Machine Learning Roadmap
Phase 1:Prerequisites
beginner6 weeksPython
Strong Python fundamentals including OOP, list comprehensions, and the scientific stack.
intermediate4 weeksLinear Algebra
Vectors, matrices, matrix multiplication, eigenvalues. These are the math behind neural networks.
intermediate3 weeksCalculus
Derivatives, chain rule, and gradients, the math behind backpropagation.
intermediate4 weeksStatistics & Probability
Probability distributions, Bayes' theorem, maximum likelihood estimation.
Phase 2:Classical Machine Learning
intermediate4 weeksSupervised Learning
Linear regression, logistic regression, decision trees, random forests, and SVMs.
intermediate3 weeksUnsupervised Learning
K-means clustering, PCA, dimensionality reduction, and anomaly detection.
intermediate2 weeksModel Evaluation
Train/validation/test splits, cross-validation, and performance metrics.
intermediate2 weeksFeature Engineering
Encoding, scaling, imputation, and creating informative features from raw data.
Phase 3:Deep Learning
advanced4 weeksNeural Networks
Perceptrons, activation functions, backpropagation, and gradient descent.
advanced3 weeksCNNs
Convolutional networks for image recognition and computer vision.
advanced4 weeksRNNs & Transformers
Sequence models, attention mechanisms, and the architecture behind GPT and BERT.
advanced4 weeksTensorFlow or PyTorch
Build and train neural networks using a major deep learning framework.
Phase 4:Applied ML
advanced4 weeksMLOps
Experiment tracking, model versioning, deployment pipelines, and monitoring.
advanced4 weeksLLMs & Fine-tuning
Work with large language models, prompt engineering, and fine-tuning techniques.
advanced6 weeksCapstone Project
Build an end-to-end ML system from data collection to deployed API.
Next steps
Keep exploring
Languages in this roadmap
Other goals