Learning Path
Question & Answer
Choose the Best Answer
Because the gradients become too small or too large, affecting weight updates
Because deeper networks have more parameters leading to overfitting
Because shallow networks are easier to optimize
Because activation functions are always linear in deep networks
Understanding the Answer
Let's break down why this is correct
When a gradient moves backward through many layers, it can shrink to almost nothing or grow to a huge number. Other options are incorrect because The idea that more parameters automatically cause vanishing or exploding gradients is a mix‑up with overfitting; Thinking that shallow networks are always easier to train ignores the fact that any network can have bad gradient flow.
Key Concepts
Vanishing/Exploding Gradients Problem
easy level question
understand
Deep Dive: Vanishing/Exploding Gradients Problem
Master the fundamentals
Definition
The vanishing/exploding gradients problem poses a challenge in training deep neural networks, hindering convergence during optimization. Techniques such as normalized initialization and intermediate normalization layers have been developed to mitigate this issue and enable the training of deep networks with improved convergence rates.
Topic Definition
The vanishing/exploding gradients problem poses a challenge in training deep neural networks, hindering convergence during optimization. Techniques such as normalized initialization and intermediate normalization layers have been developed to mitigate this issue and enable the training of deep networks with improved convergence rates.
Ready to Master More Topics?
Join thousands of students using Seekh's interactive learning platform to excel in their studies with personalized practice and detailed explanations.