MASTER OF SCIENCE IN APPLIED ARTIFICIAL INTELLIGENCE

Interest in and usage of Machine Learning systems has increased dramatically in recent years. More and more innovative products and research rely on Machine Learning systems that leverage data to make predictions and identify trends. However – as with many cutting-edge fields – Machine Learning systems are often implemented improperly. As a result, many Machine Learning systems are unreliable, inefficient, or even useless. Machine Learning Operations (MLOps) is a methodology whose goal is to design, build, deploy, and maintain machine learning models properly. MLOps combines practices from Machine Learning, Data Engineering, and DevOps to ensure that Machine Learning models and algorithms are reliable, efficient, and – most importantly – useful. This course will introduce students to the key concepts of MLOps and a holistic method of designing suitable ML systems. Students will learn and perform the best practices for building Machine Learning systems with hands-on learning experiences and real-world applications. While students will learn about and implement some Machine Learning algorithms in this course, this course is not intended to teach them about the field of Machine Learning. Rather, students will learn how to properly design Machine Learning systems throughout the entire lifecycle.

Prerequisites: AAI 510, AAI 511, AAI 520, AAI 521, AAI 530, and AAI 531

Recent advances in big data, computational power, smart homes, and autonomous vehicles have rendered artificial intelligence (AI) as a major technological revolution in engineering and computer science. The goal of this course is to introduce students to the fundamental principles, techniques, challenges, and applications of AI, machine learning, and natural language processing. Topics covered include heuristic search and optimization techniques, genetic algorithms, machine learning, neural networks, and natural language understanding. Several applications of AI will be explored, including computer vision, pattern recognition, image processing, biomedical systems, Internet of Things, and robotics.

Machine learning (ML) is an interdisciplinary field that is focused on building models by algorithmic processing of data with minimal assumptions about the nature of the data. The models may be used to understand a process, make informed projections, or automate decisions. The field combines principles from statistics, computer science, and application domains. The application domains range across engineering, manufacturing, medicine, commerce, research, etc. This class will introduce students to the fundamental concepts and algorithms for machine learning. Students will learn fundamental concepts such as data cleaning and transformation, feature engineering, modeling training, validation and testing, overfitting, underfitting, and model evaluation. They will learn supervised learning algorithms such as regression, support vector machines, etc; and unsupervised learning algorithms such as k-means, Principal Component Analysis (PCA), and hierarchical clustering. Time series analysis will be briefly covered as well. Students will learn to appreciate and be sensitive to ethical issues affecting the use of machine learning in society. Prerequisites: AAI 500 and AAI 501

Neural networks have enjoyed several waves of popularity over the past half-century. The many applications of neural networks include apps that identify people in photos, automated vision systems for large-scale object recognition, smart home appliances that recognize continuous, natural speech, self-driving cars, and software that translates from any language to any other language. In this course, students will learn the fundamental principles and concepts of neural networks and state-of-the-art approaches to deep learning using in-demand Python packages, such as TensorFlow and PyTorch. Students will learn to design neural network architectures and training methods using hands-on assignments and will perform comprehensive final projects in this course. Prerequisites: AAI 500 and AAI 501