Fundamentals of AI

Question 1

What are neural networks?

Answer 1

Neural networks consist of multiple layers of interconnected neurons that process input data through mathematical operations.

Question 2

What are weights in a neural network?

Answer 2

Weights are values assigned to the connections between the neurons.

Question 3

What is bias in a neural network?

Answer 3

Bias is the value added to the data at a neuron.

Question 4

What do activation functions do in a neural network?

Answer 4

Activation functions determine whether a neuron should activate based on its inputs.

Question 5

What is artificial intelligence (AI)?

Answer 5

Artificial intelligence is a discipline that aims to create systems capable of performing tasks that usually require human intelligence.

Question 6

What is machine learning (ML)?

Answer 6

Machine learning is a domain of AI that teaches machines to learn from past experiences and data.

Question 7

What is deep learning (DL)?

Answer 7

Deep learning is a specialized domain of machine learning that trains neural networks with multiple layers to model complex patterns in data.

Question 8

What is generative AI?

Answer 8

Generative AI is a specialized area of ML and DL that focuses on creating new content by learning patterns from existing data.

Question 9

What is computer vision?

Answer 9

Computer vision is a field within AI focused on enabling machines to interpret and understand visual information from images and videos.

Question 10

What is natural language processing (NLP)?

Answer 10

Natural language processing is an area of AI dedicated to enabling machines to understand, interpret, and generate human language.

Question 11

What are large language models (LLMs)?

Answer 11

Large language models are advanced NLP systems trained on vast amounts of text data to generate coherent and contextually relevant text.

Question 12

What is labeled data in AI?

Answer 12

Labeled data comes with predefined tags or annotations that identify the characteristics or categories of each data point.

Question 13

What is unlabeled data in AI?

Answer 13

Unlabeled data lacks explicit labels, requiring the AI model to identify patterns or clusters without prior categorization.

Question 14

What is structured data?

Answer 14

Structured data is highly organized and fits neatly into predefined formats like rows and columns.

Question 15

What is unstructured data?

Answer 15

Unstructured data doesn’t have a predefined format, making it more challenging to process.

Question 16

What is time series data?

Answer 16

Time series data consists of sequences of data points collected at specific time intervals.

Question 17

What is image data?

Answer 17

Image data refers to visual information stored in pixel form.

Question 18

What is text data?

Answer 18

Text data includes written or spoken language, often in the form of documents, chat logs, or social media posts.

Question 19

What are the three primary ML techniques?

Answer 19

The three primary ML techniques are:
* Supervised learning
* Unsupervised learning
* Reinforcement learning

Question 20

What is supervised learning?

Answer 20

Supervised learning is a technique where an algorithm is trained on labeled data.

Question 21

What is regression in supervised learning?

Answer 21

Regression is a model that finds a relationship between independent and dependent variables and predicts a continuous value.

Question 22

What is classification in supervised learning?

Answer 22

Classification is a model trained on labeled data to predict labels of unseen data.

Question 23

What is unsupervised learning?

Answer 23

Unsupervised learning is a technique where an algorithm finds patterns in data without predefined categories.

Question 24

What is clustering in unsupervised learning?

Answer 24

Clustering is a model trained to find similarities in data and create groups based on those similarities.

Question 25

What is reinforcement learning?

Answer 25

Reinforcement learning is a type of machine learning where an agent interacts with an environment to maximize cumulative rewards.

Question 26

What is the first step in the ML model training process?

Answer 26

Data collection is the first step in model training.

Question 27

What is data preparation in ML?

Answer 27

Data preparation is the process of cleaning, transforming, and organizing data for model training.

Question 28

What is feature engineering?

Answer 28

Feature engineering is the process of creating new features or modifying existing ones to improve model performance.

Question 29

What happens during the ML modeling phase?

Answer 29

A suitable algorithm or model type is selected based on the problem and data characteristics.

Question 30

What is model training?

Answer 30

Model training is the phase where the algorithm learns from the data by adjusting its parameters.

Question 31

What are hyperparameters?

Answer 31

Hyperparameters are model settings that are not learned from data and are set before training begins.

Question 32

What is the final step in assessing ML model performance?

Answer 32

Evaluation is the final step in assessing how well the trained model performs on new, unseen data.

Question 33

What is accuracy in ML evaluation metrics?

Answer 33

Accuracy is the ratio of the correct number of predictions to the total number.

Question 34

What does precision measure in ML?

Answer 34

Precision is used to evaluate models where the cost of misclassifying a negative instance as positive is high.

Question 35

What is recall in ML evaluation metrics?

Answer 35

Recall, also known as sensitivity, is used to evaluate models where the cost of misclassifying a positive instance as negative is high.

Question 36

What is the F1-score?

Answer 36

The F1-score is the harmonic mean of precision and recall.

Question 37

What does the Receiver Operating Curve (ROC) represent?

Answer 37

ROC is the plot between false positives and true positives.

Question 38

What is Area Under the Curve (AUC)?

Answer 38

AUC is the area under the ROC curve.

Question 39

What is Mean Absolute Error (MAE)?

Answer 39

MAE is the average of the difference between predicted data points and their ground truth.

Question 40

What is Mean Square Error (MSE)?

Answer 40

MSE is the average of the squares of the difference between predicted data points and their ground truth.

Question 41

What is Root Mean Square Error (RMSE)?

Answer 41

RMSE is the square root of Mean Square Error.

Question 42

What is cost per user in business evaluation metrics?

Answer 42

Cost per user is the sum of the cost of building, developing, and maintaining an ML model divided by the total number of users.

Question 43

What do development costs refer to in ML?

Answer 43

Development costs are the total expense of developing the ML model.

Question 44

What is customer feedback in ML evaluation?

Answer 44

Customer feedback gathers users’ qualitative and quantitative responses regarding their experience with the ML model’s outputs.

Question 45

What does return on investment measure in ML?

Answer 45

Return on investment measures the profitability of the ML model relative to its costs.

Question 46

What is user adoption rate?

Answer 46

User adoption rate is the percentage of intended users who actively use the ML model after its deployment.

Question 47

What is bias in ML models?

Answer 47

Bias is the error introduced due to the under-fitted model.

Question 48

What is variance in ML models?

Answer 48

Variance is the error introduced due to the overfitted model.

Question 49

What is fairness in ML models?

Answer 49

Fairness is the error introduced when a model favors one class over another.

Question 50

What does goodness of fit indicate in ML?

Answer 50

Goodness of fit shows how a model balances the variance tradeoff and fits the data points to generate accurate predictions.

Question 51

What is inferencing in ML?

Answer 51

Inferencing is the process of using the trained machine learning model to make predictions.

Question 52

What is real-time inferencing?

Answer 52

Real-time inferencing takes the input, processes it, and returns the prediction immediately.

Question 53

What is batch inferencing?

Answer 53

Batch inferencing takes multiple inputs and generates predictions over time.