Machine Learning Algorithms

Learning Machine Algorithms provides a comprehensive introduction to core machine learning and deep learning concepts, spanning supervised and unsupervised learning, neural network architectures, computer vision, and natural language processing. It progresses from classical algorithms to modern deep learning frameworks and state-of-the-art models. This also introduces Generative AI, equipping students with both theoretical understanding and hands-on experience using industry-standard libraries.

Hierarchical Relationship

Artificial Intelligence (AI)
- Machine Learning (ML)
  - Supervised Learning
  - Unsupervised Learning
  - Reinforcement Learning
  - Deep Learning
    - Artificial Neural Networks (ANN)
    - Recurrent Neural Networks (RNN)
      - LSTM
      - GRU
    - Convolutional Neural Networks (CNN)
    - Transformers
      - BERT
      - GPT
      - LLaMA
      - Mistral
Evolutionary Computation
- Genetic Algorithms (GA)
- Genetic Programming
- Particle Swarm Optimization (PSO)
- Ant Colony Optimization (ACO)
Symbolic AI
- Expert System
- Logic Programming
- Knowledge Representation & Reasoning

Key skills you gain

Machine Learning Fundamentals: Build predictive models using supervised and unsupervised learning techniques, feature engineering, model evaluation, and optimization methods.
Data Analysis & Model Development: Prepare, analyze, and visualize data using Python, NumPy, Pandas, and Scikit-learn to develop real-world machine learning solutions.
Deep Learning & Neural Networks: Design and train Artificial Neural Networks (ANNs), Convolutional Neural Networks (CNNs), and Recurrent Neural Networks (RNNs) using TensorFlow and PyTorch.
Advanced AI Applications: Develop intelligent systems for computer vision, natural language processing, recommendation systems, and generative AI applications with industry-standard frameworks.

CURRICULUM

Artificial Neural Networks

Machine learning has evolved rapidly, driving a surge of interest in Artificial Neural Networks (ANNs. They are computational models that draw inspiration from the structure and operations of the human brain. They comprise interconnected nodes, or artificial neurons, organized in layers. Neural networks are designed to process and examine complex data, recognize patterns, and make predictions or decisions based on their learned knowledge. They excel in solving problems that are difficult to define using traditional programming techniques or when explicit rules are unavailable.

Deep learning refers to the process of training these networks, allowing them to process raw or minimally processed data and automatically identify patterns—a concept known as feature learning or representation learning.

You will learn both the theory behind these technologies and how to apply them to real problems in machine learning and data mining. Through hands-on exercises, you will also practise training and evaluating different ANN models, helping you develop a strong foundation in the field.

Topics Covered

Foundations of Neural Networks:	Organization of the Human Brain, Biological Neuron: Structure and Function, Features and Working of Biological Neural Networks (BNN), Biological vs Artificial Neurons, Artificial Neuron Models, Characteristics of Artificial Neural Networks (ANN), Comparison of Biological Neural Networks and Artificial Neural Networks, Models of Neurons.
Perceptron and Learning Principles:	Principles of Neural Network Design, McCulloch-Pitts Neuron Model, Perceptron Learning Model, Adaline and Madaline Models, Basic Learning Laws, Linear Separability, XOR Problem and Its Solution, Single Layer Neural Networks, Multilayer Perceptrons (MLP).
Backpropagation Networks:	Backpropagation Learning, Feedforward Neural Networks, Input Layer / Hidden Layer / Output Layer Computations, Backpropagation Algorithm, Error Calculation and Weight Updates, Selection of Learning Parameters, Number of Hidden Nodes, Stability and Convergence Analysis.
Self-Organizing, Counter Propagation and Associative Memory Networks:	Counter Propagation Networks, Kohonen Layer, Grossberg Layer, Self-Organizing Maps (SOM), Competitive Learning, Clustering and Visualization Applications, Hopfield Networks, Energy Functions and Network Stability, Bidirectional Associative Memory (BAM), Pattern Storage and Recall, Applications of Associative Memory Networks.
Stochastic and Adaptive Models:	Boltzmann Machines, Stochastic Learning, Energy-Based Models, Boltzmann Learning Algorithm, Applications of Boltzmann Machines, Fundamentals of ART Networks, ART Architecture and Components, Features of ART Models, Stability-Plasticity Dilemma, Character Recognition using ART Networks.
Libraries:	NumPy, SciPy, Matplotlib, Seaborn, Pandas, Scikit-learn, TensorFlow, Keras, MiniSom, PyTorch

Knowledge Discovery and Data Mining (KDDM)

Knowledge Discovery and Data Mining (KDDM) is the process of discovering meaningful, valid, and actionable knowledge from large volumes of data. It combines data preprocessing, statistical analysis, machine learning, pattern recognition, and visualization techniques to identify hidden patterns, relationships, trends, and insights that support informed decision-making. KDDM enables organizations to transform raw data into valuable knowledge, improve operational efficiency, support strategic decision-making, and drive innovation in the era of Artificial Intelligence and Big Data.

Topics Covered

Classification:	k-Nearest Neighbors (KNN), Decision Trees (ID3, C4.5, CART), Naïve Bayes Classifier, Random Forest, and Support Vector Machines (SVM)
Clustering:	K-Means, DBSCAN, and Hierarchical Clustering
Association Mining:	Apriori and FP-Growth
Regression:	Linear Regression, Polynomial Regression, and Logistic Regression
Libraries:	NumPy, Matplotlib, Pandas, scikit-learn, Seaborn

Deep Learning

Deep learning is a subfield of machine learning. Deep learning models are characterized by having multiple hidden layers (referred to as deep neural networks) between the input and output layers. These deep neural networks can learn hierarchical representations of data by automatically discovering intricate features and patterns at different levels of abstraction. Deep learning models excel at learning from large and complex datasets, and they have achieved remarkable success in various AI tasks, such as computer vision, natural language processing, speech recognition, and more.

Deep learning is a powerful technique within the broader context of neural networks, enabling the development of highly advanced AI models.

Topics Covered

Convolutional Neural Networks (CNN):	Convolutional layers (filters, kernels, stride, padding), Pooling layers (Max / Average pooling), Flattening, Fully Connected (FC) layers, Softmax output.
Classic CNN Architectures:	LeNet-5, AlexNet, VGGNet (VGG-16/VGG-19), GoogLeNet / Inception, ResNet (Residual Networks), MobileNet.
Sequential Models:	Recurrent Neural Networks (RNNs), Long Short-Term Memory (LSTM), Gated Recurrent Units (GRU).
Libraries and Frameworks:	PyTorch, TensorFlow, Keras, torchvision, NumPy, Matplotlib, Scikit-learn, Hugging Face Transformers, OpenCV, Pandas, tqdm, ONNX Runtime.

Computer Vision Models

Develop expertise in designing intelligent vision systems capable of detecting, classifying, segmenting, and understanding visual data. Students work with state-of-the-art object detection and segmentation models used in autonomous systems, healthcare, surveillance, and industrial automation.

Topics Covered

Single-Stage Object Detection Models:	YOLO (v8/v9/v10/v11), SSD (Single Shot Multibox Detector), and RetinaNet.
Two-Stage Object Detection Models:	R-CNN (Regions with CNN), Fast R-CNN, Faster R-CNN.
Semantic Segmentation Models:	U-Net, DeepLabv3+, PSPNet (Pyramid Scene Parsing Network), SegNet, SAM2 (Segment Anything Model 2), Mask2Former.
Frameworks, Libraries & AI Model Platforms:	PyTorch, TensorFlow, Ultralytics, Detectron2, torchvision, OpenCV, segmentation-models-pytorch, Hugging Face Transformers, ONNX Runtime, Albumentations, NumPy, Matplotlib.

Natural Language Processing (NLP)

Learn how machines process, understand, and generate human language. Students explore modern NLP techniques ranging from text preprocessing and language representation to transformer-based large language models used in chatbots, search engines, virtual assistants, and generative AI applications.

Topics Covered

Natural Language Processing (NLP):	Origins, Challenges, and Applications of NLP, Text tokenization, Normalization, and Language modeling, Bag of Words (BoW).
Preprocessing and Text Representation:	Stemming, lemmatization, stop-word removal, morphological analysis, Bag-of-words, TF-IDF, word embeddings (Word2Vec, GloVe), ELMo (Embeddings from Language Models).
Syntactic Analysis and Semantics:	Part-of-Speech (POS) tagging, constituency parsing, dependency parsing, Named Entity Recognition (NER), distributional semantics, and topic modeling (LDA, NMF).
Transformer-Based Models:	BERT (Bidirectional Encoder Representations from Transformers), GPT (Generative Pre-trained Transformer), Transformer-XL, RoBERTa.
Libraries and Frameworks:	NLTK, spaCy, Gensim, Scikit-learn, Hugging Face Transformers, PyTorch, TensorFlow, Keras, NumPy, Pandas, ONNX Runtime, Matplotlib.