INTRODUCTION OF
MACHINE LEARNING
AND MODELS
TYPES OF LEARNING, ALGORITHMS & MODEL EVALUATION
Presented By Miss. S. A. Chavan
INTRODUCTION TO MACHINE LEARNING
• ML is a subset of Artificial Intelligence (AI).
• It enables systems to learn and improve automatically from experience.
• Uses data to make predictions or decisions without explicit programming
TYPES OF LEARNING
• Supervised Learning – trained with labeled data.
• Unsupervised Learning – trained with unlabeled data.
• Semi-Supervised Learning – mix of labeled + unlabeled data.
SUPERVISED MACHINE LEARNING
TYPES OF SUPERVISED MACHINE LEARNING
• Classification: Where the output is a categorical variable (e.g., spam vs. non-spam
emails, yes vs. no).
• Regression: Where the output is a continuous variable (e.g., predicting house prices,
stock prices).
SUPERVISED LEARNING ALGORITHMS
• Linear Regression – predicts continuous values (e.g. house price).
• Logistic Regression – predicts binary outcomes (0 or 1).
• Decision Tree – uses tree structure to make decisions.
• K-Nearest Neighbours (KNN) – classifies based on nearest data points.
• Random Forest – group of decision trees (ensemble model).
UNSUPERVISED MACHINE LEARNING
TYPES UNSUPERVISED LEARNING
• [Link]:is an unsupervised machine learning technique that groups unlabeled data
into clusters based on similarity. Its goal is to discover patterns or relationships within
the data without any prior knowledge of categories or labels.
• 2. Association: is a rule-based unsupervised learning technique used to discover
interesting relationships between variables in large datasets. It identifies patterns in the
form of “if-then” rules, showing how the presence of some items in the data implies the
presence of others.
UNSUPERVISED LEARNING ALGORITHMS
• K-Means Clustering – divides data into k clusters.
• KNN (k-Nearest Neighbours) – finds similar data points (used sometimes
unsupervised too).
• Hierarchical Clustering – builds tree of clusters.
• Neural Networks – multiple layers that mimic human brain to learn
complex data.
SEMI SUPERVISED MACHINE LEARNING
• Semi-Supervised Machine Learning is a type of machine learning that sits
between supervised learning and unsupervised learning. It uses a small amount of
labeled data along with a large amount of unlabeled data during training.
• Real-World Applications
1. Email Spam Detection
2. Medical Imaging Diagnosis
3. Speech Recognition
4. Social Media Content Classification
SEMI SUPERVISED MACHINE LEARNING
LIFE CYCLE OF MACHINE LEARNING
MODEL EVALUATION
• Purpose: Check how well the model performs on unseen data.
• Key Method: Cross-Validation
• Benefits of Cross-Validation:
• Prevents overfitting
• Provides better model accuracy
• Uses data efficiently
CROSS VALIDATION IN MACHINE LEARNING
• Cross-validation is a technique used to check how well a machine learning
model performs on unseen data while preventing overfitting. It works by:
• Splitting the dataset into several parts.
• Training the model on some parts and testing it on the remaining part.
• Repeating this resampling process multiple times by choosing different
parts of the dataset.
• Averaging the results from each validation step to get the final
performance.
TYPES CROSS VALIDATION
1.K-Fold
• Divide Entire Data Into the k Folds
• Take average of all and find output
• Disadvantage each and every iteration does nit takes equal representation
of every class it may take overfitting.
TYPES CROSS VALIDATION
[Link] K-Fold
• overcome drawback of k fold
• Equal representation of each and every class.
TYPES CROSS VALIDATION
[Link]-One –Out
• It takes N-1 iteration. its extreme state of k fold, if data k we divide it into
10-1=9.
• Not used in real it takes time
TYPES CROSS VALIDATION
[Link]-P-Out
• We take P examples for the testing rather than one.
• if p=3,this P is selected randomly in every iteration.
POSITIVE & NEGATIVE CLASS CROSS
VALIDATION
• Positive & Negative Class Concept:
• Positive → target class (e.g. spam mail)
• Negative → non-target class (e.g. normal mail)
Thank You…