About W Booth School

SEP 786 Artificial Intelligence and Machine Learning Fundamentals

• Solving Problems using AI: Searching, optimization, online search agents. Constraint satisfaction.
• Knowledge, Reasoning and Planning: Logic and Inference, Planning and Acting, Knowledge Representation. Knowledge and Reasoning with Uncertainty. Machine learning problems, training and testing, overfitting.
• Modelling strategies: data preprocessing, overfitting and model tuning. Measuring predictor importance. Factors that Can Affect Model Performance. Feature selection. Measuring performance of classification models.

SEP 787  Machine Learning : Classification Models

• Discriminant analysis and other linear classification: Logistic regression, Linear discriminant analysis, Partial least squares discriminant analysis, Penalized models, Nearest shrunken centroids
• Linear Support Vector Machine: Empirical vs structural risk minimization, Soft margin classifier
• Nonlinear classification models: Nonlinear discriminant analysis, Flexible discriminant analysis, Support vector machines, K-nearest neighbors, Naïve Bayes
• Classification Trees and Rule based modes: Basic classification trees, Rule-based models, Bagged trees, Random forests, Boosting
• Remedies for severe class imbalance: The effect of class imbalance, Model tuning, Alternate cutoffs, Adjusting prior probabilities, Unequal case weights.

SEP 788 Neural Networks and Development Tools

• Introduction to AI landscape.
• Tools for building a machine learning project (Python crash course).
• Neural Networks Mathematical background.
• Hyperparameters, Generalization, Training process.
• Using Python scikit-learn.
• Project 1 – build and train a neural network using python scikit-learn
• Neural networks vs deep learning.
• TensorFlow
• Applying TensorFlow for Machine learning,
• Project 2- use TensorFlow/Keras for defining and training a deep learning network (use case).
• Other DNN frameworks and hardware.
• Project 3- More complex deep learning challenge (using Google cloud or Azure) .

SEP 789 Deep Learning and Its Applications

• Image processing using machine learning.
• Convolutional Neural Network (CNN) Architecture and training.
• Image recognition application.
• Transfer learning, Image classification, Image segmentation, Image labeling, Clinical imaging.
• Project 1 – build and train a CNN network (image processing).
• Recurrent Neural Network (RNN) Architecture; RNN Applications (Time series, Stock market).
• Deep learning application in Natural language processing.
• Smart manufacturing: Comparison between deep learning and traditional machine learning, Product quality inspection, Fault assessment, Defect prognosis.
• Project 2 – build and train a RNN network.
• Reinforcement learning: Architecture; Application in Robotics, Application in display advertising.
• Advanced topics: Autoencoders, Deep Residual Networks, Generative Models (GANs).
• More Applications: Digital & Smart Systems, Energy, Transportation, Micro-Nano Systems, Advanced Manufacturing
• Project 3 – select one project out of 3-4 themes with data sets to apply deep learning with minimal guidance.

SEP 767 Multivariate statistical methods for Big Data analysis and process improvement

• Course overview and introduction
• Principal Component Analysis (PCA)
• Applications of PCA
  • Monitoring processes
  • Data visualization
• Projection to Latent Structures (PLS)
• Applications of Latent Variable Methods
  • Soft Sensors
  • Advanced pre-processing
• Working with images
• Classification
• Dealing with batch data
• Multiblock data analysis

SEP 6CG3: Fundamentals of computer graphics and animation development

Review platforms and languages for development: C++, C#, Unity, Maya API, Python, CUDA/Open CL along with  open sourse software in the Visual effects field: Open Image IO, Open shading language, Mitsuba.  Key mathematical and algorithmic foundations of animation and applications in the field of visual effects applications: geometry, algebra, calculus, vector fields.  Areas of research: rendering, character animation, simulation, computer vision.

Principles and mathematics foundation of computer graphics. Creation of 2D and 3D pictures. Application of the given principles in common situations, such as how to approximate an ideal solution on available hardware, or how to represent a data structure more efficiently. Rendering equation, GPU architecture considerations, and importance- sampling in physically based rendering.

• Modern approaches to shading and rendering, e..g. probability theory for use in Monte-Carlo rendering
• Implementations of GPU shaders, software rendering, and graphics-intensive 3D interfaces
• 3D real-time graphics platforms–their design goals and trade-offs–including new mobile and browser platforms
• Programming and debugging approaches unique to graphics development
• Algorithms used for path following, hierarchical kinematic modelling, rigid body dynamics, flocking behaviour, particle systems, collision detection.

SEP 6VE3: Visual effects and animation production technology

Domain knowledge of visual effects pipelines. Overview of how productions are executed:  Film, TV, Games, Mixed reality.   Introduction to major 3rd party applications software: Autodesk Maya, Pixar’s Renderman, Mitsuba, Foundry Nuke, Unity Game Engine.  Brief summary of research and development areas: rendering, digital creature/human, simulation, image processing, computer vision.

Basics of visual effects and compositing, the fundamentals of bluescreen  and greenscreen keying, 3D texturing, cloning, wire & rig removal, rotoscoping, 2D and 3D motion tracking, and matchmoving. Various forms of 2D, 2.5D & 3D visual effects, including 3D CGI, crowd replication, face replacements, faking shadows, reflections and Z depth, atmospheric, smoke, cloud & heat FX, sky replacements, day-for-night and digital 3D HUD FX. Selected topics in 2D, 2.5D & 3D digital matte painting and projections, film colorization, particle systems, fluid and rigid body dynamics, full digital environments, digital destruction, advanced lighting and rendering techniques, stereoscopic 3D, 2D to 3D conversions, and expert 3D and Photoshop extraction and modeling techniques.

SEP 714: Workflow management for animated prototypes

The course deals with the workflow employed in production of animated visual content.  Management of large scale dataset for creative technology application, asset management and development of building blocks which are required to develop the pipeline and use of Python as the basis for integration within the workflow.

• Development with Python
• Asset creation, Asset bundles & version management
• Dependency graph evaluation
• Database infrastructure for published assets
• Department and production workflows
• Render farm utilization
• Distributed render management

SEP 715: Rendering techniques

Mathematical theory behind a modern photorealistic rendering system and its practical implementation.   Monte Carlo integration, Shading and lighting algorithms, Acceleration structures, Ray tracing optimization.  Volume rendering techniques used for feature animation and visual effects production.

The course presents both the mathematical theory behind a modern photorealistic rendering system and its practical implementation. Through a method known as 'literate programming', the material combines a human-readable documentation and source code into a single framework that is specifically designed to aid comprehension. Ray-tracing hair and curves primitives, numerical precision issues with ray tracing, LBVHs, realistic camera models, the measurement equation, and Discussion of bidirectional path tracing, numerical robustness issues in ray tracing, realistic camera models, and subsurface scattering.

Modern production volume rendering techniques in a generic context, explaining how the techniques fit together and how the modules are used to achieve real-world goals.  Implementation of the techniques, showing how to translate abstract concepts into concrete, working code and how the ideas work together to create a complete system.

SEP 791: Augmented Reality, Virtual Reality and Mixed Reality

In-depth exploration of the rapidly developing new interdisciplinary topic employing techniques from computer graphics, computer vision, and virtual immersion techniques with applications in varying fields including entertainment, manufacturing and sciences.

• Stereoscopy fundamentals
• Psychology of vision and immersion
• Current hardware (Magic Leap AR, Oculus, Vive, PS4 VR, Hololens)
• Virtual reality vs. Augmented reality vs. mixed reality
• Holographic techniques of challenges
• 360 degrees video processing for VR
• Development platforms

SEP 792: Interactive applications utilizing GPU's for real-time projects

Modern techniques used to generate rapidly synthetic three-dimensional images. With the advent of programmable shaders, a wide variety of new algorithms have arisen and evolved over the past few years and are presented in this course.

• Open GL/ Vulkan, Unity/ Unreal game engines
• Game engine architecture
• Real time rendering techniques
• CPU compute via CUDA/ Open CL/ Direct compute
• GPU architecture
• Computer vision