Upper Division

Summary of Course Content
None

Illustrative Reading
None

Potential Course Overlap
None

Summary of Course Content
I. Views of Technology
II. Philosophical Ethics
III. Technology and the Environment
IV. War and Other Threats to Human Existence
V. Privacy and Intellectual Property
VI. Responsibility and Professional Ethics


Illustrative Reading
A reader assembled by Phillip Rogaway includes work by: Ian Barbour, Robert Heilbroner, Langdon Winner, John Lienhard, Neil Postman, Deborah Johnson, Hans Jonas, David Strong, Jared Diamond, Ruth Schwartz Cowan, Freeman Dyson, Marshal McLuhan, Thomas Friedman, Suketu Mehta, the UN IPCC, Garrett Hardin, Amory Lovins, Eric Markusen, Bill Joy, James Boyle, Richard Stallman, Cory Doctorow, Jeff Schmidt, and the ACM.

Potential Course Overlap
There is no significant overlap with any other course since the focus of this course is on ethical issues as they arise in the field of computer science. Engineering 190 is a related course on professional ethics and responsibility in engineering. .

Final Exam
Yes Final Exam

Summary of Course Content

1. Basic Theory of Curves and Surfaces
   1. Mathematical representation of shapes
   2. Parametric representation of curves and surfaces
   3. Evaluation of geometrical characteristics
2. Interpolation Methods
   1. Lagrange and Hermite interpolation
   2. Ferguson and Coons surface patches
3. Theory of Splines
   1. Spline functions
   2. Natural splines
   3. Generation of spline curves and surfaces
   4. Best approximation/error-minimizing approximation (e.g., least squares method)
4. Approximation Methods for Curves and Surfaces
   1. Bernstein-Bezier Approximation
   2. B-spline curves and surfaces
   3. Rational polynomial curves and surfaces
   4. NURBS (Non Uniform Rational B-splines)
5. Special Surface Schemes
   1. General surface schemes (e.g., triangular patches, multi-sided patches)
   2. Subdivision schemes (e.g., Doo-Sabin and Catmull-Clark schemes)
   3. Surface interrogation (e.g., normal and curvature behavior)
   4. Scattered data interpolation (e.g., object/function reconstruction)
6. Applications of Geometric Modeling
   1. Elements of computer-aided design systems (e.g., extruded, ruled, rotational surfaces; degree elevation/reduction; implicit vs. parametric representation)
   2. Methods for discretizing/meshing geometry (e.g., triangulation, quadrangulation)
   3. Computer graphics/animation applications (e.g., character modeling)
   4. Scientific data approximation and visualization applications (e.g., Voronoi diagrams; approximation methods for triangulations/tessellations)

Illustrative Reading
G. Farin, Curves and Surfaces for CAGD: A Practical Guide, 5th ed., Morgan Kaufman, 2002.

Potential Course Overlap
None

Summary of Course Content

1. Grid Structures Scientific data sets can be given without any given connectivity among the data (scattered data) or on a so-called structured or unstructured grid. Typical grids (rectilinear, curvilinear, prismatic, tetrahedral, etc.) are discussed and appropriate data structures and interpolation methods are introduced.
2. Basic Scalar Field Visualization A variety of techniques for the visualization of scalar fields, i.e. functions of the form f(x,y) and f(x,y,z), are discussed. Algorithms that use color and/or opacity to represent the scalar value will be presented, including slicing, and various volume rendering techniques (ray casting, 3D texture-based volume rendering in OpenGL, cell sorting and projection). Contour curves and surfaces will also be discussed.
3. Basic Vector Field Visualization A variety of techniques for the visualization of vector fields, i.e., vector-valued functions of the form [u(x,y), v(x,y)] and [u(x,y,z), v(x,y,z), w(x,y,z)] will be discussed. Algorithms that will be presented include the approximation and visualization of path, stream, streak, and time lines, surfaces, and tubes, as well as texture-based and glyph-based methods. Tensor visualization will also be briefly discussed. Optional topics:
   1. Molecular visualization: The techniques for visualizing atoms and bonds, and special glyphs for representing protein structures may be discussed.
   2. Animation: Methods for producing animated image sequences for visualizing time varying data, and for interpolating data in time as well as space, may be discussed.
   3. Tensor fields: The method of finding the principal components of a symmetric tensor may be discussed, as well as methods using them to visualize tensor fields.
   4. Information visualization: The distinction between scientific visualization of continuous quantitative data and information visualization of discrete or non-quantitative data and may be discussed, as well as a few examples of information visualization, for example, graph and/or tree visualization.

Illustrative Reading
Alexandru Telea, Data Visualization: Principles and Practice. A K Peters, Ltd., 2008.

Potential Course Overlap
None

Summary of Course Content

1. Computer Graphics Hardware
   1. The interactive graphics pipeline
   2. Basic architecture of modern Graphics Processing Units
   3. The CPU-GPU interface
2. Curve and Surface Drawing
   1. Line drawing
   2. Bezier curves and B-spline curves
   3. Rasterization of triangles
3. Transformations
   1. Transformation matrices and their combinations
   2. Modeling and viewing transformations
4. Modeling
   1. Object representations
   2. Hierarchical scene structure and generation of complex objects
   3. Object file formats
   4. Texture mapping
5. Lighting
   1. Specular and diffuse lighting models
   2. Interactive lighting models, including their drawbacks
   3. Flat and Gouraud shading of triangulated models
6. Rendering
   1. Camera models and interaction
   2. Z-buffering and other visible-surface algorithms Other topics such as Bezier curves, ray tracing, clipping and culling may be discussed.

Illustrative Reading

• P. Shirley, M. Ashikhmin, and S. Marschner, Fundamentals of Computer Graphics, 3rd edition, AK Peters, 2009.
• E. Angel and D. Schreiner, Interactive Computer Graphic: A Top Down Approach With Shader-Based Open GL, 6th edition, Addison- Wesley, 2011.
• S. Gortler, Foundations of 3D Computer Graphics, MIT Press, 2012.
• D. Hearn, M. Baker, and W. Carithers, Computer Graphics with Open GL, 4th edition, Prentice-Hall, 2010

Potential Course Overlap
There is no significant overlap with other courses.

Summary of Course Content

1. Students will acquire a general background on computer vision. Topics will include: Features and Filters
   1. Linear filters
   2. Edge detection and image gradients
   3. Edges, contours, and binary image analysis
   4. Texture
   5. Color
2. Grouping and Fitting
   1. Gestalt properties
   2. K-means, Mean-shift, Spectral clustering
   3. Hough transform
   4. Deformable contours
   5. RANSAC
   6. Homography
3. Recognition
   1. Local Invariant feature detection and description
   2. Indexing local features
   3. Instance recognition
   4. Generic category recognition
   5. Discriminative classifiers (Nearest Neighbors, Support Vector Machines, Boosting)
   6. Window-based models
   7. Part-based models

Illustrative Reading
Richard Szeliski, Computer Vision: Algorithms and Applications, Springer, 2011.

Potential Course Overlap
There is a very small overlap with ECS 173. ECS 174 will have very limited overlap with the "2D image processing" module of ECS 173 (it has no overlap with the other 2 modules). ECS 174 focuses less on low-level image processing, and more on the high-level understanding of visual content. So the computer vision algorithms and techniques taught in ECS 174 are geared towards achieving this goal, most of which are not covered in ECS 173. There is also a minimal overlap with ECS 171 in the teaching of some unsupervised and supervised learning algorithms. This overlap is minimal and the treatment of the underlying methods is fundamentally different: ECS 171 focuses on general pattern recognition and machine-learning techniques, whereas ECS 174 focuses on processing visual input (i.e., computing image and video features) and applications of machine-learning techniques to visual data. It also teaches many algorithms specific to computer vision problems that are not taught in general machine learning courses such as ECS 171.

Summary of Course Content

1. Analysis of 2D Images (photographs)
   1. Low-level information extraction: Frequency-domain representation of images, edge and corner detection, and texture analysis will be discussed in detail. Specific algorithms to be discussed include derivative of Gaussian edge detection, Harris corner detection, and texton estimation.
   2. Image features: Students will learn various constructions for extracting relevant features from images. Students will learn about filter bank approaches, geometric and illumination invariants, and linear subspace decompositions of image patches. Identification of salient surface patches will also be discussed.
   3. Object recognition: Students will receive an overview of methods for describing and detecting objects in 2D images. Appearance-based methods based on principal components analysis, convolutional image filters, and raw image classification will be described. Shape-based object detection based on constellations of object parts, local edge features, and alignment to prototype shapes will be presented.
2. Analysis of 3D surface imagery
   1. 3D surface parameterization and representation: Representation of 3D surfaces based on points, parametric surface models, patches, and geons will be discussed. The effects of noise, partial occlusion, and sensor artifacts on these surface descriptions will also be described.
   2. Automated model building from surface data: Semi-automated and fully-automated procedures for building complete 3D models from collections of partial 3D sensor data sets will be presented. Semi-automated techniques based on landmark placement will be discussed. Fully-automated techniques based on local surface descriptors, constrained data collection, and global surface descriptors will be shown as well.
   3. Object recognition in 3D data: Detection of objects in 3D surface data sets will be discussed. The effects of partial occlusion and clutter will be discussed. Techniques based on alignment, local surface descriptors, and machine learning approaches will be described.
3. Analysis of volumetric images
   1. Low-level processing: Students will learn approaches to correct for image artifacts found in computed tomography (CT), magnetic resonance (MR), and functional MR images. Bias field correction, blowout, and scattering artifacts will be discussed.
   2. Description and modeling of biological shapes: Methods for mathematically describing biological objects found in volumetric images will be presented. Representation of 3D solids will be discussed, and computational anatomy approaches to representation of populations of shapes will be presented.
   3. Localization and detection of objects: Principles and algorithms for localizing biological shapes in volumetric images will be presented. Shape-model-based techniques for estimating the location of constrained, expected objects such as the brain will be discussed. Low-level detection of amorphous, unexpected objects such as tumors and calcifications will also be presented.

Illustrative Reading
Terry S. Yoo (Editor), Insight into Images: Principles and Practice for Segmentation, Registration, and Image Analysis, AK Peters Publishers, July 29, 2004

Potential Course Overlap
Volumetric images are also treated in ECS 177, but the emphasis there is on the visualization rather than automated extraction of high-level data. Two-dimensional image processing is treated in greater mathematical depth in EEC 206 and EEC 208, graduate courses which are currently taught infrequently.

Summary of Course Content
This course will provide an introduction to machine learning methods and learning theory. Students will acquire a general background on machine learning and pattern recognition, including state-of-the-art techniques in supervised and unsupervised learning. The course will include five problem sets that are related to the course outline. Students will work individually or as part of teams to complete a term project that will pertain on the application of these methods in different scientific fields. Topics will include:

1. Supervised learning
   1. Regression
   2. Generative learning
      1. Naive Bayes
      2. Bayesian learning
   3. Discriminative learning
      1. K-nearest neighbors
      2. Decision trees
      3. Support Vector Machines (SVM) and kernels 2) Unsupervised learning
         1. Clustering (K-means, hierarchical)
         2. Dimensionality reduction methods (principal component analysis, independent component analysis)
         3. Association rule mining
         4. Self-organizing maps
      4. Learning theory
         1. Bias-variance trade-offs
         2. Kernels
         3. Statistical validation
         4. VC Theory
      5. ML applications in other fields (Social networks, biology, image processing) Students will have to complete a computational/review project in coordination with the instructor.

Illustrative Reading

• C. Bishop. Pattern Recognition and Machine Learning. Springer, 2007 • Technical papers and class notes will be used.

Potential Course Overlap
There is an overlap with ECS 170, related to feature extraction methods and Bayesian methods. This overlap is minimal and the treatment of the underlying methods is fundamentally different: ECS 170 focuses on AI algorithms and logic-based decision making while ECS 171 takes a pattern recognition and machine-learning approach.