🤖 Tracking my Machine Learning learning journey — implementations, experiments, and projects using Python, Scikit-Learn, PyTorch & Gymnasium, following a structured roadmap.
Name: Piyush Maji
Interests: Machine Learning · Data Science · Algorithms
Language: Python 🐍
This repository contains my learning materials, implementations, and projects while studying machine learning through a structured roadmap.
| # | Module | Progress | Status |
|---|---|---|---|
| 01 | Supervised Learning with Scikit-Learn | ████████░░ 67% |
🟡 In Progress |
| 02 | Unsupervised Learning in Python | ░░░░░░░░░░ 0% |
⬜ Pending |
| 03 | Deep Learning with PyTorch | ░░░░░░░░░░ 0% |
⬜ Pending |
| 04 | Reinforcement Learning with Gymnasium | ░░░░░░░░░░ 0% |
⬜ Pending |
Overall: ██░░░░░░░░ 17% — 1 of 4 modules in progress
01 — Supervised Learning with Scikit-Learn 🟡 67% Complete
- Classification
- Regression
- Model Evaluation
- Data Preprocessing
- Hyperparameter Tuning
- Pipelines
Build predictive models using real agricultural datasets, evaluate performance, and improve accuracy using tuning techniques.
02 — Unsupervised Learning in Python ⬜ Pending
- Clustering for Dataset Exploration
- Hierarchical Clustering
- t-SNE Visualization
- Dimensionality Reduction
- Discovering Interpretable Features
Apply clustering algorithms to discover patterns in biological datasets and visualize the clusters.
03 — Deep Learning with PyTorch ⬜ Pending
- Introduction to PyTorch
- Neural Network Architecture
- Training Neural Networks
- Hyperparameter Tuning
- Model Evaluation
04 — Reinforcement Learning with Gymnasium ⬜ Pending
- Introduction to Reinforcement Learning
- Model-Based Learning
- Model-Free Learning
- Advanced RL Strategies
Train an RL agent to learn optimal policies and maximize reward through exploration.
ML-Journey/
├── 1_Supervised_Learning/
│ ├── classification/
│ ├── regression/
│ ├── model_evaluation/
│ ├── preprocessing/
│ ├── hyperparameter_tuning/
│ ├── pipelines/
│ └── project_agriculture/
├── 2_Unsupervised_Learning/
│ ├── clustering/
│ ├── hierarchical_clustering/
│ ├── tsne_visualization/
│ ├── dimensionality_reduction/
│ └── project_penguins/
├── 3_Deep_Learning_PyTorch/
│ ├── intro_pytorch/
│ ├── neural_networks/
│ ├── training/
│ └── evaluation/
├── 4_Reinforcement_Learning/
│ ├── intro_rl/
│ ├── model_based/
│ ├── model_free/
│ └── project_taxi/
└── README.md
- Understand machine learning fundamentals
- Implement ML algorithms from scratch
- Learn model evaluation techniques
- Practice hyperparameter tuning
- Build real-world ML projects
- Decision Trees & Random Forest
- Support Vector Machines
- Advanced Neural Networks
- Deep Learning Projects
- End-to-End ML Projects
Structured learning path based on DataCamp ML tracks and industry best practices.
If you find this repository helpful, consider giving it a star ⭐ — it keeps me motivated!