# ms-mirza/road-to-machine-learning architecture

> Architecture diagram of the GitHub repository ms-mirza/road-to-machine-learning, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-06-27). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/ms-mirza/road-to-machine-learning
- Repository: https://github.com/ms-mirza/road-to-machine-learning

## Overview

1. This repository is a static, documentation-heavy learning platform rather than an executable application. Its primary “runtime” is GitHub/Markdown rendering, with content organized as a large curriculum for machine learning, data science, MLOps, and adjacent engineering topics.

2. The core architecture is the numbered module track `00-prerequisites` through `25-generative-ai-llms`. These folders form the main learning spine: foundations first, then data science tooling, classic ML, deep learning, specialized domains, production/MLOps, and advanced electives. The numbering is important because the repo uses it as the canonical dependency order.

3. The content is split into repeating substructures within most modules: a main lesson guide, advanced-topics notes, quick references, project tutorials, and a module README. That pattern is a key architectural boundary: each module is self-contained for learning, but the README pages connect it back to the overall roadmap.

4. The repo has a second major track for hands-on projects: `16-projects-beginner`, `17-projects-intermediate`, and `18-projects-advanced`. These act as practical application layers over the theory modules, with increasing complexity from simple tabular ML to CV, NLP, RAG, deployment, and end-to-end pipelines. The project folders are the main “practice” boundary in the architecture.

5. A third major subsystem is the `system-design` track. It is intentionally separate from the ML modules and covers infrastructure concepts such as networking, caching, SQL/NoSQL, replication, sharding, message queues, and ML-specific system design. This track supports roles like ML Engineer, MLOps Engineer, Data Engineer, and Full-Stack AI Engineer.

6. The `resources` directory is the support and reference layer. It contains cheatsheets, guides, career roadmaps, interview prep, tooling references, and domain-specific deep dives such as RAG, LangChain, MLflow, Docker, ethics, data validation, and model testing. These files are not part of the sequential learning path, but they feed into many modules as cross-cutting reference material.

7. There is a distinct “full-stack AI” subsystem spanning `resources/full_stack_track`, `resources/full_stack_ai_engineer_roadmap.md`, and `examples/full_stack_track`. This is the only part that explicitly bridges ML learning with product engineering topics like TypeScript, APIs, databases, Next.js, containers, and AI integration. It functions as a companion track rather than a replacement for the core ML curriculum.

8. The repository also includes lightweight executable artifacts, but they are limited and instructional. `01-python-for-data-science/example_basics.py` and some project folders contain runnable Python examples, while most other material is markdown-first. The repo is therefore documentation-led with selective code samples, not a library or application codebase.

9. Supporting automation is minimal but important: `.github/workflows/python-check.yml` provides CI validation, and `tools/check_links.py` plus `tools/check_md_links.py` indicate that link integrity and markdown quality are maintained as part of repository hygiene. This suggests the main technical risk is content drift, broken references, and documentation consistency rather than runtime failures.

10. The external dependency surface is intentionally small. `requirements.txt` defines the Python packages used for examples and checks, but the architecture depends more on external services and learning tools than on in-repo infrastructure. The README and resources reference GitHub, YouTube, Kaggle, cloud platforms, ML frameworks, and deployment targets, but the repo itself remains a curated static knowledge base.

11. From a diagram perspective, the main flow is: roadmap/README → module lessons → exercises/projects → cross-cutting resources → career/application tracks. A second flow exists for operational learning: theory modules → deployment/MLOps/system design → advanced projects/capstones. That separation is the most important architectural boundary in the repo.

12. In short, this is a layered educational monorepo: foundations at the base, progressively specialized modules in the middle, project and career tracks on top, and small automation/tooling around the edges to keep the content navigable and valid.

Main entry points: [`resources`](https://github.com/ms-mirza/road-to-machine-learning/tree/main/resources) (Resources), [`README.md`](https://github.com/ms-mirza/road-to-machine-learning/blob/main/README.md) (Repo README), [`LEARNING_ROADMAP.md`](https://github.com/ms-mirza/road-to-machine-learning/blob/main/LEARNING_ROADMAP.md) (Roadmap), [`03-supervised-learning-regression`](https://github.com/ms-mirza/road-to-machine-learning/tree/main/03-supervised-learning-regression) (Supervised ML)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_grp_core["Learning spine"]
  node_learning_roadmap["Roadmap<br/>curriculum map"]
  node_getting_started["Getting Started<br/>onboarding<br/>[GETTING_STARTED.md]"]
  node_prereqs["Prerequisites<br/>foundations module"]
  node_python_ds["Python DS<br/>data science module"]
  node_intro_ml["Intro ML<br/>ml module"]
  node_supervised_ml["Supervised ML<br/>core ml module"]
  node_model_eval["Evaluation<br/>core ml module"]
  node_deep_learning["Deep Learning"]
  node_deployment_mlops["Deploy & MLOps<br/>ops module"]
  node_mlops_basics["MLOps Basics<br/>ops module"]
  node_electives_adv["Advanced Electives<br/>special topics"]
end

subgraph group_grp_projects["Projects"]
  node_beginner_projects["Beginner Projects<br/>practice track"]
  node_intermediate_projects["Intermediate Projects<br/>practice track"]
  node_advanced_projects["Advanced Projects<br/>capstone track"]
  node_capstones["Capstones<br/>capstone set"]
end

subgraph group_grp_system["System design"]
  node_system_design["System Design<br/>infra curriculum"]
end

subgraph group_grp_resources["Resources"]
  node_resources_hub["Resources<br/>reference library"]
end

subgraph group_grp_fullstack["Full-stack AI"]
  node_fullstack_roadmap["Full-Stack Roadmap<br/>companion track"]
  node_fullstack_track["Full-Stack Track<br/>roadmap track"]
  node_fullstack_examples["Full-Stack Examples"]
end

subgraph group_grp_automation["Automation"]
  node_ci_check["CI Check<br/>workflow<br/>[python-check.yml]"]
  node_link_tools["Link Tools<br/>validation tools<br/>[check_links.py]"]
end

node_repo_readme["Repo README<br/>entry doc<br/>[README.md]"]

node_repo_readme -->|"introduces"| node_learning_roadmap
node_repo_readme -->|"onboards"| node_getting_started
node_learning_roadmap -->|"starts with"| node_prereqs
node_prereqs -->|"enables"| node_python_ds
node_python_ds -->|"feeds into"| node_intro_ml
node_intro_ml -->|"progresses to"| node_supervised_ml
node_supervised_ml -->|"refines"| node_model_eval
node_model_eval -->|"advances to"| node_deep_learning
node_deep_learning -->|"operationalizes"| node_deployment_mlops
node_deployment_mlops -->|"broadens to"| node_mlops_basics
node_mlops_basics -->|"extends to"| node_electives_adv
node_supervised_ml -->|"applies in"| node_beginner_projects
node_model_eval -->|"strengthens"| node_intermediate_projects
node_deep_learning -->|"powers"| node_advanced_projects
node_deployment_mlops -->|"culminates in"| node_capstones
node_learning_roadmap -->|"references"| node_resources_hub
node_resources_hub -->|"specializes into"| node_fullstack_roadmap
node_fullstack_roadmap -->|"structures"| node_fullstack_track
node_fullstack_track -->|"demonstrates"| node_fullstack_examples
node_resources_hub -->|"supports"| node_system_design
node_repo_readme -->|"maintained by"| node_ci_check
node_ci_check -->|"uses"| node_link_tools
node_resources_hub -.->|"informs"| node_beginner_projects
node_system_design -.->|"supports"| node_advanced_projects
node_electives_adv -.->|"feeds"| node_advanced_projects

click node_repo_readme "https://github.com/ms-mirza/road-to-machine-learning/blob/main/README.md"
click node_learning_roadmap "https://github.com/ms-mirza/road-to-machine-learning/blob/main/LEARNING_ROADMAP.md"
click node_getting_started "https://github.com/ms-mirza/road-to-machine-learning/blob/main/GETTING_STARTED.md"
click node_prereqs "https://github.com/ms-mirza/road-to-machine-learning/tree/main/00-prerequisites"
click node_python_ds "https://github.com/ms-mirza/road-to-machine-learning/tree/main/01-python-for-data-science"
click node_intro_ml "https://github.com/ms-mirza/road-to-machine-learning/tree/main/02-introduction-to-ml"
click node_supervised_ml "https://github.com/ms-mirza/road-to-machine-learning/tree/main/03-supervised-learning-regression"
click node_model_eval "https://github.com/ms-mirza/road-to-machine-learning/tree/main/05-model-evaluation-optimization"
click node_deep_learning "https://github.com/ms-mirza/road-to-machine-learning/tree/main/09-neural-networks-basics"
click node_deployment_mlops "https://github.com/ms-mirza/road-to-machine-learning/tree/main/13-model-deployment"
click node_mlops_basics "https://github.com/ms-mirza/road-to-machine-learning/tree/main/14-mlops-basics"
click node_electives_adv "https://github.com/ms-mirza/road-to-machine-learning/tree/main/25-generative-ai-llms"
click node_beginner_projects "https://github.com/ms-mirza/road-to-machine-learning/tree/main/16-projects-beginner"
click node_intermediate_projects "https://github.com/ms-mirza/road-to-machine-learning/tree/main/17-projects-intermediate"
click node_advanced_projects "https://github.com/ms-mirza/road-to-machine-learning/tree/main/18-projects-advanced"
click node_capstones "https://github.com/ms-mirza/road-to-machine-learning/tree/main/18-projects-advanced/capstones"
click node_system_design "https://github.com/ms-mirza/road-to-machine-learning/tree/main/system-design"
click node_resources_hub "https://github.com/ms-mirza/road-to-machine-learning/tree/main/resources"
click node_fullstack_roadmap "https://github.com/ms-mirza/road-to-machine-learning/blob/main/resources/full_stack_ai_engineer_roadmap.md"
click node_fullstack_track "https://github.com/ms-mirza/road-to-machine-learning/tree/main/resources/full_stack_track"
click node_fullstack_examples "https://github.com/ms-mirza/road-to-machine-learning/tree/main/examples/full_stack_track"
click node_ci_check "https://github.com/ms-mirza/road-to-machine-learning/blob/main/.github/workflows/python-check.yml"
click node_link_tools "https://github.com/ms-mirza/road-to-machine-learning/blob/main/tools/check_links.py"

classDef toneNeutral fill:#f8fafc,stroke:#334155,stroke-width:1.5px,color:#0f172a
classDef toneBlue fill:#dbeafe,stroke:#2563eb,stroke-width:1.5px,color:#172554
classDef toneAmber fill:#fef3c7,stroke:#d97706,stroke-width:1.5px,color:#78350f
classDef toneMint fill:#dcfce7,stroke:#16a34a,stroke-width:1.5px,color:#14532d
classDef toneRose fill:#ffe4e6,stroke:#e11d48,stroke-width:1.5px,color:#881337
classDef toneIndigo fill:#e0e7ff,stroke:#4f46e5,stroke-width:1.5px,color:#312e81
classDef toneTeal fill:#ccfbf1,stroke:#0f766e,stroke-width:1.5px,color:#134e4a
class node_learning_roadmap,node_getting_started,node_prereqs,node_python_ds,node_intro_ml,node_supervised_ml,node_model_eval,node_deep_learning,node_deployment_mlops,node_mlops_basics,node_electives_adv toneBlue
class node_beginner_projects,node_intermediate_projects,node_advanced_projects,node_capstones toneAmber
class node_system_design toneMint
class node_resources_hub toneRose
class node_fullstack_roadmap,node_fullstack_track,node_fullstack_examples toneIndigo
class node_ci_check,node_link_tools toneTeal
class node_repo_readme toneNeutral
```

## Components

### Learning spine

Numbered curriculum from prerequisites through advanced ML and GenAI.

- [Roadmap](https://github.com/ms-mirza/road-to-machine-learning/blob/main/LEARNING_ROADMAP.md): curriculum map · Canonical learning sequence and dependency order for the numbered modules. · `LEARNING_ROADMAP.md`
- [Getting Started](https://github.com/ms-mirza/road-to-machine-learning/blob/main/GETTING_STARTED.md): onboarding · Quick setup and navigation entry point. · `GETTING_STARTED.md`
- [Prerequisites](https://github.com/ms-mirza/road-to-machine-learning/tree/main/00-prerequisites): foundations module · Math, Python, and environment fundamentals. · `00-prerequisites`
- [Python DS](https://github.com/ms-mirza/road-to-machine-learning/tree/main/01-python-for-data-science): data science module · Python, NumPy, pandas, visualization, EDA, and basic web/data tooling. · `01-python-for-data-science`
- [Intro ML](https://github.com/ms-mirza/road-to-machine-learning/tree/main/02-introduction-to-ml): ml module · Problem framing, terminology, and first-model concepts. · `02-introduction-to-ml`
- [Supervised ML](https://github.com/ms-mirza/road-to-machine-learning/tree/main/03-supervised-learning-regression): core ml module · Regression and classification as the main supervised-learning branch. · `03-supervised-learning-regression`
- [Evaluation](https://github.com/ms-mirza/road-to-machine-learning/tree/main/05-model-evaluation-optimization): core ml module · Metrics, validation, and optimization practices. · `05-model-evaluation-optimization`
- [Deep Learning](https://github.com/ms-mirza/road-to-machine-learning/tree/main/09-neural-networks-basics): deep learning module · Neural networks and framework-based training workflows. · `09-neural-networks-basics`
- [Deploy & MLOps](https://github.com/ms-mirza/road-to-machine-learning/tree/main/13-model-deployment): ops module · Model deployment and operational ML practices. · `13-model-deployment`
- [MLOps Basics](https://github.com/ms-mirza/road-to-machine-learning/tree/main/14-mlops-basics): ops module · Operational lifecycle, monitoring, and delivery concepts. · `14-mlops-basics`
- [Advanced Electives](https://github.com/ms-mirza/road-to-machine-learning/tree/main/25-generative-ai-llms): special topics · Later-stage topics such as explainability, RL, GNNs, audio, and GenAI. · `25-generative-ai-llms`

### Projects

Practice tracks and capstones that apply the curriculum.

- [Beginner Projects](https://github.com/ms-mirza/road-to-machine-learning/tree/main/16-projects-beginner): practice track · Entry projects for tabular ML and simple dashboards. · `16-projects-beginner`
- [Intermediate Projects](https://github.com/ms-mirza/road-to-machine-learning/tree/main/17-projects-intermediate): practice track · Harder projects spanning classification, recommendation, fraud, and time series. · `17-projects-intermediate`
- [Advanced Projects](https://github.com/ms-mirza/road-to-machine-learning/tree/main/18-projects-advanced): capstone track · Advanced applications including CV, chatbots, pipelines, deployment, and capstones. · `18-projects-advanced`
- [Capstones](https://github.com/ms-mirza/road-to-machine-learning/tree/main/18-projects-advanced/capstones): capstone set · End-to-end culminating projects tying multiple skills together. · `18-projects-advanced/capstones`

### System design

Infrastructure and design-learning track separate from the core ML modules.

- [System Design](https://github.com/ms-mirza/road-to-machine-learning/tree/main/system-design): infra curriculum · Architecture and distributed-systems learning track supporting ML engineering roles. · `system-design`

### Resources

Cross-cutting references, cheatsheets, and support material.

- [Resources](https://github.com/ms-mirza/road-to-machine-learning/tree/main/resources): reference library · Cheatsheets, guides, interviews, ethics, tooling, and domain references. · `resources`

### Full-stack AI

Companion track bridging ML learning with product engineering.

- [Full-Stack Roadmap](https://github.com/ms-mirza/road-to-machine-learning/blob/main/resources/full_stack_ai_engineer_roadmap.md): companion track · Bridge from ML learning to product engineering and AI integration. · `resources/full_stack_ai_engineer_roadmap.md`
- [Full-Stack Track](https://github.com/ms-mirza/road-to-machine-learning/tree/main/resources/full_stack_track): roadmap track · Structured phases for TypeScript, APIs, SQL, Next.js, containers, and AI integration. · `resources/full_stack_track`
- [Full-Stack Examples](https://github.com/ms-mirza/road-to-machine-learning/tree/main/examples/full_stack_track): examples · Executable companion examples for the full-stack AI track. · `examples/full_stack_track`

### Automation

Lightweight CI and link-validation tooling for repository hygiene.

- [CI Check](https://github.com/ms-mirza/road-to-machine-learning/blob/main/.github/workflows/python-check.yml): workflow · Repository validation workflow for documentation quality and checks. · `.github/workflows/python-check.yml`
- [Link Tools](https://github.com/ms-mirza/road-to-machine-learning/blob/main/tools/check_links.py): validation tools · Scripts that verify links and markdown integrity. · `tools/check_links.py`

### Other components

- [Repo README](https://github.com/ms-mirza/road-to-machine-learning/blob/main/README.md): entry doc · Top-level orientation for the learning repository. · `README.md`

## Connections

- Repo README → Roadmap: introduces · The top-level README points readers into the canonical curriculum sequence.
- Repo README → Getting Started: onboards · Quick-start guidance helps new readers navigate the repository.
- Roadmap → Prerequisites: starts with · The roadmap establishes the prerequisite foundations as the first step.
- Prerequisites → Python DS: enables · Foundations feed into practical Python and data-science tooling.
- Python DS → Intro ML: feeds into · Data handling and EDA prepare learners for ML concepts.
- Intro ML → Supervised ML: progresses to · Introductory ML concepts lead into supervised learning.
- Supervised ML → Evaluation: refines · Model-building naturally flows into evaluation and optimization.
- Evaluation → Deep Learning: advances to · Core classical ML branches into neural-network methods.
- Deep Learning → Deploy & MLOps: operationalizes · Model training leads into deployment and delivery concerns.
- Deploy & MLOps → MLOps Basics: broadens to · Deployment topics extend into broader MLOps lifecycle management.
- MLOps Basics → Advanced Electives: extends to · Operational foundations lead into advanced and specialized electives.
- Supervised ML → Beginner Projects: applies in · Early projects reuse supervised-learning fundamentals.
- Evaluation → Intermediate Projects: strengthens · Evaluation skills support more challenging applied projects.
- Deep Learning → Advanced Projects: powers · Deep-learning knowledge is used in advanced application projects.
- Deploy & MLOps → Capstones: culminates in · Deployment and MLOps knowledge is expressed in capstone work.
- Roadmap → Resources: references · Cross-cutting reference material supports many modules.
- Resources → Full-Stack Roadmap: specializes into · The resources layer contains a dedicated full-stack AI companion path.
- Full-Stack Roadmap → Full-Stack Track: structures · The roadmap is implemented as a phased companion track.
- Full-Stack Track → Full-Stack Examples: demonstrates · Example artifacts support the full-stack AI learning path.
- Resources → System Design: supports · Reference material feeds the separate system-design curriculum.
- Repo README → CI Check: maintained by · Repository hygiene is guarded by CI validation.
- CI Check → Link Tools: uses · The workflow relies on link and markdown checking scripts.
- Resources → Beginner Projects: informs · References and cheatsheets support project execution.
- System Design → Advanced Projects: supports · System design concepts inform advanced end-to-end projects.
- Advanced Electives → Advanced Projects: feeds · Advanced topics are applied in the most sophisticated projects.