AI & Machine Learning Curriculum
A comprehensive 20-week journey into artificial intelligence and machine learning. Build intelligent systems that analyze data, learn from patterns, and make predictions through practical, hands-on projects.
Program Investment
What's Included
- 20 week intensive program
- 24/7 mentor-assisted learning
- 12+ AI & ML projects
- GPU-enabled cloud environments
- Blockchain-verified portfolio
Foundations & Setup
Week 0
Goal: Establish development environment and mathematical foundations.
Topics:
- Python development environment setup (Anaconda, Jupyter, VS Code)
- Mathematics review: Linear algebra, statistics, calculus basics
- Introduction to AI/ML landscape and career paths
- Git workflow for data science projects
Machine Learning Fundamentals
Weeks 1-2
Goal: Understand core ML concepts and supervised learning.
Topics:
- Supervised & unsupervised learning, model evaluation
- Feature engineering and data preprocessing
- Scikit-learn library fundamentals
- Overfitting, underfitting, and bias-variance tradeoff
- Bias Clinic: Introduction to algorithmic bias and fairness metrics
Bias Clinic Session
Audit your house price prediction model for socioeconomic bias. Analyze how features like zip code, neighborhood demographics, and historical pricing patterns may encode systemic inequities.
Project:
House price prediction model with feature engineering + bias documentation
Advanced Machine Learning
Weeks 3-4
Goal: Master unsupervised learning and ensemble methods.
Topics:
- Clustering, dimensionality reduction (PCA, t-SNE)
- Ensemble methods: Random Forest, Gradient Boosting, XGBoost
- Hyperparameter tuning and model selection
- Feature selection and importance analysis
Project:
Customer segmentation and recommendation system
Neural Networks & Deep Learning
Weeks 5-6
Goal: Build and train neural networks from scratch.
Topics:
- Neural network fundamentals and backpropagation
- Deep learning frameworks: TensorFlow and PyTorch
- Activation functions, loss functions, and optimizers
- Regularization techniques: dropout, batch normalization
Project:
Multi-class image classifier using neural networks
Convolutional Neural Networks
Weeks 7-8
Goal: Implement computer vision solutions with CNNs.
Topics:
- CNN architecture: convolution, pooling, fully connected layers
- Popular architectures: LeNet, AlexNet, VGG, ResNet
- Transfer learning and pre-trained models
- Image processing, object detection, OpenCV
Project:
Real-time object detection application
Recurrent Neural Networks
Weeks 9-10
Goal: Process sequential data with RNNs and LSTMs.
Topics:
- RNN fundamentals and vanishing gradient problem
- LSTM and GRU architectures
- Sequence-to-sequence models and attention mechanisms
- Time series forecasting and analysis
Project:
Stock price prediction and sentiment analysis system
Natural Language Processing
Weeks 11-12
Goal: Build intelligent text processing applications.
Topics:
- Text preprocessing, sentiment analysis, chatbots
- Word embeddings: Word2Vec, GloVe, contextual embeddings
- Transformer architecture and attention mechanisms
- BERT, GPT, and modern language models
- Bias Clinic: Language model bias, toxicity detection, responsible AI frameworks
Bias Clinic Session
Test language models for gender, racial, and cultural biases in text generation. Implement toxicity filters and analyze how training data shapes model outputs. Document stakeholder impact and create responsible AI guidelines.
Project:
Intelligent chatbot with sentiment analysis + bias mitigation and content moderation
Computer Vision Applications
Weeks 13-14
Goal: Develop advanced computer vision systems.
Topics:
- Face recognition, object detection, face recognition
- Object tracking and motion analysis
- Image segmentation and edge detection
- Real-time video processing with OpenCV
- Bias Clinic: Surveillance ethics, facial recognition bias across demographics
Bias Clinic Session
Analyze facial recognition accuracy across different skin tones, genders, and age groups. Examine privacy implications, consent frameworks, and the ethics of surveillance technology deployment in public spaces.
Project:
Computer vision application with documented ethical considerations and bias mitigation strategies
Capstone Project
Weeks 15-16
Goal: Deliver a comprehensive AI solution for real-world problems.
Capstone Options:
- Predictive Analytics Dashboard for business intelligence
- Computer Vision Application for healthcare or security
- NLP-powered content analysis and recommendation system
- AI-powered automation solution for specific industry
Requirements:
End-to-end AI solution with data pipeline, model deployment, web interface, and production-ready code
Ethical Documentation Required
All capstone projects must include: (1) Bias audit report, (2) Fairness metrics analysis, (3) Stakeholder impact assessment, (4) Documented ethical considerations, (5) Mitigation strategies for identified risks
Ready to start your journey in AI & Machine Learning?
Apply to Skymirror Academy