Welcome to my learning hub! Integrating core Subsurface Energy Engineering into Machine Learning, Data Analytics, and Software Engineering has been a continuous and rewarding journey.
My approach to learning centers on bridging foundational mathematical principles with practical, hands-on application to real-world engineering datasets.Below is a curated selection of core machine learning, deep learning, and artificial intelligence courses that I've been using in my learning journey,as they provide structured pathways for mastering modern data science and engineering.
Platform / Provider: UC Berkeley (YouTube Lecture Series)
Covers fundamental AI algorithms including search trees, constraint satisfaction, Markov Decision Processes (MDPs), reinforcement learning, probabilistic reasoning, and machine learning models.
Platform / Provider: Massachusetts Institute of Technology (MIT)
An intuitive and rigorous introduction to deep learning algorithms and applications. Topics include neural networks, computer vision (CNNs), sequence modeling (RNNs/LSTMs/Transformers), and generative AI models.
Platform / Provider: Stanford University (Lectures by Andrew Ng)
The premier graduate-level introduction to machine learning. Covers supervised learning (linear models, SVMs, kernels), unsupervised learning (clustering, dimensionality reduction), learning theory, and reinforcement learning.
Platform / Provider: Google Developers
A fast-paced, practical introduction to machine learning using TensorFlow. Features interactive coding exercises, best practices for feature engineering, model productionization, and handling real-world datasets.