Objective
- Build foundational AI/ML knowledge and practical skills for entry-level tasks.
- Understand key concepts in deep learning, with a focus on ANN.
- Complete a guided capstone project to showcase learning.
Structure
Weekly progress combines theoretical sessions, hands-on tasks, and project work to ensure steady growth.
Month 1: Fundamentals of AI/ML and Tools
Week 1: Introduction to AI and ML
- Topics:
- What is AI? Branches of AI and real-world applications.
- What is ML? Types of ML: Supervised, Unsupervised, Reinforcement Learning.
- Overview of ML workflows.
- Tasks:
- Identify ML applications in day-to-day life.
- Set up Python and essential libraries (NumPy, Pandas, Matplotlib).
Week 2: Python for Data Analysis
- Topics:
- Data exploration and manipulation using Pandas.
- Data visualization with Matplotlib and Seaborn.
- Tasks:
- Perform EDA on a sample dataset.
- Generate summary statistics and data visualizations.
Week 3: Introduction to Machine Learning Algorithms
- Topics:
- Linear Regression, Logistic Regression.
- Performance metrics: Accuracy, Precision, Recall, and F1-score.
- Tasks:
- Build and evaluate a Linear Regression model for predicting housing prices.
Week 4: Data Preprocessing and ML Pipelines
- Topics:
- Handling missing data, scaling, encoding categorical variables.
- Introduction to ML pipelines.
- Tasks:
- Create a pipeline for preprocessing and training a model using scikit-learn.
Month 2: Core Machine Learning and Deep Learning Foundations
Week 5: Decision Trees and Ensemble Methods
- Topics:
- Decision Trees: Working and applications.
- Ensemble methods: Bagging (Random Forest), Boosting (Gradient Boosting).
- Tasks:
- Build a Random Forest model for classification tasks.
Week 6: Unsupervised Learning
- Topics:
- K-Means Clustering, Hierarchical Clustering.
- Dimensionality Reduction: PCA.
- Tasks:
- Apply K-Means to segment customers in a retail dataset.
Week 7: Introduction to Deep Learning and Artificial Neural Networks (ANN)
- Topics:
- What is Deep Learning? ANN architecture and components.
- Activation functions: Sigmoid, ReLU, Softmax.
- Forward propagation and backpropagation.
- Tasks:
- Implement an ANN for binary classification using TensorFlow/Keras.
Week 8: Advanced ANN Concepts
- Topics:
- Optimizers: Gradient Descent, Adam.
- Regularization techniques: Dropout, Batch Normalization.
- Tasks:
- Improve an ANN model using dropout and different optimizers.
Month 3: Capstone Project and Future Skills
Week 9: Capstone Project Planning
- Activities:
- Select a dataset (e.g., loan approval, e-commerce trends).
- Define the project’s objectives and success metrics.
Week 10: Model Development
- Activities:
- Build an end-to-end ML model pipeline, train, and evaluate.
- Document findings and insights.
Week 11: Deployment Basics
- Topics:
- Introduction to model deployment using Flask/Streamlit.
- Tasks:
- Create a simple interface to showcase the project.
Week 12: Presentation and Feedback
- Activities:
- Present the project to mentors and peers.
- Receive feedback and refine the project.