• Introduction to AI & ML: Concepts, History, Applications
• Roles in AI/ML
• Linear Algebra & Calculus Essentials for ML
• Probability & Statistics Review
• Python Refresher: Advanced Topics (Lambda, Comprehensions, etc.)
• Introduction to NumPy for numerical computing
• Introduction to Pandas for data manipulation
• Jupyter Notebooks & Google Colab
• Git & GitHub for ML projects

• ML Workflow Overview
• Handling Missing Data (Imputation Techniques)
• Dealing with Categorical Data (One-Hot Encoding, Label Encoding)
• Feature Scaling (Standardization, Normalization)
• Outlier Detection and Handling
• Feature Engineering: Creating New Features
• Feature Selection Techniques
• Introduction to Principal Component Analysis (PCA) for Dimensionality Reduction
• Data Splitting (Train/Test/Validation) & Cross-Validation

• Introduction to Supervised Learning
• Linear Regression (Simple & Multiple)
• Polynomial Regression & Overfitting
• Regularization (Lasso, Ridge, Elastic Net)
• Logistic Regression (Binary & Multinomial)
• Classification Metrics (Accuracy, Precision, Recall, F1-Score, ROC-AUC)
• K-Nearest Neighbors (KNN)
• Decision Trees (Building, Pruning)
• Support Vector Machines (SVMs)
• Model Selection & Hyperparameter Tuning (Grid Search, Randomized Search)

• Introduction to Ensemble Learning
• Bagging (Random Forests)
• Boosting (AdaBoost, Gradient Boosting, XGBoost, LightGBM)
• Stacking
• Introduction to Unsupervised Learning
• Clustering (K-Means, Hierarchical Clustering, DBSCAN)
• Introduction to Anomaly Detection
• Evaluation Metrics for Clustering (Silhouette Score - Intro)

• Introduction to Neural Networks
• Perceptrons & Activation Functions
• Multi-Layer Perceptrons (MLPs)
• Forward Propagation & Backpropagation (Conceptual)
• Optimizers (SGD, Adam, RMSprop) & Loss Functions
• Introduction to TensorFlow/Keras
• Building, Training, and Evaluating Simple ANNs
• Introduction to Convolutional Neural Networks (CNNs) for Image Data
• Introduction to Recurrent Neural Networks (RNNs) for Sequence Data
• Regularization in Deep Learning (Dropout, Early Stopping)

• Brief Introduction to PyTorch (Optional)
• Introduction to Computer Vision Tasks (Image Classification, Object Detection Concepts)
• Introduction to Natural Language Processing Tasks (Text Classification, Sentiment Analysis Concepts)
• Working with Time Series Data (ML Approaches)
• Model Interpretation (Feature Importance - Intro)
• Introduction to Model Deployment Concepts (Saving/Loading Models, Basic Flask API)
• AI/ML Capstone Project: End-to-End Implementation
• Career Guidance & Portfolio Building for AI/ML Roles

This specialization is designed for individuals with a foundational understanding of programming (preferably Python) and basic math/statistics, who want to build a career in AI or Machine Learning. It's suitable for data analysts, software engineers, graduates from quantitative fields, and those looking for a deep dive into building intelligent systems.

A solid grasp of Python programming basics and an understanding of fundamental mathematics (linear algebra, calculus, probability, statistics) is highly recommended. While we review math concepts, prior exposure is beneficial. Some prior data analysis experience is a plus but not strictly required.

You will primarily work with Python and its key libraries for ML, including NumPy, Pandas, Scikit-learn, and deep learning frameworks like TensorFlow/Keras and potentially an introduction to PyTorch. We'll also touch upon tools for model deployment.

Yes, upon successfully completing all modules, assignments, and the capstone project, you will earn a Certificate of Specialization in AI & Machine Learning from CodeParallels.

While Data Science is a broader field that includes analytics, visualization, and some ML, this specialization focuses specifically and more deeply on the algorithms, modeling, and deployment aspects of Machine Learning and Artificial Intelligence. It prepares you for roles centered around building and implementing AI/ML solutions.