ARTIFICIAL INTELLIGENCE

By,
SHOBHANRAJ.M.N
VKKFGC MYSORE
1. What is anomaly detection?
Ans: Anomaly detection is the process of identifying data points that deviate significantly
from normal patterns or expected behaviour. These abnormal data points, known as
anomalies or outliers, can indicate errors, fraud, or interesting new trends.

2. What is Speech Recognition?

Ans: Speech recognition is the process of converting spoken language into text. It's like
having a computer understand and transcribe what you're saying.

4. What is NLP?
Ans: NLP (Natural Language Processing) is a field of artificial intelligence that focuses on
the interaction between computers and human (natural) languages. It involves teaching
computers to understand, interpret, and generate human language in a way that is both
meaningful and useful.

5. Define Data Analysis.

Ans: Data analysis is the process of using statistical and logical techniques to examine data
and extract useful information.

6. Explain the process of data analysis.

1. Define the Problem or Research Question:

Clearly articulate the specific issue you want to investigate or the question you seek to
answer.
2. Collect Data:
Gather relevant data from various sources, such as databases, surveys, experiments, or
public datasets.
3. Data Cleaning:
 Identify and correct errors, inconsistencies, or missing values in the data.
4. Analyzing the Data:
 Apply statistical techniques or machine learning algorithms to uncover patterns,
trends, and relationships within the data.
5. Data Visualization:
Create charts, graphs, or other visual representations to make the data easier to
understand and interpret.
6. Presenting Data:
 Communicate the findings in a clear and concise manner, often using visualizations,
reports, or presentations.
7. Explain the categories of data Analytics
Data analytics can be broadly categorized into five main types:
1. Descriptive Analytics:
 Purpose: Summarizes and describes existing data.
 Techniques: Aggregation, grouping, sorting, and basic statistical calculations.
 Examples: Calculating sales totals, average customer age, or identifying the most
popular products.
2. Diagnostic Analytics:
 Purpose: Investigates the underlying causes of events or trends.
 Techniques: Drill-down analysis, data mining, and root cause analysis.
 Examples: Determining why sales declined in a specific region or understanding the
factors contributing to customer churn.
3. Predictive Analytics:
 Purpose: Forecasts future outcomes or trends based on historical data.
 Techniques: Statistical modeling, machine learning algorithms, and time series
analysis.
 Examples: Predicting customer lifetime value, forecasting sales for the next quarter, or
identifying potential fraud cases.
4. Prescriptive Analytics:
 Purpose: Recommends optimal actions or decisions based on data analysis.
 Techniques: Optimization algorithms, simulation modeling, and decision trees.
 Examples: Suggesting the best marketing channels to reach target customers,
optimizing inventory levels, or recommending personalized product recommendations.
5. Cognitive Analytics:
 Purpose: Combines artificial intelligence and machine learning to simulate human
thought processes and decision-making.
 Techniques: Natural language processing, computer vision, and cognitive computing.
 Examples: Developing intelligent chatbots, analyzing unstructured data like images or
text, and automating complex decision-making processes.
8. With an example explain Text Analytics Techniques.
1. Tokenization:
 Definition: Breaking down text into smaller units, typically words or sentences.
 Example: Sentence: "The quick brown fox jumps over the lazy dog." Tokens: "The,"
"quick," "brown," "fox," "jumps," "over," "the," "lazy," "dog"
2. Stemming and Lemmatization:
 Definition: Reducing words to their root form.
 Example: Stemming: "jumping" becomes "jump" Lemmatization: "jumping" becomes
"jump" (considering context and grammar)
3. Stop Word Removal:
 Definition: Removing common words (like "the," "and," "a") that often carry little
semantic meaning.
 Example: Sentence: "The quick brown fox jumps over the lazy dog." After removing
stop words: "quick brown fox jumps lazy dog"
4. Part-of-Speech Tagging:
 Definition: Assigning grammatical tags to words (e.g., noun, verb, adjective).
 Example: Sentence: "The quick brown fox jumps over the lazy dog." Tags: "DT JJ
NN VB PP DT JJ NN" (determiner, adjective, noun, verb, preposition, determiner,
adjective, noun)
5. Named Entity Recognition (NER):
 Definition: Identifying named entities within text, such as people, organizations,
locations, and dates.
 Example: Sentence: "The quick brown fox jumps over the lazy dog." Named entity:
"lazy dog" (a hypothetical organization)
6. Sentiment Analysis:
 Definition: Determining the sentiment expressed in text (positive, negative, neutral).
 Example: Sentence: "The movie was fantastic!" Sentiment: Positive
7. Topic Modeling:
 Definition: Discovering underlying topics or themes within a collection of documents.
 Example: A collection of news articles might reveal topics such as "politics,"
"sports," and "technology."
8. Text Classification:
 Definition: Categorizing text documents into predefined categories.
 Example: Classifying emails as "spam" or "not spam."
9. What are the key tasks commonly performed in computer vision?
 Image Classification:
 Assigning a label to an image from a predefined set of categories.
 Examples: Classifying images as cats, dogs, or cars; identifying objects in a scene.
 Object Detection and Localization:
 Identifying and locating specific objects within an image.
 Examples: Detecting faces in a crowd, finding vehicles in aerial imagery.
 Image Segmentation:
 Dividing an image into different regions or segments based on their content.
 Examples: Segmenting a person from their background, separating foreground
objects from the background.
 Image Restoration:
 Improving the quality of images by removing noise, enhancing contrast, or
sharpening details.
 Examples: Restoring old photographs, improving blurry images.
 Facial Recognition:
 Identifying individuals based on their facial features.
 Examples: Verifying identities in security systems, unlocking devices with facial
recognition.

11. Write a note on Data Analytics.

Data analytics is the process of examining data to extract insights, draw conclusions, and
make informed decisions. It involves collecting, cleaning, organizing, and interpreting data
using statistical and analytical techniques.
Key steps in data analysis:
 Data collection: Gathering relevant data from various sources.
 Data cleaning: Identifying and correcting errors, inconsistencies, or missing values.
 Data exploration: Summarizing and visualizing the data to understand its
characteristics.
 Data analysis: Applying statistical techniques and models to analyze the data and extract
meaningful insights.
 Data interpretation: Interpreting the results of the analysis and drawing conclusions
based on the findings.
Common data analysis techniques:
  Descriptive statistics: Summarizing and describing the data using measures like mean,
median, mode, standard deviation, and correlation.
 Inferential statistics: Making inferences about a population based on a sample of data,
using techniques like hypothesis testing and confidence intervals.
 Data visualization: Creating charts, graphs, and other visual representations to make
the data easier to understand and interpret.
 Machine learning: Using algorithms to identify patterns and make predictions in the
data.
 Data mining: Discovering hidden patterns and relationships in large datasets.

10. Write an advantage of AI

 Efficiency: AI can do tasks faster and better than humans.
 Accuracy: AI makes fewer mistakes than humans.
 Always available: AI can work 24/7.
 Personalization: AI can tailor products and services to your needs.
 Innovation: AI can create new things.
 Cost-saving: AI can save money.
 Accessibility: AI can help people with disabilities.
 Research: AI can help scientists discover new things.
 Safety: AI can help prevent accidents.