and MACs for L1, L3, and L4. Compare L4’s MACs to a standard 3×3 conv with 64→128 channels (same input size as L4). Show formulas and numbers.

(d) Where would you place BatchNorm relative to activation for stable training (pre‑act vs post‑act) and why?

(e) When would you prefer stride vs pooling vs dilation to preserve information while controlling compute?

(f) Explain the bias–variance and optimization trade‑offs of using depthwise separable convolutions in tiny‑model regimes.

Quick Overview

Context

You are given an input tensor X with shape H×W×C = 64×64×3. Consider the following convolutional neural network (CNN):

L1: Conv 3×3, stride=1, padding=1, 32 filters

L2: MaxPool 2×2, stride=2

L3: Conv 3×3, dilation=2, stride=1, padding=2, 64 filters

L4: Depthwise separable conv: depthwise 3×3 (stride=1, padding=1) + pointwise 1×1 to 128 channels

Tasks

(a) Compute the output shape H×W×C after each layer.

(b) Compute parameter counts and MACs for L1, L3, and L4. Compare L4’s MACs to a standard 3×3 conv with 64→128 channels (same input size as L4). Show formulas and numbers.

(d) Where would you place BatchNorm relative to activation for stable training (pre‑act vs post‑act) and why?

(e) When would you prefer stride vs pooling vs dilation to preserve information while controlling compute?

(f) Explain the bias–variance and optimization trade‑offs of using depthwise separable convolutions in tiny‑model regimes.

Explain CNN shapes, params, and trade-offs

Quick Overview

CNN Shapes, Compute, and Design Trade-offs

Context

Tasks

Solution

Comments (0)

Explain CNN shapes, params, and trade-offs

Quick Overview

CNN Shapes, Compute, and Design Trade-offs

Context

Tasks

Solution

Comments (0)