CSC 6621 - Applied Machine Learning

• Understand the fundamental concepts and application of supervised, unsupervised, semi-supervised, and reinforcement learning 
• Understand the concepts of learning theory, (e.g., what is learnable, bias, variance, overfitting, curse of dimensionality, splitting data for evaluation of model predictions) 
• Derive, visualize, apply, and interpret metrics and loss functions to assess the quality of model predictions and fit to data 
• Describe the fundamentals of deep learning and what is required to be able to use it 
• Compare various modern deep neural network architectures (e.g., convolutional neural networks (CNNs), encoder-decoders, generative adversarial networks (GANs), or transformers).
• Implement, train, and evaluate deep learning models using popular libraries
• Describe applications of deep learning to solving real-world problems 
• Describe the components of the intelligent agent framework 
• Apply agent and state-based frameworks to solve various problems such as game playing 
• Provide examples of search problems and techniques for solving them 
• Describe and apply algorithms such as value iteration and q-learning to identify optimal policies 
• Describe the role of heuristics and describe the trade-offs among completeness, optimality, time complexity, and space complexity 
• Read, interpret, and explain primary literature from the field of AI
• Present the results of ML and AI projects to technical and non-technical audiences

• Software development
• Object-oriented Python
• Jupyter Notebooks
• Data ingestion, manipulation, and cleaning using DataFrames
• Data exploration and interpretation using visualization and statistical techniques
• Training and applying basic machine learning models
• Ability to apply and interpret appropriate metrics for classification and regression problems