Courses


Spring/ Fall 2015

 



Fall 2015
ECE 549/ CS 543 Computer Vision 
Instructor: Derek Hoiem

I worked as a teaching assistant for the course. 

I covered one tutorial and two lectures: 

Fall 2015
CS 445 Computational Photography
I gave a guest lecture on Linear Algebra and MATLAB Tutorial


Spring 2014

 



ECE 598PM: Computational Inference and Learning 
Instructor: Pierre Moulin

Materials: 

  • Core concepts: entropy, divergence, Bayes inference, maximum likelihood principle, Maximum A Priori (MAP) estimation, Minimum Mean Squared Error (MMSE) estimation
  • Stochastic approximation, Monte Carlo methods and importance sampling
  • Bayesian recursive estimation using particle filtering
  • Parameter estimation via Expectation Maximization (EM) algorithm
  • Alternating minimization algorithms, RANSAC
  • Variational inference methods and mean-field techniques 
  • Graphical models, approximate inference and message passing
  • Compressive sensing, low rank matrix recovery and completion
  • Approximate nearest-neighbor in high dimensions; hashing
  • Distributed algorithms
Resources:

Fall 2013

 



NEUR 453: Cognitive Neuroscience of Vision
Instructor: Diane Beck

Materials: 

  • Color Vision
  • Form amd Motion
  • Object Recognition
  • Face Recognition
  • Faces, Places, Bodies and Tools
  •  Visual Attention 
  • Neglect
Resources:

Spring 2013
 
ECE 513: Vector Space Signal Processing
Instructor: Yoram Bresler


Materials: 
  • Inverse problems and matrix theory
  • General linear vector spaces
  • Hilbert space of random variables 
  • Applications in signal processing
Resources:
  • Lecture notes: [Link]

Fall 2012
    CS 473 Fundamental Algorithms
    Instructor: 
    Jeff Erickson

    Materials:
    • Recursion, Dynamic programming, Randomized algorithm, Amortized analysis, Graph algorithms, Maxflow/Mincut, NP hardness
    Resources: 
    • Useful resources collected by Jeff [Webpage]
    • Lecture recordings [Videos]
     
    IE 521: Convex Optimization 
    Instructor: 
    Angelia Nedich

    Materials
    • Convex sets and functions
    • Convex optimization problems
    • Duality theory and KKT condition
    • First-order methods
    • Interior-point methods, Stochastic optimization
    Resources: 

    Spring 2012
      ECE 544NA: Statistical Learning and Pattern Recognition  
      Instructor: Pierre Moulin

      Materials:
      • Overview
        • Basic concepts, Bayes theory, supervised learning, classi.cation
      • Model Assessment, Selection, and Inference
        • Model complexity, statistical and information-theoretic metrics, Bayesian approach, complexity regularization
      • Sparse Methods 
        • Dimensionality reduction, L1 regularization, lasso, group lasso, sparse coding, sparse Principal Components Analysis, low-rank matrix approximation
      • Graphical Models
        • Basic models, Bayesian networks, inference on graphs
      Resources:
       
      Math 412: Graph Theory
      Instructor: Alexandr V. Kostochka

      Materials:
      • Fundamentals
      • Trees and distance
      • Matching and factors
      • Connectivity and paths
      • Graph coloring
      • Planar graphs
      • Edges and cycles
      Resources: 

      Fall 2011
       


      ECE 547: Topics in Image Processing 
      Instructor: Thomas S. Huang

      Materials:
      • 2D Fourier transform
      • Image/video coding
      • 3D reconstruction
      • Image restoration
      • Order-statistics filter and mathematical morphology
      • Texture, shape and structure
      • Geometric optics
      Resources:

      ECE 563: 
      Information Theory 

      Instructor: Olgica Milenkovic

      Materials:
      • Entropy, Relative Entropy, and Mutual Information.
      • Asymptotic Equipartition Property.
      • Data Compression.
      • Channel Capacity.
      • Differential Entropy.
      • Gaussian Channel.
      • Information Theory and Statistics.
      • Universal Source Coding.

      Spring 2011

       
       ECE 561: Detection and Estimation Theory 

      Instructor: Pierre Moulin

      Materials:
      • Elements of Hypothesis testing
      • Signal detection in discrete time
      • Elements of parameter estimation
      • Elements of signal estimation
      Resources:

      ECE 549: Computer Vision 

      Instructor: Derek Hoiem

      Materials:
      • Image formation and basic processing
      • Grouping and fitting
      • Recognition
      • Multiple views and motion
      • Advanced topics
      Resources:

      Fall 2010


      ECE 534: 
      Random Process 

      Instructor: Pierre Moulin

      Materials:

      Resources:

      [lecture note] [midterm 1] [midterm 2] [final exam] [homework set]




      CS 498: 
      Computational Photography (Derek Hoiem)


      www.hitwebcounter.com

      Comments