Scribd
Upload
2 views3 pages

AI Modelling Concepts and Techniques

The document covers advanced concepts in AI, including definitions and distinctions between AI, Machine Learning (ML), and Deep Learning (DL). It outlines key data terminology, modeling approaches (rule-based vs. learning-based), types of machine learning (supervised, unsupervised, reinforcement), and details on neural networks and their applications. Additionally, it highlights the specific deep learning model, Convolutional Neural Networks (CNN), primarily used for image processing.

Uploaded by

isk160410
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
2 views3 pages

AI Modelling Concepts and Techniques

The document covers advanced concepts in AI, including definitions and distinctions between AI, Machine Learning (ML), and Deep Learning (DL). It outlines key data terminology, modeling approaches (rule-based vs. learning-based), types of machine learning (supervised, unsupervised, reinforcement), and details on neural networks and their applications. Additionally, it highlights the specific deep learning model, Convolutional Neural Networks (CNN), primarily used for image processing.

Uploaded by

isk160410
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

Advanced Concepts of Modelling in AI – Summary Notes

1. AI, ML, and Deep Learning

Artificial Intelligence (AI): Machines performing tasks requiring human intelligence.

Machine Learning (ML): Subset of AI; learns patterns from data.

Deep Learning (DL): Subset of ML using neural networks with many layers; works well on large
datasets.

2. Data Terminology

Data: Raw information.

Features: Attributes describing data.

Labels: Value to be predicted.

Training Set: Data used to teach the model.

Testing Set: Data used to evaluate the model.

3. AI Modelling Approaches

A. Rule-Based Approach

• Uses fixed rules set by humans.

• Does not learn or adapt.

• Example: Simple chatbots.

B. Learning-Based Approach

• Learns patterns from data.

• Improves accuracy with more experience.

4. Machine Learning Types

A. Supervised Learning (Labeled data)

1. Classification – predicts categories.

Examples: Spam/Not spam, Dog/Cat.

2. Regression – predicts numeric values.

Examples: Price, temperature.

B. Unsupervised Learning (Unlabeled data)

1. Clustering – groups similar items.

2. Association – finds relationships (e.g., “Bread → Butter”).


C. Reinforcement Learning

• Learns by trial and error.

• Receives rewards and penalties.

5. Neural Networks (ANN)

What are Neural Networks?

• Computer models inspired by the human brain.

• Used for recognition, predictions, and decision-making.

Structure:

• Input Layer – receives data

• Hidden Layers – extract patterns

• Output Layer – final prediction

How ANN Works:

• Inputs × Weights → add Bias → Activation function → Output

• Learns using forward propagation and backpropagation.

Key Terms:

• Weights – importance of inputs

• Bias – adjustment term

• Activation Function – helps model learn complex patterns

Applications:

• Face recognition

• Voice assistants

• Medical imaging

• Chatbots

• Fraud detection

6. Deep Learning Specific Model: CNN

• Used mainly for image processing.

• Layers: Convolution, ReLU, Pooling, Fully Connected.

• Applications: Face ID, object detection, medical scans.

You might also like