Course

Course Summary
Credit Type:
Course
ACE ID:
UMDC-0001
Organization's ID:
AIF
Location:
Online
Length:
24 weeks, 120 hours
Dates Offered:
Credit Recommendation & Competencies
Level Credits (SH) Subject
Upper-Division Baccalaureate 3 Artificial Intelligence and Machine Learning
Description

Objective:

This program is for individuals with an active interest in applying for entry-level jobs to work in Artificial Intelligence related fields. During the program, students will explore the topics, technology, and skills required to gain practice in the successful application of AI/ML techniques to address key industry problems.

Learning Outcomes:

  • Define mathematical and statistical concepts relevant to data science
  • Define concepts of structured and unstructured data
  • Demonstrate an in-depth understanding of supervised and unsupervised learning
  • Examine data science applications
  • Explain the concepts relevant to training AI/ML models
  • Analyze the complexity of a given problem and come up with suitable optimizations
  • Demonstrate advanced programming skills with Python
  • Design and train ML models based on different kinds of architecture
  • Describe the fundamentals of Bayesian decision models and hypothesis testing
  • Design and train ML models based on different kinds of architecture
  • Demonstrate mastery of the implementation of adversarial neural networks

General Topics:

  • Artificial Intelligence and Machine Learning (AI/ML) Roadmap Fundamentals of Probability Fundamentals of Statistics Regression Analysis Dimensionality Reduction Methods Linear Discriminant Analysis Types of Learning Artificial Neural Networks I, II and III Fundamentals of Decision Trees Performance Evaluation Trees Natural Language Processing Design and Analysis of Neural Networks Neural Networks Components and Concepts I and II Architecting Deep Neural Networks Architecting Recurrent Neural Networks Computer Vision Methodologies Design and Customization of the Components of Convolutional Neural Networks Architecting Convolutional Neural Networks Language Models I and II Generative Adversarial Networks Deep Feedforward Networks, Dynamics and Processes Regularization Methods for Deep Learning Regression Bayesian Decision Theory Hypothesis Testing Decision Trees Unsupervised Learning Algorithms for Convolutional Networks Algorithms for Recurrent or Recursive Networks Autoencoders and Compression Mechanisms Optimal Decision Deep Reinforcement Learning Stochastic Machine Learning Adversarial Networks
Instruction & Assessment

Instructional Strategies:

  • Audio Visual Materials
  • Case Studies
  • Discussion
  • Laboratory
  • Learner Presentations
  • Practical Exercises
  • Project-based Instruction
  • Performance Rubrics (Checklists)

Methods of Assessment:

  • Case Studies
  • Examinations
  • Performance Rubrics (Checklists)
  • Presentations
  • Quizzes

Minimum Passing Score:

70%
Supplemental Materials

Other offerings from University of Miami, Division of Continuing & International Education

(UMDC-0007)
(UMDC-0006)
(UMDC-0004)