Continuous learning across deep learning, machine learning, and applied data science.
Foundations of deep learning, neural network components, training challenges, and building regression and classification models with Keras — including CNNs, RNNs, and transformers.
Custom Keras layers and models integrated with TensorFlow 2.x, advanced CNNs, transformers for sequential data and time series, plus foundations of unsupervised learning, autoencoders, GANs, and reinforcement learning with DQNs.
End-to-end ML workflow covering KNN, decision trees, linear & logistic regression, PCA, model selection, tuning, and combatting bias and drift.
Completed a project-based Udemy course, applying theory through practical exercises and capstone projects.