Machine Learning Specialization
The full Andrew Ng machine learning foundation across supervised learning, advanced algorithms, unsupervised learning, recommenders, and reinforcement learning.
Certificate Archive
Certificates, badges, and books.
A dedicated evidence page for the full education archive: verified Coursera/Credly credentials, Kaggle learning certificates, and the books that shaped my AI engineering path.
Certificates
Verified credentials and learning proofs.
Click any certificate image to zoom it. Use the button on each card for the verified certificate, Kaggle certificate/course link, or official source.
Supervised Machine Learning: Regression and Classification
Regression, classification, logistic regression, cost functions, and gradient descent as the first formal ML layer.
Advanced Learning Algorithms
Neural networks, decision trees, random forests, boosted trees, and practical ML development decisions.
Unsupervised Learning, Recommenders, Reinforcement Learning
Clustering, anomaly detection, PCA, collaborative filtering, recommender systems, and reinforcement learning foundations.
Deep Learning Specialization(v.2)
Neural networks, optimization, project strategy, CNNs, sequence models, attention, and Transformers.
Neural Networks and Deep Learning
The real beginning of the deep learning path: parameters, activations, forward propagation, gradients, vectorization, and deep networks.
Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization
Initialization, regularization, optimization algorithms, gradient checking, and better neural-network training practice.
Structuring Machine Learning Projects
Machine learning project strategy: error analysis, bias/variance, dataset splits, and choosing what to improve next.
Convolutional Neural Networks
CNN fundamentals, ResNets, transfer learning, object detection, face recognition, neural style transfer, and segmentation.
Introduction to TensorFlow for AI, ML and Deep Learning
Keras training pipelines, callbacks, image classification basics, and practical TensorFlow foundations.
Convolutional Neural Networks in TensorFlow
TensorFlow computer vision practice: image pipelines, augmentation, transfer learning, and multi-class classification.
Generative AI: Introduction and Applications
A broad introduction to generative AI applications across text, image, audio, video, and code.
Intro to Programming
Early notebook-based programming practice inside Kaggle Learn.
Python
Practical Python exercises for data science workflows and notebook confidence.
Intro to Machine Learning
Applied ML workflow practice: validation, decision trees, random forests, and prediction.
Pandas
DataFrame manipulation, indexing, grouping, missing values, and cleaning basics.
Completed 5-Day Gen AI Intensive
GenAI system concepts: prompting, embeddings, retrieval, and modern application architecture.
5-Day AI Agents Intensive Course with Google
Agents as systems with tool use, memory, planning, execution loops, and GenAI workflows.
Books
Books that shaped the path.
All four books are included here with official publisher links and repository links where available.
Machine Learning with PyTorch and Scikit-Learn
PyTorch, sequence modeling, Transformers, GANs, graph neural networks, and reinforcement learning.
Introducing MLOps: How to Scale Machine Learning in the Enterprise
The production layer after notebooks: deployment, monitoring, governance, artifacts, and feedback loops.
Natural Language Processing with Transformers
Current NLP mastery layer focused on Hugging Face, Transformers, classification, generation, QA, and summarization.
Build a Large Language Model (From Scratch)
LLM internals: tokenization, embeddings, attention, GPT blocks, pretraining, evaluation, and fine-tuning.