This repository contains a collection of end-to-end Machine Learning, Deep Learning and MLOps projects created for learning, practice and real-world style implementation.
Each project follows a complete pipeline starting from data processing to model training, evaluation and deployment-ready structure.
-
End to End DL Project for ANN classification
End-to-end deep learning pipeline for a classification task using Artificial Neural Networks (ANN). -
End to End DL Project for Simple RNN
End-to-end deep learning project implementing a Recurrent Neural Network for sequence based problems. -
End to End DL Project for LSTM and RNN
Sequence modelling project using LSTM and RNN architectures with a complete training and evaluation pipeline. -
End to End ML Project
Classical machine learning project covering data preprocessing, feature engineering, model building and evaluation. -
End to End MLOps Project
An end-to-end MLOps focused project covering experiment tracking, model versioning and production-ready structure. -
Foundations
Core concepts, practice material and foundational implementations for ML and DL. -
my full dl and ml notes
Personal learning notes and references for deep learning and machine learning.
- Python
- Scikit-learn
- TensorFlow / Keras
- Pandas, NumPy, Matplotlib
- MLflow / MLOps tools (where applicable)
This repository is maintained as a personal learning and portfolio collection to demonstrate practical understanding of:
- end-to-end ML and DL pipelines
- neural network based models
- sequence modelling using RNN and LSTM
- production-oriented project structure and MLOps concepts
Abhishek Chaudhary