Scribd
Upload
4 views36 pages

Ai PPT

The document provides an overview of Artificial Intelligence (AI) and its significance, highlighting its role in task automation, data-driven decisions, and healthcare improvements. It discusses the differences between traditional programming and AI, various applications and components of AI, and outlines the steps involved in machine learning. Additionally, it covers types of machine learning, potential risks associated with AI, and its future implications in various industries.

Uploaded by

21cse056
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
4 views36 pages

Ai PPT

The document provides an overview of Artificial Intelligence (AI) and its significance, highlighting its role in task automation, data-driven decisions, and healthcare improvements. It discusses the differences between traditional programming and AI, various applications and components of AI, and outlines the steps involved in machine learning. Additionally, it covers types of machine learning, potential risks associated with AI, and its future implications in various industries.

Uploaded by

21cse056
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 36

ARTIFICIAL

INTELLIGENCE AND
MACHINE LEARNINIG
AN INTRODUCTORY SESSION
HAVE IDEAS ? SHOW THEM!
WHAT IS AI?
WHAT IS NEED OF AI

Here are five concise points explaining the need for AI:

1. Task Automation: AI handles repetitive tasks, boosting efficiency.


2. Data-Driven Decisions: AI analyzes data for better decision-making.
3. Personalization: AI tailors services to individual preferences.
4. Healthcare Improvement: AI aids in diagnostics and treatment planning.
5. Efficient Data Handling: AI processes large data sets quickly and accurately.
TRADITIONAL PROGRAMMING VS AI
AI APPLICATIONS
AI SUBSETS
AI COMPONENTS
TYPICAL EXAMPLE OF AI MODEL
HOW AI MODEL WORKS
Proble Data
Evaluatio
m Exploratio
n
Scoping n

Data Deployme
Acquisitio Modeling nt
n
EXERCISE TIME

• You are working in the HR department of a local company. Pandemic strikes


globally and recession is coming. There is a concern that your fellow colleagues will
leave your company for other companies
• Your boss wants you to investigate and identify those with the highest employee
attrition, so that actions can be taken to retain their talents within the company
Problem
Scoping

• You are working in the HR department of a local company. It is a normal occurrence


that employees leave the company. It was not a big issue in the past since the
company can find a replacement.
• However, currently the company is under pressure due to recession. The company
doesn’t have budget to hire new employees and it is creating stress to the other
employees. Your boss wants you to investigate and predict who is most likely to
quit, so that the management can persuade the person to stay before the person
decides to quit.
HIGHLIGHT THE PROBLEM STATEMENT

• You are working in the HR department of a local company. It is a normal occurrence


that employees leave the company. It was not a big issue in the past since the
company can find a replacement.
• However, currently the company is under pressure due to recession. The company
doesn’t have budget to hire new employees and it is creating stress to the other
employees. Your boss wants you to investigate and predict who is most likely
to quit, so that the management can persuade the person to stay before the
person decides to quit.
HERE’S THE IDEA OUT!

• Through the data collected from our colleagues, there are many factors that may
contribute to employee attrition.
• By using machine learning, we can predict who has the highest probability of
leaving the company, and so we can do our best to retain them. This is an
application of Employee Attrition Prediction!
HUMANS AND MACHINES
TYPES OF MACHINE LEARNING
TYPES OF REGRESSION
MACHINE LEARNING MODEL STEPS

1. Data Collection: Gathering relevant data from various sources to train the model.
2. Data Preprocessing: Cleaning and transforming data to ensure it's in the right format for modeling.
3. Feature Selection/Engineering: Identifying and creating important features that influence the model's
output.
4. Model Selection: Choosing an appropriate algorithm based on the problem type (e.g., regression,
classification).
5. Training: Feeding data into the model to learn patterns and relationships.
6. Evaluation: Testing the model's performance on unseen data to assess accuracy and effectiveness.
7. Tuning/Optimization: Adjusting hyperparameters and refining the model for improved performance.
8. Deployment: Integrating the model into a production environment for real-world use.
9. Monitoring: Continuously tracking model performance to ensure consistency and effectiveness over
time.
DIFFERENT DATA FOR DIFFERENT MODELS
Supervised Learning:
• - Trains on labeled data (input-output pairs).
• - Learns to predict correct outputs based on inputs.
• - Example: Classifying images as "cat" or "dog."
Unsupervised Learning:
• - Uses unlabeled data.
• - Finds patterns or structures in data.
• - Example: Grouping similar customers for marketing.
Reinforcement Learning:
• - Agent interacts with the environment.
• - Learns through rewards and penalties.
• - Example: Teaching a robot to navigate a maze.
EVERY COIN HAS A FLIP!

These are some cons or risks of artificial intelligence


• High implementation cost
• Human replication
• If the control of machines goes in the wrong hands, it may cause destruction.
FUTURE OF AI

• Automation: across industries


• Personalization: user experiences
• Job Changes: transform the future of job market
• Ethics: regulations will evolve for responsible Ai use
SUMMARY

• AI and its need


• Difference between traditional programming and AI
• Applications, types and components of AI
• Machine learning
• Types of Machine Learning-Supervised, Unsupervised and Reinforcement
Learning and their types
• Machine Learning Model steps

You might also like