Day 1: Introduction to AI & ML

• Hour 1-2: AI vs ML vs Deep Learning: Definitions and Differences
• Hour 2-3: Importance and Applications of AI & ML
• Hour 3-4: Setting up the Environment (Python, Jupyter Notebook, Libraries)
• Hour 4-8: Python Refresher: Essential Libraries for ML (NumPy, pandas)

Day 2: Supervised Learning - Basics

• Hour 1-2: Introduction to Supervised Learning
• Hour 2-3: Linear Regression
• Hour 3-6: Logistic Regression, Naive Bayes, KNN
• Hour 6-8: Hands-on: Building & Evaluating Regression Models

Day 3: Supervised Learning - Advanced

• Hour 1-2: Decision Trees and Random Forests
• Hour 2-3: Support Vector Machines (SVM)
• Hour 3-6: Ensemble Methods: Boosting, Bagging
• Hour 6-8: Hands-on: Classification Problems & Model Evaluation

Day 4: Unsupervised Learning

• Hour 1-2: Introduction to Unsupervised Learning
• Hour 2-4: Clustering: K-means, Hierarchical
• Hour 4-6: Dimensionality Reduction: PCA, t-SNE
• Hour 6-8: Hands-on: Clustering and Visualization

Day 5: Neural Networks and Deep Learning - Basics

• Hour 1-2: Introduction to Neural Networks
• Hour 2-3: Forward and Backward Propagation
• Hour 3-4: Activation Functions, Loss Functions
• Hour 4-8: Hands-on: Building a Basic Neural Network with TensorFlow/Keras

Day 6: Convolutional Neural Networks (CNNs)

• Hour 1-2: Introduction to CNNs
• Hour 2-3: Image Classification and Feature Learning
• Hour 3-4: Pooling, Flattening, and Full Connection
• Hour 4-8: Hands-on: Image Recognition Tasks with CNNs

Day 7: Recurrent Neural Networks (RNNs) and Natural Language Processing

• Hour 1-2: Introduction to RNNs and LSTM
• Hour 2-5: Basics of Natural Language Processing (Tokenization, Embedding, TfIdf, Bag of Words)
• Hour 5-6: Sequence Models and Attention Mechanism
• Hour 6-8: Hands-on: Text Generation and Sentiment Analysis

Day 8: Dive into Large Language Models (LLMs)

• Hour 1-2: Introduction to LLMs
• Hour 2-3: Inner Workings of GPT-style Models
• Hour 3-4: Training and Fine-tuning LLMs
• Hour 4-5: Practical Applications of LLMs
• Hour 5-6: Ethical Considerations and Limitations
• Hour 6-7: Hands-on Session: Using Pre-trained LLMs
• Hour 7-8: Advanced Topics & Wrap-up

Prerequisites for AI and Machine Learning Master’s Program

• Candidates must have a bachelor’s degree with an average score of 50% or more
• Understanding of basic concepts in programming, statistics and mathematics is required
• Candidates with 2+ years of working experience in AI and Machine learning are advised to take up this course. Nevertheless, having work experience is not mandatory and candidates with no experience can also apply.

Note - Candidates are advised to have knowledge of Python before taking up this course. We offer a free pre-course session for candidates who do not have knowledge about python to help them understand the master program better.

Talk to our Master’s Program Counselor in AI and Machine Learning certification for a better understanding of the scope and application process of this AI and Machine Learning course. We have a team of dedicated experts at Sprintzeal who will guide you with the master program details, application process, and other essential queries.