AI0-001 AI Concepts and Techniques — 40 Questions

Question 1

A machine learning engineer is training a logistic regression model and notices that the loss is decreasing very slowly. The learning rate is set to 0.001. What is the MOST likely cause and appropriate fix?

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

Accepted Answer

The learning rate is too low; increase it to 0.01. A learning rate of 0.001 is very low for many logistic regression implementations, causing the gradient descent algorithm to take extremely small steps toward the minimum of the loss function. This results in a slow decrease in loss because each weight update is minimal. Increasing the learning rate to 0.01 allows larger steps per iteration, accelerating convergence without typically causing divergence in well-scaled data.

Answer

The learning rate is too high; decrease it to 0.0001

Answer

The model is overfitting; add L2 regularisation

Answer

The batch size is too large; reduce it

Question 2

A data scientist is evaluating a binary classifier for a medical diagnosis task. The dataset is imbalanced with 5% positive cases. Which THREE metrics should the data scientist consider for a comprehensive evaluation?

Accepted Answer

Precision. Precision (A) is correct because it measures the proportion of true positive predictions among all positive predictions, which is critical in imbalanced medical diagnosis where false positives can lead to unnecessary stress or procedures. In a dataset with only 5% positive cases, a model that predicts all negatives would achieve high accuracy but zero precision, so precision helps assess the cost of false alarms.

Answer

Accuracy

Answer

Perplexity

Question 3

A product team wants a system that can generate high-quality synthetic images of furniture in different room settings for an online catalog. The images must be photorealistic and vary in style. Which generative AI approach is BEST suited for this task?

Accepted Answer

Diffusion model. Diffusion models are the best choice because they iteratively denoise random noise to produce high-quality, photorealistic images with diverse styles. Unlike GANs, they avoid mode collapse and training instability, and they generate more detailed and varied outputs than VAEs, making them ideal for furniture catalog images in different room settings.

Answer

Variational autoencoder (VAE)

Answer

Generative adversarial network (GAN)

Answer

Recurrent neural network (RNN)

Question 4

A research team is fine-tuning a BERT model for a text classification task. They notice that the model's performance on the validation set fluctuates wildly across epochs, sometimes dropping significantly from one epoch to the next. Which technique is MOST likely to stabilise training?

Accepted Answer

Apply gradient clipping. Gradient clipping directly addresses the problem of exploding gradients, which can cause large, destabilizing weight updates during fine-tuning of large models like BERT. By capping the gradient norm (e.g., to a value like 1.0), it prevents a single batch from drastically altering the model's parameters, thus smoothing out validation performance fluctuations across epochs.

Answer

Use a smaller batch size

Answer

Increase the learning rate

Answer

Increase the number of epochs

Question 5

A data scientist is preparing to train a convolutional neural network (CNN) for image classification. Which TWO actions are most effective for preventing overfitting? (Choose 2)

Accepted Answer

Use data augmentation. Data augmentation (A) is effective for preventing overfitting because it artificially expands the training dataset by applying random transformations (e.g., rotation, flipping, cropping, color jitter) to existing images. This exposes the CNN to a wider variety of input patterns, reducing the model's tendency to memorize noise or specific details and improving generalization to unseen data.

Answer

Increase the number of epochs

Answer

Use L2 regularization

Answer

Add more convolutional layers

Question 6

A company wants to build a customer service chatbot that answers questions about their internal policy documents. The documents are updated monthly, and the team cannot afford to retrain a model each time. Which approach is MOST appropriate?

Accepted Answer

Use Retrieval-Augmented Generation (RAG) with the policy documents indexed in a vector store. Retrieval-Augmented Generation (RAG) is the most appropriate approach because it allows the chatbot to answer questions by retrieving relevant chunks from the policy documents stored in a vector store, without requiring model retraining when documents are updated monthly. The retrieval component dynamically fetches the latest content, while the generation component uses a pre-trained LLM to produce answers, making it cost-effective and scalable for frequently changing knowledge bases.

Answer

Train a custom model from scratch on the policy documents each month

Answer

Use a larger foundation model with a longer context window and paste all documents into each prompt

Answer

Fine-tune a base LLM on the policy documents monthly

Question 7

A data scientist needs to predict whether a customer will churn (yes/no) based on historical data. Which type of machine learning problem is this?

Accepted Answer

Binary classification. This is a binary classification problem because the target variable has exactly two discrete outcomes: 'yes' (churn) or 'no' (no churn). Classification algorithms such as logistic regression, decision trees, or support vector machines are used to assign input features to one of these two predefined classes. The output is a categorical label, not a continuous value or a reward signal.

Answer

Reinforcement learning

Answer

Regression

Answer

Clustering

Question 8

A team trains a neural network for image classification. During training, the loss decreases on the training set but increases on the validation set after a few epochs. What is the most likely cause?

Accepted Answer

Overfitting. Overfitting occurs when the model learns the training data too well, including noise and irrelevant patterns, causing it to memorize rather than generalize. This is evidenced by the loss decreasing on the training set while increasing on the validation set after a few epochs, as the model's performance on unseen data degrades.

Answer

Vanishing gradients

Answer

Incorrect learning rate scheduling

Answer

Underfitting

Question 9

A generative AI model is asked to 'Write a poem about AI' and returns a very short, generic response. The user wants longer, more creative outputs. Which parameter adjustment is MOST likely to help?

Accepted Answer

Increase the temperature parameter. Increasing the temperature parameter raises the randomness of token selection, encouraging the model to explore less probable word sequences and produce more varied, creative, and longer outputs. A low temperature (e.g., 0.1) makes the model deterministic and repetitive, often yielding short, generic responses. By increasing temperature (e.g., to 0.8 or 1.0), the model is more likely to generate diverse and expansive text, directly addressing the user's request for longer, more creative poems.

Answer

Decrease the top-p value

Answer

Increase the frequency penalty

Answer

Decrease the max tokens limit

Question 10

An AI engineer is tuning a large language model for a summarization task. The output summaries are too verbose and include irrelevant details. Which technique should be applied to encourage concise outputs?

Accepted Answer

Provide a few-shot example with concise summaries. Providing a few-shot example with concise summaries (Option A) directly demonstrates the desired output format to the model, leveraging in-context learning to bias generation toward brevity and relevance. This is the most effective technique for controlling output style without altering the model's underlying parameters.

Answer

Use chain-of-thought prompting

Answer

Decrease the top-k value

Answer

Increase the temperature

Question 11

Which of the following is a key characteristic of Narrow AI (Weak AI)?

Accepted Answer

It is designed to excel at a single, specific task. Narrow AI, also known as Weak AI, is designed and trained to perform a single, specific task with high proficiency, such as language translation, image recognition, or playing chess. It cannot generalize its intelligence to other domains, which distinguishes it from Artificial General Intelligence (AGI). Option C correctly captures this fundamental characteristic.

Answer

It can perform any intellectual task that a human can

Answer

It requires no training data

Answer

It surpasses human intelligence in all domains

Question 12

A prompt engineer wants to reduce the risk of prompt injection attacks in an LLM-based application that processes user input. Which strategy is MOST effective?

Accepted Answer

Sanitize user input to remove or neutralize special characters and instruction-like patterns. Sanitizing user input to remove or neutralize special characters and instruction-like patterns directly addresses the root cause of prompt injection attacks: the ability for user-supplied text to alter the intended behavior of the LLM. By stripping or escaping tokens that mimic system instructions (e.g., 'Ignore previous instructions' or delimiter sequences), the application prevents the injection vector from reaching the model's instruction-following logic. This is a fundamental input validation technique analogous to SQL injection prevention, applied to the LLM context.

Answer

Set the temperature to 0

Answer

Use a system prompt that instructs the model to ignore injection attempts

Answer

Use a larger, more powerful LLM

Question 13

A company wants to classify images of products into categories. They have a large dataset of labeled images. Which TWO types of neural networks are most suitable for this task? (Select TWO.)

Accepted Answer

Convolutional Neural Network (CNN). Convolutional Neural Networks (CNNs) are the standard architecture for image classification because they use convolutional layers to automatically learn spatial hierarchies of features (edges, textures, shapes) from pixel data. They are highly effective for large labeled image datasets due to their parameter efficiency and translation invariance.

Answer

Generative Adversarial Network (GAN)

Answer

Recurrent Neural Network (RNN)

Answer

Multi-layer Perceptron (MLP)

Question 14

A data scientist is building a model to predict whether a transaction is fraudulent. The dataset has 99.9% legitimate transactions and 0.1% fraudulent ones. Which evaluation metric is MOST appropriate to assess model performance given this class imbalance?

Accepted Answer

F1-score. With 99.9% legitimate transactions and only 0.1% fraudulent ones, accuracy would be misleadingly high (99.9%) even if the model never predicts fraud. The F1-score is the harmonic mean of precision and recall, making it robust to class imbalance by penalizing both false positives and false negatives. This makes it the most appropriate metric for evaluating fraud detection performance.

Answer

BLEU score

Answer

Accuracy

Answer

Perplexity

Question 15

Which machine learning paradigm involves training an agent to make decisions by interacting with an environment and receiving rewards or penalties based on its actions?

Accepted Answer

Reinforcement learning. Reinforcement learning (RL) is the correct paradigm because it explicitly involves an agent learning a policy through trial-and-error interactions with an environment, receiving scalar reward signals (positive or negative) to maximize cumulative reward. This matches the question's description of making decisions based on rewards or penalties, which is the defining characteristic of RL, as opposed to learning from labeled data or discovering hidden patterns without feedback.

Answer

Unsupervised learning

Answer

Supervised learning

Answer

Self-supervised learning

Question 16

Which neural network architecture is specifically designed to process sequential data, such as time series or sentences, by maintaining a hidden state that captures information about previous inputs?

Accepted Answer

Recurrent Neural Network (RNN). Recurrent Neural Networks (RNNs) are specifically designed for sequential data because they maintain a hidden state that is updated at each time step, allowing information about previous inputs to persist and influence current and future outputs. This feedback loop makes them ideal for tasks like time series forecasting, natural language processing, and speech recognition, where order and context matter.

Answer

Transformer

Answer

Convolutional Neural Network (CNN)

Answer

Multi-layer Perceptron (MLP)

Question 17

A company wants to automatically group customer support tickets into categories (e.g., billing, technical, account) without pre-labeled data. Which machine learning approach should they use?

Accepted Answer

Unsupervised clustering using K-means. The company has no pre-labeled data, which means supervised learning (which requires labeled examples) is not feasible. Unsupervised clustering, such as K-means, groups data points into clusters based on feature similarity without needing any labels, making it ideal for automatically discovering categories like billing, technical, or account from raw ticket text.

Answer

Supervised classification with logistic regression

Answer

Semi-supervised learning with a small labeled set

Answer

Reinforcement learning with a reward function

Question 18

A team is training a deep learning model for image classification. They observe that training accuracy is high but validation accuracy is low, indicating overfitting. Which TWO techniques should they apply to reduce overfitting? (Select TWO)

Accepted Answer

Use L2 regularization. L2 regularization (also known as weight decay) adds a penalty proportional to the square of the magnitude of the weights to the loss function. This discourages the model from learning overly complex patterns that fit the training data noise, effectively reducing overfitting by keeping weights small and the decision boundary simpler.

Answer

Increase learning rate

Answer

Increase the number of layers

Answer

Reduce training data size

Question 19

A machine learning engineer is training a logistic regression model and notices that the loss is decreasing very slowly. The learning rate is set to 0.001. What is the MOST likely cause and appropriate fix?

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

Accepted Answer

Normalize the pixel values to zero mean and unit variance. Normalizing pixel values to zero mean and unit variance (A) ensures that input features have similar scales, which prevents certain weights from updating disproportionately and stabilizes gradient descent. This is especially important for CNNs processing satellite imagery, where raw pixel intensities can vary widely across bands and scenes, leading to poor convergence.

Answer

Remove dropout layers to allow more gradient flow

Answer

Use a smaller batch size to reduce memory

Answer

Increase the learning rate by 10x

Question 20

A data scientist is preparing a dataset for a binary classification model. The dataset has 1000 samples, with 800 positives and 200 negatives. To evaluate the model properly, which THREE steps should they take? (Select THREE)

Accepted Answer

Use a stratified train-test split to preserve class proportions. Stratified train-test splitting ensures that the class distribution (80% positive, 20% negative) is preserved in both training and test sets. This prevents the model from being evaluated on a test set that has a different class ratio, which could give a misleading impression of performance, especially in imbalanced datasets.

Answer

Remove the minority class samples to make the dataset balanced

Answer

Report only accuracy as the evaluation metric