Course

Machine Learning: Theory and Hands-on Practice with Python

University of Colorado Boulder

In the Machine Learning specialization, you will delve into the fundamentals of supervised and unsupervised learning, as well as introductory deep learning topics using Python. This course equips you with the skills to apply machine learning algorithms to real-world data, understand when to use different models, and enhance model performance. With a strong emphasis on practical application, you will gain hands-on experience with popular Python libraries and develop the ability to evaluate and compare the strengths and weaknesses of various machine learning models.

Throughout the course, you will explore classic supervised learning algorithms such as logistic regression, decision trees, KNN, and ensembling methods like Random Forest and Boosting. Additionally, you will delve into unsupervised methods, including dimensionality reduction techniques, clustering, and recommender systems. The specialization culminates with an introduction to deep learning basics, encompassing model architectures, neural network building and training using libraries like Keras, and practical examples of CNNs and RNNs.

By the end of the course, you will be adept at selecting the most suitable machine learning models based on data properties, tuning hyperparameters to enhance model performance, and applying various techniques such as sampling and regularization to refine your models.

Certificate Available ✔

Get Started / More Info
Machine Learning: Theory and Hands-on Practice with Python
Course Modules

Gain comprehensive insights into supervised learning, unsupervised algorithms, and deep learning. Master modern machine learning tools and libraries, and build and evaluate machine learning models using Python.

Introduction to Machine Learning: Supervised Learning

Introduction to Machine Learning: Supervised Learning

  • Utilize modern machine learning tools and popular Python libraries.
  • Compare the strengths and weaknesses of logistic regression.
  • Learn how to handle linearly-inseparable data.
  • Understand the concept and implementation of decision trees for data splitting.

Unsupervised Algorithms in Machine Learning

Unsupervised Algorithms in Machine Learning

  • Comprehend unsupervised learning and its methods.
  • Explore various matrix factorization algorithms and their applications.

Introduction to Deep Learning

Introduction to Deep Learning

  • Apply optimization methods during training and analyze their behavior.
  • Implement CNN architecture and train for image classification tasks using cloud tools and deep learning libraries.
  • Utilize deep learning packages for sequential data, including model building, training, and tuning.
More Machine Learning Courses

Data Engineering in AWS

Whizlabs

Data Engineering in AWS provides comprehensive training in analyzing data gathering techniques, handling missing data, and implementing feature extraction and selection...

Introducción al procesamiento de lenguaje natural

Universidad Austral

Introducción al procesamiento de lenguaje natural es un curso introductorio que te capacitará en NLP, clasificación de texto, análisis de sentimiento y más,...

Probabilistic Graphical Models 3: Learning

Stanford University

This course delves into the learning aspect of probabilistic graphical models, exploring parameter estimation and structure learning. Students gain hands-on experience...

Prompt Engineering

Vanderbilt University

Unleash the power of Generative AI with Prompt Engineering to automate tasks, increase productivity, and augment human intelligence.