🤖 AI & Machine Learning
Introduction to Artificial Intelligence with Python
Learn the core concepts, tools, and practices of modern AI using Python. You will set up a productive environment, refre...
93
Views
Sections
1. Orientation and Python Environment Setup780 views
Set up the Python environment, tools, and workflows you will use throughout the course.
15 topics (15 versions)
1.1Syllabus Overview
281
1.2Learning Outcomes
196
1.3Software Requirements
303
1.4Python Installation
1.5Virtual Environments
1.6IDE Setup VS Code
1.7Jupyter Notebooks
1.8Conda vs Pip
1.9Project Structure
1.10Git and GitHub
1.11Command Line Basics
1.12Reproducibility Basics
1.13Dataset Sources
1.14Asking for Help
1.15Course Project Brief
2. Python Essentials for AI233 views
Refresh core Python features and patterns most useful for AI and data-intensive programming.
15 topics (15 versions)
2.1Python Syntax Review
51
2.2Data Types
124
2.3Control Flow
55
2.4Functions
2.5Modules and Packages
2.6File I/O
2.7List Comprehensions
1
2.8Generators
1
2.9Error Handling
2.10Object-Oriented Basics
2.11Typing Hints
2.12Dataclasses
2.13Itertools and Functools
2.14Logging Basics
2.15Performance Tips
1
3. AI Foundations and Problem Framing375 views
Understand what AI is, how to frame problems, and how to plan experiments responsibly.
15 topics (15 versions)
3.1What Is AI
133
3.2AI vs ML vs DL
84
3.3Intelligent Agents
158
3.4Problem Types
3.5Data vs Model Tradeoffs
3.6Bias and Leakage
3.7Train Test Split Concept
3.8Metrics Selection
3.9Baseline Models
3.10Experiment Design
3.11Reproducible Pipelines
3.12Data Ethics Overview
3.13Human in the Loop
3.14Documentation Practices
3.15Reading Research
4. Math for Machine Learning270 views
Build the mathematical foundation in linear algebra, calculus, probability, and statistics for ML.
15 topics (15 versions)
4.1Linear Algebra Vectors
115
4.2Matrices and Operations
81
4.3Matrix Decomposition
73
4.4Calculus Derivatives
4.5Chain Rule
4.6Gradient Descent Math
4.7Norms and Distances
4.8Probability Basics
1
4.9Random Variables
4.10Distributions
4.11Expectation and Variance
4.12Bayes Theorem
4.13Statistical Inference
4.14Hypothesis Testing
4.15Convexity Basics
5. Data Handling with NumPy and Pandas303 views
Manipulate arrays and tabular data efficiently using NumPy, Pandas, and basic visualization.
15 topics (15 versions)
5.1NumPy Arrays
57
5.2Broadcasting Rules
78
5.3Vectorization Patterns
168
5.4Random Number Generation
5.5Pandas Series
5.6DataFrame Operations
5.7Indexing and Selection
5.8GroupBy and Aggregation
5.9Merging and Joins
5.10Time Series Basics
5.11Missing Data Handling
5.12Categorical Data
5.13Visualization with Matplotlib
5.14Seaborn Quickstart
5.15Performance Optimization
6. Data Cleaning and Feature Engineering248 views
Prepare high-quality datasets and craft informative features using robust, repeatable pipelines.
15 topics (15 versions)
6.1Data Quality Assessment
60
6.2Outlier Detection
73
6.3Imputation Strategies
114
6.4Scaling and Normalization
6.5Encoding Categoricals
6.6Feature Hashing
6.7Feature Selection
6.8Dimensionality Reduction
1
6.9Text Vectorization
6.10Image Preprocessing
6.11Signal Processing Basics
6.12Feature Crossing
6.13Target Leakage Avoidance
6.14Pipeline Construction
6.15Feature Store Concepts
7. Supervised Learning Fundamentals5 views
Learn core supervised algorithms, when to use them, and how to implement them in Python.
15 topics (15 versions)
7.1Linear Regression
7.2Regularized Regression
7.3Logistic Regression
7.4kNN Classifier
7.5Naive Bayes
1
7.6Decision Trees
1
7.7Random Forests
7.8Gradient Boosting
1
7.9XGBoost Basics
7.10SVM Classification
7.11Calibration Methods
7.12Multiclass Strategies
1
7.13Imbalanced Learning
7.14Hyperparameter Tuning
1
7.15Model Interpretation
8. Model Evaluation and Validation0 views
Evaluate models rigorously with proper validation, metrics, diagnostics, and reporting.
15 topics (15 versions)
8.1Train Validation Test
8.2Cross Validation
8.3Stratification
8.4Metrics for Regression
8.5Metrics for Classification
8.6ROC and AUC
8.7Precision Recall Curves
8.8Confusion Matrix
8.9Learning Curves
8.10Bias Variance Tradeoff
8.11Error Analysis
8.12Ablation Studies
8.13Model Robustness
8.14Reproducible Reports
8.15Model Cards Basics
9. Unsupervised Learning Techniques4 views
Explore unsupervised methods for structure discovery, compression, and anomaly detection.
15 topics (15 versions)
9.1kMeans Clustering
1
9.2Hierarchical Clustering
9.3DBSCAN
9.4Gaussian Mixtures
9.5Dimensionality Reduction
9.6PCA Practical
9.7tSNE and UMAP
1
9.8Anomaly Detection
9.9Association Rules
1
9.10Topic Modeling
9.11Autoencoders Intro
9.12Clustering Evaluation
9.13Visualization Techniques
1
9.14Density Estimation
9.15Self Supervised Basics
10. Optimization and Regularization1 views
Master optimization techniques and regularization strategies to train stable, generalizable models.
15 topics (15 versions)
10.1Loss Functions
10.2Gradient Descent
10.3Stochastic Gradient
10.4Momentum and Nesterov
10.5Adagrad and RMSProp
10.6Adam and Variants
10.7Learning Rate Schedules
1
10.8Early Stopping
10.9L1 and L2
10.10Dropout Concepts
10.11Batch Normalization
10.12Weight Decay
10.13Initialization Schemes
10.14Vanishing Gradients
10.15Hyperparameter Search
11. Neural Networks with PyTorch2 views
Build, train, and debug neural networks in PyTorch using modern training utilities.
15 topics (15 versions)
11.1Tensors and Autograd
11.2Computational Graphs
11.3Building Modules
11.4Forward and Backward
11.5Activation Functions
11.6Initialization in PyTorch
11.7Optimizers in PyTorch
11.8Dataloaders and Datasets
11.9Training Loops
11.10GPU Acceleration
11.11Saving and Loading
11.12Debugging Tips
11.13Mixed Precision
11.14Regularization in NN
1
11.15Reproducibility in PyTorch
1
12. Deep Learning Architectures5 views
Dive into common deep learning architectures and design patterns for complex tasks.
15 topics (15 versions)
12.1Multilayer Perceptrons
1
12.2Convolutional Networks
1
12.3Recurrent Networks
12.4LSTM and GRU
12.5Attention Mechanisms
12.6Transformers Overview
12.7Encoder Decoder Models
12.8Residual Connections
1
12.9Normalization Layers
1
12.10Positional Encoding
12.11Sequence to Sequence
12.12Graph Neural Networks
12.13Autoencoders Deep
12.14Generative Models
12.15Transfer Learning
1
13. Computer Vision Basics6 views
Apply deep learning to images, detection, and segmentation with practical computer vision workflows.
15 topics (15 versions)
13.1Image Formats
1
13.2Color Spaces
13.3Convolutions and Kernels
13.4Edge Detection
13.5Data Augmentation CV
1
13.6CNN Architectures
1
13.7Object Detection Intro
1
13.8Semantic Segmentation
1
13.9Transfer Learning CV
13.10Pretrained Models
13.11Bounding Boxes
13.12Metrics for Vision
1
13.13OpenCV Essentials
13.14Visualization GradCAM
13.15Deployment for Vision
14. Model Deployment and MLOps4 views
Ship models to production with APIs, containers, tracking, monitoring, and responsible AI practices.
15 topics (15 versions)
14.1Model Packaging
1
14.2REST APIs with FastAPI
14.3Batch Inference
14.4Streaming Inference
14.5Docker Containers
14.6CI CD Pipelines
14.7Experiment Tracking
14.8Model Registry
14.9Data Versioning
14.10Monitoring and Drift
1
14.11A/B Testing
1
14.12Security Fundamentals
14.13Fairness and Bias Audits
1
14.14Privacy and Compliance
14.15Documentation and Handover