This repository contains hands-on implementations, exercises, and applied machine learning workflows completed as part of the IBM AI Engineering Professional Certificate. The program focuses on practical AI engineering using machine learning, deep learning, and large language models (LLMs) with PyTorch, TensorFlow, and modern MLOps practices.
| Certification | Credential |
|---|---|
 |
IBM – AI Engineering |
 |
IBM – Generative AI Engineering with LLMs Pr |
 |
IBM – Deep Learning with TensorFlow, Keras, and PyTorch |
- End-to-end ML development: model design, training, optimization, evaluation
- Supervised learning: linear/logistic regression, SVMs, decision trees, ensembles
- Unsupervised learning: k-means, hierarchical clustering, PCA
- Bias–variance tradeoff, regularization (L1/L2), cross-validation, hyperparameter tuning
- Neural network architecture design (feedforward, CNNs, RNNs, LSTMs, GRUs)
- Activation functions, initialization strategies, dropout, batch normalization
- Backpropagation, gradient descent variants (Adam, RMSProp, SGD with momentum)
- Computer Vision pipelines with CNNs
- Sequence modeling and time series forecasting
- Transformer architecture, attention mechanisms, encoder–decoder frameworks
- LLM fine-tuning using PEFT (LoRA, QLoRA) and prompt optimization
- Retrieval-Augmented Generation (RAG) using LangChain and vector databases
- Model evaluation for LLM tasks (BLEU, ROUGE, perplexity)
- Hugging Face model training and deployment workflows
- Tokenization, embeddings (Word2Vec, GloVe), contextual embeddings
- Sequence-to-sequence models for translation and classification
- Text preprocessing pipelines and feature engineering
- Model serving and API deployment with FastAPI and Flask
- Interactive AI applications using Gradio
- Experiment tracking and reproducibility
- Data pipeline engineering and model lifecycle management
- IBM watsonx.ai integration for foundation model deployment
| Category | Tools (non-exhaustive) |
|---|---|
| Programming | Python, NumPy, Pandas, SciPy |
| Machine Learning | scikit-learn, XGBoost |
| Deep Learning | PyTorch, TensorFlow, Keras |
| LLM/Generative AI | Hugging Face Transformers, LangChain, FAISS, ChromaDB |
Each folder in this repository corresponds to a course module or applied lab from the IBM AI Engineering curriculum. Source code includes:
- Notes from lectures
- Training notebooks
- Model builds and experiments
All work in this repository represents original implementations. Please do not copy this work; doing so would violate Coursera's Honor Code and IBM Skills Network's academic policy.
For more details on methodology or project implementations, refer to the source folders in this repository.