AMMAN HUSSAIN ANSARI ammmanism

🧭 Core Philosophy

Mathematics → Algorithms → Models → Systems → Infrastructure

graph TB
    A[📐 Mathematics<br/>Calculus • Probability • Stats • Linear Algebra] -->|Theory| B[⚙️ Algorithms<br/>ML from Scratch • Optimization]
    B -->|Implementation| C[🧠 Models<br/>DL • Transformers • LLMs]
    C -->|Integration| D[🏗️ Systems<br/>RAG • GenAI • Pipelines]
    D -->|Deployment| E[⚡ Infrastructure<br/>Docker • K8s • AWS • MLOps]
    
    style A fill:#00D9FF,stroke:#fff,stroke-width:3px,color:#000
    style B fill:#FF6B6B,stroke:#fff,stroke-width:3px,color:#fff
    style C fill:#4ECDC4,stroke:#fff,stroke-width:3px,color:#000
    style D fill:#FFD166,stroke:#fff,stroke-width:3px,color:#000
    style E fill:#06D6A0,stroke:#fff,stroke-width:3px,color:#000

💡 "If I can't derive it, code it, and deploy it — I don't consider it learned."

I build AI systems from scratch — starting from mathematical proofs, implementing core algorithms in NumPy, scaling to PyTorch, and deploying on production infrastructure.

This GitHub is my public research laboratory and engineering notebook.

🎯 What I'm Building Toward

Deep Understanding
_{Math → Code}

Mathematical Rigor
_{Proofs & Derivations}

Systems Thinking
_{Production-Ready}

Research Depth
_PhD-Level

Production Scale
_{Docker • K8s • AWS}

🌍 Open to Remote Opportunities Globally

📊 Live Skill Matrix (Current as of Feb 2026)

📐 Mathematics Foundation

Skill	Progress	Topics Covered
Calculus & Optimization		Gradients • Chain Rule • Lagrange Multipliers
Probability Theory		Bayesian Inference • Distributions • Sampling
Statistics		Hypothesis Testing • Estimation • Confidence Intervals
Linear Algebra		Vector Spaces • Eigenvalues • SVD

🤖 Machine Learning

Skill	Progress	Topics Covered
Supervised Learning		Linear/Logistic Regression • Trees • Ensembles
Unsupervised Learning		K-Means • PCA • Clustering
ML Theory		Bias-Variance • Regularization • PAC Learning
Feature Engineering		Encoding • Scaling • Selection • Creation

🧬 Deep Learning

Skill	Progress	Topics Covered
Backpropagation		Chain Rule • Computational Graphs • Gradients
Neural Architectures		MLP • CNN • RNN • ResNet
Optimization		SGD • Momentum • Adam • RMSProp
Regularization		Dropout • BatchNorm • L1/L2

🧠 Transformers & LLMs

Skill	Progress	Topics Covered
Attention Mechanisms		Self-Attention • Multi-Head • Cross-Attention
Transformer Architecture		Encoder-Decoder • Positional Encoding
LLM Training		Pretraining • Fine-tuning • RLHF
PEFT Methods		LoRA • QLoRA • Adapters

🔍 RAG & GenAI

Skill	Progress	Topics Covered
Document Processing		Chunking • Parsing • OCR
Retrieval Systems		Dense • Sparse • Hybrid
Vector Databases		Pinecone • Weaviate • FAISS
RAG Evaluation		RAGAS • Faithfulness • Relevancy

🏗️ MLOps & Infrastructure

Skill	Progress	Topics Covered
Containerization		Docker • Docker Compose
Orchestration		Kubernetes • Helm
CI/CD		GitHub Actions • Testing
Cloud (AWS)		EC2 • S3 • Lambda • SageMaker

🔢 Reinforcement Learning

Skill	Progress	Topics Covered
Value-Based Methods		Q-Learning • DQN
Policy Gradient		REINFORCE • PPO • A3C

💻 Data Structures & Algorithms

Skill	Progress	Topics Covered
Core DSA		Arrays • Trees • Graphs • DP

🛠️ Tech Arsenal

💻 Languages & Core Libraries

🧠 ML/DL Frameworks

🤖 GenAI & LLM Stack

🔍 Vector Databases

⚙️ Backend & APIs

☁️ Cloud & DevOps

🗄️ Databases

🔧 Tools

📚 Learning Journey & Completed Courses

✅ COMPLETED COURSES (2025)

Course	Platform/Instructor	Duration	Completion Date	Key Takeaways
🎥 Essence of Calculus	3Blue1Brown (YouTube)	12 videos (~3 hrs)	✅ Nov 2025	Visual intuition for gradients, optimization, chain rule
🎥 Essence of Probability	3Blue1Brown (YouTube)	10 videos (~3 hrs)	✅ Dec 2025	Bayesian thinking, distributions, conditional probability
🎥 Essence of Linear Algebra	3Blue1Brown (YouTube)	16 videos (~4 hrs)	✅ Dec 2025	Geometric intuition, transformations, eigenvectors
📚 CS50's Introduction to AI	Harvard (edX)	7 weeks	✅ Oct 2025	Search, optimization, ML basics, neural networks
🎥 Machine Learning Fundamentals	StatQuest (YouTube)	50+ videos	✅ Nov 2025	ML algorithms explained with clarity and humor

📖 IN PROGRESS (Jan - Apr 2026)

Course	Platform/Instructor	Duration	Progress	Focus	Target Completion
🎥 Data-Driven Science & Engineering	Steve Brunton (YouTube)	35 videos (~8 hrs)	![60%](https://geps.dev/progress/60)	Applied statistics, hypothesis testing	Mar 2026
🎥 Machine Learning Course	Sebastian Raschka (YouTube)	95 videos (~40 hrs)	![45%](https://geps.dev/progress/45)	Deep ML theory + hands-on practice	Apr 2026
🎥 GenAI Intensive Bootcamp	Andrew Brown	66+ hours	![20%](https://geps.dev/progress/20)	Production GenAI systems, RAG pipelines	Apr 2026
📚 Deep Learning Book	Goodfellow, Bengio, Courville	Self-paced	![15%](https://geps.dev/progress/15)	Comprehensive DL theory	Apr 2026
📚 Pattern Recognition & ML	Christopher Bishop	Self-paced	![10%](https://geps.dev/progress/10)	Mathematical ML foundations	Apr 2026
🎥 Fast.ai Practical Deep Learning	Jeremy Howard	~40 hours	![25%](https://geps.dev/progress/25)	Practical DL for coders	Apr 2026
🎥 NLP Specialization	Hugging Face	Self-paced	![30%](https://geps.dev/progress/30)	Transformers, tokenization, fine-tuning	Apr 2026
📚 Reinforcement Learning	Sutton & Barto	Self-paced	![20%](https://geps.dev/progress/20)	RL theory and algorithms	Apr 2026

📅 PLANNED FOR 2026

🎓 Stanford CS229 - Machine Learning (Andrew Ng)
🎓 MIT 6.S191 - Introduction to Deep Learning
🎓 Berkeley CS285 - Deep Reinforcement Learning
🎓 Stanford CS224N - NLP with Deep Learning
🎓 AWS Machine Learning Specialty - Certification
📚 Designing Data-Intensive Applications - Martin Kleppmann
📚 Hands-On Machine Learning - Aurélien Géron (3rd Edition)

🚀 Repository Ecosystem

✅ COMPLETED PROJECTS

🎯 ml-from-scratch ✅

Foundation Complete: ML Algorithms from Mathematical First Principles

# Linear Regression
∂L/∂w = (1/n)X^T(Xw - y)
w := w - α·∂L/∂w

# Logistic Regression  
σ(z) = 1/(1 + e^(-z))
∂L/∂w = (1/n)X^T(σ(Xw) - y)

Fully Implemented:

✅ Linear Regression (OLS, Gradient Descent, Ridge, Lasso)
✅ Logistic Regression (Binary, Multiclass, Regularized)
✅ K-Nearest Neighbors (Classification, Regression, Distance Metrics)
✅ K-Means Clustering (with elbow method, silhouette analysis)
✅ Naive Bayes (Gaussian, Multinomial, Bernoulli)
✅ Decision Trees (CART algorithm, pruning)
✅ Random Forests (Bagging, feature importance)
✅ Support Vector Machines (Linear, Kernel methods)
✅ Principal Component Analysis (PCA)
✅ Gradient Boosting basics

Key Features:

📐 Math-first approach (derivations → code)
🧪 100% unit tested against sklearn
📊 Visual comparisons & insights
📝 Comprehensive documentation with theory
🎯 Performance benchmarking

Completed: January 2026

📖 View Repository →

🚧 ACTIVE DEVELOPMENT

📊 probability-statistics-simulations

Statistical Intuition Through Code

Implemented:

✅ Monte Carlo simulations
✅ Common distributions (Normal, Binomial, Poisson)
🚧 Bayesian inference from scratch

In Progress:

🚧 Hypothesis testing (t-test, ANOVA, chi-square)
🚧 Resampling methods (Bootstrap, Permutation)

Planned:

📅 Central Limit Theorem demonstrations
📅 Markov Chain Monte Carlo (MCMC)

Expected Completion: March 2026

🧬 deep-learning-from-scratch

Neural Networks: Theory → Code

Implemented:

✅ Backpropagation mathematics
✅ Dense layers
✅ Activation functions (ReLU, Sigmoid, Tanh, Softmax)
🚧 Convolutional layers

In Progress:

🚧 BatchNorm implementation
🚧 Dropout regularization
🚧 Advanced optimizers (Adam, RMSProp)

Expected Completion: April 2026

📅 PLANNED FOR 2026

🧠 transformers-from-scratch

Attention → GPT/BERT

Roadmap:

Scaled dot-product attention
Multi-head attention
Positional encoding
Encoder/Decoder blocks
GPT-style generation
BERT-style pretraining

Attention(Q,K,V) = 
  softmax(QK^T/√d_k)V

Timeline: May - July 2026

🔍 rag-from-scratch

Production RAG Pipeline

Components:

Document processing
Chunking strategies
Embedding models
Vector search (FAISS, Pinecone)
Retrieval methods
Generation + RAGAS evaluation

Timeline: July - September 2026

⚙️ mlops-pipeline

End-to-End ML System

Pipeline:

Data ingestion
Feature engineering
Model training
Deployment (FastAPI)
Monitoring
CI/CD

Timeline: September - November 2026

🎮 reinforcement-learning-lab

RL Algorithms from Scratch

Algorithms:

Q-Learning
Deep Q-Networks (DQN)
Policy Gradient
PPO
Actor-Critic

Timeline: October - December 2026

💻 leetcode-solutions

DSA for AI Engineers

Progress:

Arrays & Strings: 45/100
Trees & Graphs: 30/80
Dynamic Programming: 15/60
Total: 120/300

Goal: 300+ problems by Dec 2026

🌐 portfolio-website

Professional Portfolio

Features:

Project showcase
Blog integration
Interactive demos
Resume & contact

Stack: Next.js, Tailwind, MDX

🏗️ Project Architecture Philosophy

┌─────────────────────────────────────────────────────────┐
│                  REPO STRUCTURE TEMPLATE                 │
├─────────────────────────────────────────────────────────┤
│  repo-name/                                             │
│  ├── 📄 README.md          ← Problem • Math • Solution │
│  ├── 📦 pyproject.toml     ← Dependencies               │
│  ├── 🔧 Makefile           ← Commands                   │
│  ├── 🐳 Dockerfile         ← Containerization           │
│  │                                                       │
│  ├── 📁 src/               ← Production code            │
│  │   ├── __init__.py                                    │
│  │   ├── models/          ← Algorithms                  │
│  │   ├── utils/           ← Helpers                     │
│  │   └── viz/             ← Visualizations              │
│  │                                                       │
│  ├── 📓 notebooks/         ← Experiments & intuition    │
│  │   ├── 01_theory.ipynb                                │
│  │   ├── 02_implementation.ipynb                        │
│  │   └── 03_comparison.ipynb                            │
│  │                                                       │
│  ├── 🧪 tests/             ← Unit tests                 │
│  │   ├── test_models.py                                 │
│  │   └── test_utils.py                                  │
│  │                                                       │
│  ├── 📚 docs/              ← Theory & math              │
│  │   ├── theory.md        ← Mathematical foundations    │
│  │   ├── derivations.md   ← Step-by-step proofs         │
│  │   └── api.md           ← Code documentation          │
│  │                                                       │
│  ├── 🚀 examples/          ← Real-world usage           │
│  │   ├── basic_example.py                               │
│  │   └── advanced_demo.py                               │
│  │                                                       │
│  └── 📊 data/              ← Sample datasets            │
│      ├── raw/                                            │
│      └── processed/                                      │
└─────────────────────────────────────────────────────────┘

Every README Answers:

❓ What problem? — Real-world motivation
📐 What math? — Mathematical foundation
⚙️ What algorithm? — Step-by-step explanation
💡 Why it works? — Intuition & proofs
🚀 How it scales? — Complexity & optimization

📊 GitHub Analytics Dashboard

📈 Overall Stats

🔥 Streak Stats

📊 Activity Graph

💻 Language Distribution

🏆 Trophies

📅 2026 Roadmap & Timeline

gantt
    title Amman's AI Engineering Journey (2026)
    dateFormat YYYY-MM-DD
    
    section ✅ Completed (2025)
    ML from Scratch            :done, comp1, 2025-11-01, 2026-01-31
    Math Foundation (3B1B)     :done, comp2, 2025-10-01, 2025-12-31
    CS50 AI                    :done, comp3, 2025-10-01, 2025-11-30
    
    section 🔥 Active (Jan-Apr 2026)
    Prob/Stats Simulations     :active, act1, 2026-02-01, 60d
    DL from Scratch            :active, act2, 2026-02-15, 75d
    Steve Brunton Stats        :active, act3, 2026-02-01, 45d
    Sebastian Raschka ML       :active, act4, 2026-01-15, 120d
    
    section 📅 Planned (May-Dec 2026)
    Transformers from Scratch  :plan1, 2026-05-01, 90d
    RAG from Scratch           :plan2, 2026-07-01, 90d
    MLOps Pipeline             :plan3, 2026-09-01, 90d
    RL Lab                     :plan4, 2026-10-01, 90d
    Portfolio Website          :plan5, 2026-06-01, 60d
    
    section 🎯 Continuous
    LeetCode Daily             :daily1, 2026-02-01, 365d
    Andrew Brown GenAI         :daily2, 2026-02-01, 180d
    Blog Posts                 :daily3, 2026-03-01, 300d

🎯 Current Focus & Milestones (February 2026)

Project	Status	Current Sprint	Next Milestone	Completion Target
ml-from-scratch	✅ COMPLETED	—	Archive & document	Completed Jan 2026
prob-stats-simulations	🔥 ACTIVE	Bayesian inference	Complete hypothesis testing	March 2026
deep-learning-scratch	🔥 ACTIVE	Conv2D layers	Complete CNN implementation	April 2026
Steve Brunton Stats	📚 LEARNING	Video 21/35	Finish all videos	March 2026
Sebastian Raschka ML	📚 LEARNING	Video 42/95	Complete course	April 2026
LeetCode Practice	⚡ DAILY	120/300 problems	Reach 200 problems	June 2026
transformers-scratch	📅 PLANNED	Planning phase	Start implementation	May 2026

🏆 2026 Goals & Achievements

✅ Achievements Unlocked (2025)

✅ ML from Scratch — Complete implementation (Jan 2026)
✅ 3Blue1Brown Math Series — All courses completed (Dec 2025)
✅ CS50 AI — Certificate earned (Oct 2025)
✅ 100+ LeetCode Problems — Milestone reached (Jan 2026)

🎯 2026 Target Milestones (Max Completion: April 2026)

Milestone	Target Date	Progress
📐 Complete Math & Stats Foundation	Q1 2026
🧬 Deep Learning from Scratch	Q2 2026
🧠 Transformers Implementation	Q3 2026
🔍 Production RAG System	Q3 2026
⚙️ MLOps Pipeline	Q4 2026
🏅 First Kaggle Medal	Q2 2026
💻 LeetCode 300+ Problems	Q4 2026
💼 Portfolio Website Live	Q2 2026
📝 Publish 10 Technical Blogs	Q4 2026

📝 Blog & Technical Writing (Planned)

"The best way to learn is to teach. Writing forces clarity."

🎯 Planned Blog Series

Title	Focus	Target Date	Status
Why Build ML from Scratch?	Philosophy & Learning	March 2026	✍️ Drafting
Mathematical Intuition: Backpropagation	Deep Learning	April 2026	📚 Researching
Implementing Attention from NumPy	Transformers	June 2026	🎯 Planned
Building Production RAG Systems	GenAI	August 2026	🔮 Future
MLOps for Solo Developers	Infrastructure	October 2026	🔮 Future
RL Fundamentals with Code	Reinforcement Learning	November 2026	🔮 Future

🤝 Collaboration & Open Source

💼 Open to Remote Opportunities

I am actively seeking remote AI/ML engineering roles with:

🌍 Location: Remote-first (Global)
💼 Role Type: Full-time, Contract, Freelance
🎯 Focus Areas: ML/DL, NLP, LLMs, RAG Systems, MLOps
📍 Current Location: Gorakhpur, India
🕐 Availability: Immediate (February 2026)

I'm Open To:

Research Projects
_{ML/DL collaborations}

Open Source
_{Contributing to AI libraries}

Technical Writing
_{Educational content}

Real Projects
_{Production AI systems}

Looking For:

🎓 Mentorship from experienced ML researchers/engineers
👥 Study groups for advanced ML topics
🔬 Research collaborations on interesting problems
💼 Remote AI/ML engineering roles (Full-time or Contract)
📚 Paper reading groups & discussion forums
🤝 Open source contributions to major AI/ML projects

📬 Connect With Me

LinkedIn
_{Professional Network}

Twitter
_{Learning in Public}

GitHub
_{Code & Projects}

Email
_{Direct Contact}

💭 My Philosophy

╔════════════════════════════════════════════════════════════════╗
║                                                                ║
║  "I don't just train models — I understand why they work.     ║
║   I don't just use tools — I build them from scratch.         ║
║   I don't just follow tutorials — I derive the theory.        ║
║   I don't just deploy code — I understand the infrastructure. ║
║                                                                ║
║   Building slowly, deeply, and correctly.                     ║
║   Because foundations matter."                                ║
║                                                                ║
╚════════════════════════════════════════════════════════════════╝

🌟 If you find my work interesting, consider:

⭐ Starring my repositories
👀 Following my journey
🤝 Collaborating on projects
💬 Sharing feedback & suggestions
💼 Reaching out for opportunities

_{Last Updated: February 3, 2026 | Built with passion for AI research & engineering | Open to Remote Work 🌍}

AMMAN HUSSAIN ANSARI ammmanism

Achievements

Achievements

🧭 Core Philosophy

💡 "If I can't derive it, code it, and deploy it — I don't consider it learned."

🎯 What I'm Building Toward

🌍 Open to Remote Opportunities Globally

📊 Live Skill Matrix (Current as of Feb 2026)

📐 Mathematics Foundation

🤖 Machine Learning

🧬 Deep Learning

🧠 Transformers & LLMs

🔍 RAG & GenAI

🏗️ MLOps & Infrastructure

🔢 Reinforcement Learning

💻 Data Structures & Algorithms

🛠️ Tech Arsenal

💻 Languages & Core Libraries

🧠 ML/DL Frameworks

🤖 GenAI & LLM Stack

🔍 Vector Databases

⚙️ Backend & APIs

☁️ Cloud & DevOps

🗄️ Databases

🔧 Tools

📚 Learning Journey & Completed Courses

✅ COMPLETED COURSES (2025)

📖 IN PROGRESS (Jan - Apr 2026)

📅 PLANNED FOR 2026

🚀 Repository Ecosystem

✅ COMPLETED PROJECTS

🎯 ml-from-scratch ✅

🚧 ACTIVE DEVELOPMENT

📊 probability-statistics-simulations

🧬 deep-learning-from-scratch

📅 PLANNED FOR 2026

🧠 transformers-from-scratch

🔍 rag-from-scratch

⚙️ mlops-pipeline

🎮 reinforcement-learning-lab

💻 leetcode-solutions

🌐 portfolio-website

🏗️ Project Architecture Philosophy

📊 GitHub Analytics Dashboard

📈 Overall Stats

🔥 Streak Stats

📊 Activity Graph

💻 Language Distribution

🏆 Trophies

📅 2026 Roadmap & Timeline

🎯 Current Focus & Milestones (February 2026)

🏆 2026 Goals & Achievements

✅ Achievements Unlocked (2025)

🎯 2026 Target Milestones (Max Completion: April 2026)

📝 Blog & Technical Writing (Planned)

🎯 Planned Blog Series

🤝 Collaboration & Open Source

💼 Open to Remote Opportunities

I'm Open To:

Looking For:

📬 Connect With Me

💭 My Philosophy

🌟 If you find my work interesting, consider:

Popular repositories Loading

Uh oh!