Machine Learning PCCST503 Semester 5 KTU CS 2024 Scheme - Dr Binu V P

  📘 Introduction to Machine Learning (ML) 🔹 What is Machine Learning? Machine Learning is a subfield of Artificial Intelligence that focuses on developing algorithms that allow computers to learn patterns from data and make decisions or predictions without explicit programming . It focuses on developing algorithms and models that allow machines to: Identify patterns in data Make decisions with minimal human intervention Predict future outcomes based on past experiences By continuously learning from new data, machine learning systems become more accurate and efficient over time. 📌 Formal Definition  A computer program is said to learn from experience E with respect to some task T and performance measure P if its performance at task T , as measured by P , improves with experience E . 🔹 Why Machine Learning? Traditional programming: Input + Program → Output Machine Learning paradigm: Input + Output → Model (learned program) 👉 Instead of writing...

  📘 Distinguishing Machine Learning from Traditional Programming 🔹 1. Fundamental Idea 🧾 Traditional Programming In conventional programming, developers write explicit instructions for the system to follow. The programmer explicitly writes rules/logic System follows deterministic instructions Input data is processed using predefined rules The output is based strictly on those rules 👉 Flow: Input + Program → Output 🤖 Machine Learning In machine learning, the system learns patterns from data instead of being explicitly programmed. Programmer provides  data + learning algorithm The model is trained using data The system  learns rules automatically from data It makes predictions or decisions based on learned patterns 👉 Flow: Input + Output → Learning Algorithm → Model Model + New Input → Predicted Output 🔹 2. Key Difference in Approach Aspect      Traditional Programming Machine Learning Input method Logic creation   ...

  📘 Unsupervised Learning 🔹 Definition Unsupervised Learning is a type of Machine Learning where the model is trained on unlabeled data , i.e., data without predefined outputs. 👉 Goal: Discover hidden patterns, structures, or relationships in data. This type of learning is particularly useful for discovering clusters in data, detecting anomalies, and finding associations. Techniques like clustering, association rule mining, and dimensionality reduction allow for deeper insights into complex datasets. It's widely used in customer segmentation, fraud detection, and market basket analysis. 🔹 Key Idea Given only input data: X = { x 1 , x 2 , x 3 , . . . , x n } X = \{x_1, x_2, x_3, ..., x_n\} 👉 The model tries to: Group similar data Identify patterns Reduce dimensionality 🔹 Characteristics No labeled outputs No “teacher” Exploratory in nature Used for pattern discovery Pic Courtesy: database town 🔹Types of Unsupervised Learning 🟦 A. Clustering ...

  Stages of Machine Learning: From Data Collection to Deployment Machine learning isn’t just about training a model—it’s a pipeline of interconnected steps . Each stage affects the final performance, reliability, and usefulness of the system. 1. Define the Problem & Collect Data This is the foundation. If this step is wrong, everything else suffers. 🔹 What happens here: Clearly define: What problem are you solving? (e.g., fraud detection, price prediction) What type of task? (classification, regression, clustering) Collect relevant data from: Databases APIs Sensors User interactions 🔹 Why it matters: Good models require relevant + high-quality data Poor data = poor predictions (no matter how advanced the model) 2. Data Preparation & Cleaning Raw data is messy. This stage makes it usable. 🔹 Key tasks: Handle missing values (fill or remove) Remove duplicates Detect and treat outliers Normalize/scale numerical features Conve...

  🔹 What is the XOR Problem? 1. 🧠 Definition The XOR (Exclusive OR) function outputs: 1 when inputs are different 0 when inputs are same Truth Table: x₁      x₂      XOR Output 0      0      0 0      1      1 1      0      1 1      1      0 2. ❌ Why is XOR a Problem for Perceptron? A single-layer perceptron can only learn linear decision boundaries (straight lines). XOR is not linearly separable : No single straight line can separate: (0,1) and (1,0) → class 1 (0,0) and (1,1) → class 0 ➡️ This limitation is called the XOR problem . 3. 📐 Geometric Intuition Points lie diagonally: Class 1 → opposite corners Class 0 → opposite corners ➡️ Requires non-linear separation 🔹 Solution: Multi-Layer Perceptron (MLP) 4. 🧩 Key Idea Add a hidden layer to: Transform input space Create non-li...