Specialization Machine Learning: Theory and Practical Work with Python

In the Machine Learning specialization, we cover supervised learning, unsupervised learning, and the fundamentals of deep learning. You’ll apply ML algorithms to real-world data, learn when to use each model and why, and improve the performance of your models. Starting with supervised learning, we’ll cover linear and logistic regression, KNN, decision trees, ensemble methods like Random Forest and Boosting, and kernel methods like SVM. We’ll then move on to unsupervised methods, including dimensionality reduction methods (e.g. PCA), clustering, and recommender systems. We’ll finish with a deep learning foundation, including choosing a model architecture, building/training neural networks using libraries like Keras, and practical examples of CNNs and RNNs. This specialization can be completed for credit through CU Boulder’s MS in Data Science or MS in Computer Science programs, both offered on Coursera. These fully accredited degrees offer targeted courses, short 8-week sessions, and tuition-based learning. Admission is based on three prerequisite courses, not academic history. CU degrees on Coursera are ideal for recent graduates or working professionals. Learn more: Applied learning project In this specialization, you'll build a movie recommendation system, identify cancer types from RNA sequences, use CNNs for digital pathology, practice NLP techniques on disaster tweets, and even create your own dog images using GANs. You'll complete a final project on supervised, unsupervised, and deep learning to demonstrate your mastery of the course.