AI0-001 AI Concepts and Foundations — 10 Questions

Question 1

A team is designing an AI system for autonomous driving. They need to decide between an end-to-end deep learning approach versus a modular pipeline (perception, planning, control). Which is a key advantage of the modular approach?

Choose an answer to begin — your selection is scored in the full session.

Accepted Answer

Each module can be validated separately.. The modular pipeline approach decomposes the autonomous driving task into distinct components (e.g., perception, planning, control), each of which can be independently developed, tested, and validated. This separation allows engineers to verify the correctness of each module against its own specification, which is critical for safety-critical systems like autonomous driving. In contrast, end-to-end deep learning models treat the entire system as a black box, making it difficult to isolate and validate individual behaviors.

Answer

It typically has lower inference latency.

Answer

It handles novel scenarios better due to joint training.

Answer

It requires less engineering effort.

Question 2

A company uses an AI model to screen job applications. The model is trained on historical hiring data that reflects past biases. After deployment, the model disproportionately rejects candidates from certain demographics. Which concept does this best illustrate?

Accepted Answer

Algorithmic bias. Algorithmic bias refers to systematic and unfair discrimination in AI outputs due to biased training data or model design. Option A (overfitting) is about a model that performs well on training data but poorly on new data due to excessive complexity. Option B (model drift) is about performance degradation over time due to changes in data distribution. Option D (underfitting) is when a model is too simple to capture patterns.

Answer

Overfitting

Answer

Model drift

Answer

Underfitting

Question 3

A company wants to use AI to automatically categorize customer support tickets into topics like 'billing', 'technical', 'account'. They have 10,000 labeled examples. Which algorithm is most suitable for this task?

Accepted Answer

Logistic regression. Logistic regression is a supervised learning algorithm that models the probability of a categorical outcome based on input features. With 10,000 labeled examples, it can efficiently learn decision boundaries to classify tickets into 'billing', 'technical', or 'account' by using a softmax (multinomial logistic regression) extension for multi-class classification.

Answer

DBSCAN

Answer

Apriori

Answer

Principal component analysis (PCA)

Question 4

Refer to the exhibit. The training log shows loss and accuracy for a binary classification model. What is the most likely issue with this model?

Accepted Answer

Overfitting. The training log shows that training loss continues to decrease while validation loss increases after a certain point, and training accuracy approaches 100% while validation accuracy plateaus or drops. This divergence is the classic signature of overfitting, where the model memorizes noise in the training data rather than learning generalizable patterns.

Answer

Insufficient epochs

Answer

Underfitting

Answer

Data leakage

Question 5

A retail company deploys a machine learning model to predict customer churn. The model outputs a probability between 0 and 1, and churn is predicted if probability > 0.5. After deployment, the model has a high false positive rate (many non-churning customers labeled as churn), which leads to unnecessary retention offers and increased costs. The data science team confirms the model was trained on historical data with a balanced class distribution. The business team wants to reduce false positives while maintaining a reasonable true positive rate. However, they cannot retrain the model because the original training data is no longer available. What is the best course of action to reduce false positives?

Accepted Answer

Increase the decision threshold to a higher value, such as 0.7.. Increasing the decision threshold to a higher value, such as 0.7, reduces false positives because the model will only predict churn when it is more confident. Since the model cannot be retrained, adjusting the threshold is the only way to trade off between precision and recall without modifying the model itself.

Answer

Retrain the model using only the most recent three months of data.

Answer

Collect new labeled data and perform transfer learning from the original model.

Answer

Decrease the decision threshold to a lower value, such as 0.3.

Question 6

A company deploys an AI model to predict equipment failure. The model performs well on historical data but fails to generalize to new data from a different factory. Which concept best describes this issue?

Accepted Answer

Overfitting. (Overfitting) is correct because the model learned patterns specific to the historical data from the original factory, including noise and factory-specific nuances, rather than generalizable features. When applied to new data from a different factory, those learned patterns do not hold, causing poor performance. This is the classic symptom of overfitting: high accuracy on training data but low accuracy on unseen data.

Answer

Transfer learning

Answer

Underfitting

Answer

Bias-variance tradeoff

Question 7

A data scientist trains a linear regression model to predict house prices. The model has high bias and low variance. Which action would most likely reduce bias?

Accepted Answer

Add polynomial features. High bias indicates the model is underfitting the data, meaning it is too simple to capture the underlying patterns. Adding polynomial features increases model complexity by introducing non-linear terms, which allows the linear regression model to better fit the training data and thus reduce bias.

Answer

Apply L2 regularization

Answer

Increase the training dataset size

Answer

Remove irrelevant features

Question 8

An AI engineer trains a deep learning model for image classification. After training, the training accuracy is 99% but validation accuracy is 85%. Which technique would best address this discrepancy?

Accepted Answer

Add dropout layers. The high training accuracy (99%) and lower validation accuracy (85%) indicate overfitting, where the model memorizes training data but fails to generalize. Dropout layers randomly deactivate neurons during training, forcing the network to learn more robust features and reducing overfitting. This technique directly addresses the discrepancy by improving validation performance without sacrificing training capacity.

Answer

Increase data augmentation

Answer

Decrease the learning rate

Answer

Increase the number of layers

Question 9

A company implements a chatbot using a rule-based system. Users complain the chatbot cannot handle new queries. Which AI approach should be considered to improve flexibility?

Accepted Answer

Machine learning. Machine learning (ML) enables a chatbot to learn from new data and adapt to unseen queries, unlike a static rule-based system. By training on historical conversations, an ML model can generalize patterns and handle novel inputs without requiring explicit rules for every scenario.

Answer

Expert system

Answer

Natural language processing (NLP)

Answer

Robotic process automation

Question 10

An AI model for detecting fraudulent transactions has high precision but low recall. Which business impact is most likely?

Accepted Answer

Many fraudulent transactions go undetected. High precision means that when the model flags a transaction as fraudulent, it is very likely correct. However, low recall indicates that the model misses a significant proportion of actual fraudulent transactions. Therefore, the most likely business impact is that many fraudulent transactions go undetected, leading to financial losses.

Answer

The model has no impact on fraud detection

Answer

The model detects all fraudulent transactions

Answer

Many legitimate transactions are flagged as fraud