This course provides an in-depth introduction to the fundamental principles, architectures, and applications of neural networks. Students will explore the theoretical foundations of neural networks, understand their mathematical underpinnings, and gain practical hands-on experience in designing and implementing neural network models. The course covers a range of topics, from basic concepts to advanced architectures such as deep neural networks and convolutional neural networks. Real-world applications, including image recognition, natural language processing, and pattern recognition, will be examined to illustrate the practical utility of neural networks. Through a combination of lectures, practical exercises, and projects, students will develop the skills needed to apply neural networks to solve complex problems.
Outcomes
- Explain the structure and function of a basic perceptron.
- Study the architecture and training of deep neural networks (DNNs).
- Investigate convolutional neural networks (CNNs) for image recognition.
- Create hands-on projects to apply neural networks to practical problems.
- Evaluate the performance of neural network models.
- Explore techniques for fine-tuning and optimizing model parameters.
- Examine ethical considerations related to the use of neural networks.
- Discuss the societal impact of neural network applications.
Prerequisites
N/A
Crosslisted Courses
N/A N/A Winter, Summer
Campus
Central
Area of Study
Career Education