AI0-001 Machine Learning and Deep Learning Practice Question
During training of a neural network, the loss oscillates and does not converge smoothly. The learning rate is set to 0.1. What is the most likely cause and what adjustment should be made?
⚠ Common exam trap
CompTIA often tests the misconception that a high learning rate always speeds up training; the trap here is that candidates may think increasing the learning rate will force faster convergence, when in fact it causes instability and oscillation.
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Learning rate too high; decrease it
A learning rate of 0.1 is relatively high for many neural network architectures. When the learning rate is too high, the optimizer takes steps that overshoot the minimum of the loss function, causing the loss to oscillate or even diverge instead of converging smoothly. Decreasing the learning rate allows for smaller, more stable weight updates, leading to smoother convergence.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Learning rate too low; increase it
Why it's wrong here
A learning rate of 0.1 is too high, causing the optimiser to overshoot minima so the loss oscillates rather than settling; the fix is to reduce it. A low rate would instead produce slow, monotonic descent. Raising it here would worsen the divergence.
- ✗
Batch size too small; increase it
Why it's wrong here
Batch size affects gradient variance, not the step magnitude that governs oscillation at a fixed rate of 0.1. Small batches add noise, but the stated symptom points to step size overshooting minima. Increasing batch size is used to stabilise noisy gradients when the rate is already suitably small.
- ✓
Learning rate too high; decrease it
Why this is correct
A learning rate of 0.1 is large enough that each gradient step overshoots the loss minimum, producing oscillation instead of smooth convergence. Reducing the learning rate shrinks step size, allowing the optimiser to settle into the minimum rather than bouncing across it.
- ✗
Too many epochs; stop early
Why it's wrong here
Oscillating loss with a learning rate of 0.1 indicates the step size overshoots the minimum, so the rate must be reduced. Stopping epochs early addresses overfitting, where training loss falls while validation loss rises, not unstable divergence.
About these practice questions
This AI0-001 question is part of Courseiva's 962-question bank — original exam-style content with full explanations and wrong-answer analysis, never real exam questions or exam dumps. Learn why practice questions differ from exam dumps →
Same concept, more angles
1 more way this is tested on AI0-001
These questions test the same concept from different angles. Work through them to make sure you can recognise it however the exam phrases it.
Variation 1. Refer to the exhibit. A data scientist is training a neural network and observes the training log above. What is the most likely cause?
medium- A.The model is overfitting
- B.The model is underfitting
- C.The batch size is too large
- ✓ D.The learning rate is too high
Why D: The training log shows a loss that initially decreases but then suddenly spikes and oscillates wildly, which is a classic sign of divergence caused by a learning rate that is too high. A high learning rate causes the optimizer to overshoot the minima in the loss landscape, leading to instability and failure to converge.
JA
Written by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
This AI0-001 practice question is part of Courseiva's free CompTIA certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the AI0-001 exam.