Introduction to Data Science

Course Details

• Course Title: Introduction to Data Science
• Course Code: MSDS-600
• Credit Hours: 3
• Pre-requisite: None
• Offered To: Master of Science in Data Science
• Level: Undergraduate, Graduate
• Institution: Regis University, Denver, CO, USA
• Faculty: Marketing and Data Science Department
• Semester Offered: Spring 2025

Objectives

This course offers a comprehensive introduction to deep learning, emphasizing machine learning techniques for training deep neural networks using Keras and TensorFlow. Students will delve into deep-learning principles and acquire a thorough understanding of neural networks, including their architecture, training methodologies, and optimization strategies. A significant focus will be placed on convolutional neural networks (CNNs) for image segmentation and classification, along with their real-world applications. Furthermore, students will learn how to utilize parallel GPU-based computation to enhance model efficiency and performance. By the conclusion of the course, participants will be equipped to implement deep learning models, adopt best practices for training and fine-tuning networks, and employ deep learning frameworks to tackle complex challenges in data science.

Learning Outcomes

Students will acquire a robust foundational understanding of deep learning concepts and their practical applications after successfully completing the course. They will be able to articulate the fundamental principles of neural networks, including feedforward networks, activation functions, and backpropagation. Students will gain hands-on experience building and training convolutional neural networks (CNNs) for image classification tasks, employing key techniques such as data augmentation, regularization, dropout, and early stopping to enhance model performance. Furthermore, they will learn to optimize learning rates and batch sizes to improve training efficiency. Through practical assignments and projects, students will develop expertise in utilizing Keras and TensorFlow to implement deep-learning models. They will also delve into advanced topics such as transfer learning and text processing with deep learning. Ultimately, students will apply their knowledge to a real-world deep learning project, utilizing Kaggle datasets to devise and present a data-driven solution.

Course Outline