Overview

Coursera Plus Annual Sale: All Certificates & Courses 25% Off!

Grab it

NVIDIA: Fundamentals of Machine Learning Course is a foundational course designed to introduce learners to key machine learning concepts and techniques. This course is the first part of the Exam Prep (NCA-GENL): NVIDIA-Certified Generative AI LLMs Associate specialization. The course covers fundamental machine learning principles, including supervised and unsupervised learning, model training, evaluation metrics, and optimization techniques. It also provides insights into data preprocessing, feature engineering, and common machine learning algorithms. This course is structured into three modules, each containing Lessons and Video Lectures. Learners will engage with approximately 5:00-6:30 hours of video content, covering both theoretical concepts and hands-on practice. Each module is supplemented with quizzes to assess learners' understanding and reinforce key concepts. Course Modules: Module 1: ML Basics and Data Preprocessing Module 2: Supervised Learning & Model Evaluation Module 3: Unsupervised Learning, Advanced Techniques & GPU Acceleration By the end of this course, a learner will be able to: - Understand the fundamentals of AI, ML, and Deep Learning, and their key differences. - Implement supervised learning techniques like classification and regression. - Apply clustering methods and time series analysis using ARIMA. - Leverage NVIDIA RAPIDS for GPU-accelerated ML workflows. This course is intended for individuals looking to enhance their machine-learning skills, particularly those interested in GPU-accelerated AI workflows and NVIDIA technologies.

Syllabus

ML Basics and Data Preprocessing.

Welcome to Week 1 of the NVIDIA: Fundamentals of Machine Learning course. This week, we will explore ML Basics and Data Preprocessing, starting with an introduction to the course and best practices for exam success. We will define machine learning and set expectations for the Fundamentals of Machine Learning course. As we progress, we will differentiate between AI, Deep Learning, and Machine Learning and examine the types of machine learning. We will also cover the key steps involved in the machine-learning process. By the end of the week, we will dive into data preprocessing essentials, understanding its significance in machine learning workflows. A demo session on data preprocessing will provide hands-on insights into preparing data for model training.

Supervised Learning & Model Evaluation

Welcome to Week 2 of the NVIDIA: Fundamentals of Machine Learning course. This week, we will explore the fundamentals of Supervised Machine Learning and Modal Evaluation, covering both Classification and Regression techniques. We will begin by understanding the principles of classification and regression models and their applications. As we progress, we will explore the process of model selection, training, and evaluation, followed by an in-depth discussion on evaluating classification models using the Confusion Matrix. Additionally, we will examine key evaluation metrics for both classification and regression models through theoretical explanations and hands-on demonstrations.

Unsupervised Learning, Advanced Techniques & GPU Acceleration

Welcome to Week 3 of the NVIDIA: Fundamentals of Machine Learning course. This week, we will cover Unsupervised Learning, Advanced Techniques & GPU Acceleration, starting with unsupervised learning techniques like KMeans, hierarchical, and density-based clustering, along with a hands-on demo. We'll also explore association rule mining and NVIDIA RAPIDS for GPU-accelerated workflows, including a demo. Additionally, we'll learn about cross-validation techniques (GridSearch and Randomized Search) with a practical demo and conclude with the ARIMA model for time series analysis, along with a hands-on demo.