Scribd
Upload
4 views12 pages

ppt mehul

The document is an ETI report on Machine Learning submitted by Ayon Asit Patra at Katgara Polytechnic Institute for the academic year 2024-25. It covers the fundamentals of machine learning, types such as supervised and reinforcement learning, the machine learning process, various algorithms, real-world applications, challenges, and future trends. Key topics include data collection, model selection, and the importance of ethical considerations in AI development.

Uploaded by

rutukandher
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 views12 pages

ppt mehul

The document is an ETI report on Machine Learning submitted by Ayon Asit Patra at Katgara Polytechnic Institute for the academic year 2024-25. It covers the fundamentals of machine learning, types such as supervised and reinforcement learning, the machine learning process, various algorithms, real-world applications, challenges, and future trends. Key topics include data collection, model selection, and the importance of ethical considerations in AI development.

Uploaded by

rutukandher
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/ 12

Academic Year :

2024 -25

KATGARA POLYTECHNIC INSTITUTE


ETI Report On :
MACHINE LEARNING
Submitted by :
Ayon . Asit . Patra

Guided By : HOD :
RIYA . I. WAGASKAR ISHAN . B .WAGASKAR
Academic Year :
2024 -25

KATGARA POLYTECHNIC INSTITUTE


ETI Report On :
MACHINE LEARNING
Submitted by :
Ayon . Asit . Patra

Guided By : HOD :
RIYA . I. WAGASKAR ISHAN . B .WAGASKAR
Academic Year :
2024 -25

KATGARA POLYTECHNIC INSTITUTE


ETI Report On :
MACHINE LEARNING
Submitted by :
Ayon . Asit . Patra

Guided By : HOD :
RIYA . I. WAGASKAR ISHAN . B .WAGASKAR
Machine Learning Explained
Machine learning uses algorithms that learn patterns from data. This allows
computers to make predictions or decisions. It happens without explicit
programming. The core idea is performance improvement through experience.
This is unlike traditional programming which relies on defined rules.
Types of Machine Learning
Supervised Learning Reinforcement Learning

Learning from labeled data, examples include classification and Learning through trial and error, examples include robotics and
regression. game playing.

• Linear Regression • Q-Learning


• Logistic Regression • Deep Q-Networks
• SVMs • Policy Gradients
The Machine Learning Process
Data Collection
Gather relevant data. Consider quality and volume.

Preprocessing
Clean and transform the data. Handle missing values.

Model Selection
Choose an algorithm. Consider accuracy and cost.

Training
Feed data to learn patterns. Optimize parameters.
Regression Algorithms
Linear Regression Polynomial Regression

Models relationships using linear equations. Extends linear regression with polynomial functions.

Use case: predicting sales based on spend. Use case: modeling growth curves and crop yield.
Classification Algorithms

Logistic Regression
Predicts probability. Use case: spam detection.

Random Forests
Ensemble method. Use case: image classification.

Neural Networks
Complex models. Use case: pattern recognition.
Real-World Applications

Healthcare Finance Retail


Disease diagnosis and Fraud detection and Recommendation
personalized medicine. algorithmic trading. systems and customer
segmentation.

Transportation
Autonomous vehicles
and traffic optimization.
Challenges and Limitations

Bias

1 Data reflects existing prejudice.

Overfitting
2 Poor unseen data performance.

Interpretability
3 Decision process is unclear.

Computation
4 Training complex models is costly.
The Future of Machine Learning

The future includes AutoML and TinyML. Also, quantum ML and Explainable AI are key. Ethical AI and continuous learning will emerge.

You might also like