Emerging trends (smaller models, edge AI) in Prompt Engineering / GenAI - Practice Problems & Coding Challenges

Challenge - 5 Problems

🧠 Conceptual

intermediate

Why are smaller AI models important for edge devices?

Edge devices like smartphones and IoT sensors have limited power and memory. Why is using smaller AI models on these devices beneficial?

A Smaller models require constant internet connection to work properly on edge devices.

B Smaller models use less memory and power, making them faster and more efficient on edge devices.

C Smaller models always provide higher accuracy than larger models.

D Smaller models increase the need for cloud computing, reducing edge device independence.

💡 Hint

Think about the limitations of battery and storage on small devices.

Smaller AI models are designed to use less memory and power, which helps edge devices run AI tasks quickly without draining battery or needing big storage.

❓ Predict Output

intermediate

Output of model size comparison code

Given the following Python code comparing two model sizes, what is the printed output?

Prompt Engineering / GenAI

model_a_size = 25000000  # 25 million parameters
model_b_size = 5000000   # 5 million parameters

if model_b_size < model_a_size:
    print(f"Model B is smaller by {model_a_size - model_b_size} parameters")
else:
    print("Model A is smaller or equal in size")

A Model B is smaller by 20000000 parameters

B Model A is smaller or equal in size

C Model B is smaller by 30000000 parameters

D SyntaxError due to missing colon

💡 Hint

Check which model size is bigger and subtract accordingly.

Model A has 25 million parameters, Model B has 5 million. Model B is smaller by 20 million parameters.

❓ Model Choice

advanced

Best model type for real-time edge AI

You want to deploy an AI model on a wearable device that must respond instantly and use very little battery. Which model type is best?

A A large transformer model with billions of parameters

B A cloud-based model accessed via internet

C A deep recurrent neural network with many layers

D A small convolutional neural network optimized for mobile

💡 Hint

Consider model size and power use for wearables.

Small CNNs optimized for mobile devices use less power and compute, making them ideal for real-time edge AI on wearables.

❓ Hyperparameter

advanced

Which hyperparameter tuning helps reduce model size for edge AI?

To make a model smaller and faster for edge deployment, which hyperparameter adjustment is most effective?

A Using a higher learning rate

B Increasing the batch size during training

C Applying pruning to remove less important weights

D Increasing the number of layers

💡 Hint

Think about removing parts of the model that are not needed.

Pruning removes unnecessary weights, reducing model size and speeding up inference, which is ideal for edge AI.

❓ Metrics

expert

Evaluating edge AI model trade-offs

You have two edge AI models:
Model X: 90% accuracy, 50ms latency, 10MB size
Model Y: 85% accuracy, 20ms latency, 5MB size

Which metric best captures the trade-off between accuracy and latency for edge use?

A Accuracy divided by latency

B Latency alone

C Accuracy alone

D Model size alone

💡 Hint

Think about a metric that balances speed and correctness.

Accuracy divided by latency shows how much accuracy you get per unit time, helping balance speed and performance on edge devices.