Chengjiang Long 龙成江[CV]

Ph.D.
Computer Vision Researcher/Senior R&D Engineer at Kitware Inc.
Adjunct Professor at Rensselaer Polytechnic Institute (RPI)

Email: chengjiang.long@kitware.com




 

Description: picture










 

ECSE-6110 Pattern Recognition

Term: Spring 2018 
Instructor:
Dr. Chengjiang Long
Time:
Tuesday and Friday, 2:00pm – 3:20pm
Building/Room: JEC 4107 
Office Hour
: Tuesday and Friday 3:20pm—4:00pm by appointment
Office Hour Location: JEC 6045
Course Assistant
: Il-Young Son
Course Website
: www.chengjianglong.com/teachings.html

Course Overview:
This course will give an introduction to the large and diverse field of pattern recognition. Topics include Introduction to Pattern Recognition, Probability theory and Linear algebra review, Basic graph concepts and Belief Network, Bayesian decision theory, Maximum-likelihood estimation, Bayesian methods, Nonparametric techniques, Principal Component Analysis, Fisher Discrimination, Linear models for regression, Linear models for classification and support vector machines, Bagging, Random Forests and Boosting, Introduction to Neural Networks and Multilayer Neural Network, Introduction to deep learning: Deep Feedforward Network and Convolutional Neural Network, Unsupervised Learning and clustering. On completion of the course, students should be sufficiently familiar with the formal theoretical structure, notation, and vocabulary of pattern recognition to be able to read and understand current technical literature. They will also have experience in the design and implementation of pattern recognition systems and be able to use those methods to program and solve practical problems.

Prerequisites:
Basic probability and statistics, some linear algebra, basic programming skills. Working familiarity with Matlab, Python, Java or C/C++ will be expected.  

Text Books:
Rechard O. Duda, Peter E. Hart, and David G. Stork, “ Pattern Classification”, 2nd Edition, John Wiley, 2001. 

Auxiliary Text Books:
Trevor Hastie, Robert Tibshirani and Jerome Friedman, “ The Elements of Statistical Learning”, 2nd Edition, Springer, 2009. 
David Barber, “ Bayesian Reasoning and Machine Learning”, Cambridge University Press, 2012. 
Ian Goodfellow and Yoshua Beio and Aaron Courville, “ Deep Learning”, MIT Press, 2016. 

Grading:
The students will be graded based on course participation (5%), four homework assignments (20%, some of them need programming), a midterm exam (20%), a final exam (20%), and a final project/presentation (35%). 
Final grade: A+(>=97), A(>=92), A-(>=90), B+(>=87), B(>=82), B-(>=80), C+(>=77), C(>=72), C-(>=70), D+(>=67), D(>=62), D-(>=60) and F (<60).  

Late submission policy:
Exponential penalty -- late for one day loses half, two day loses another half of the remaining, and so on and so forth. 

Topics:

  • Introduction to Pattern Recognition.
  • Probability theory and Linear algebra review.
  • Basic graph concepts and Belief Network.
  • Bayesian decision theory.
  • Maximum-likelihood estimation.
  • Bayesian methods.
  • Nonparametric techniques.
  • Dimension reduction: Principal Component Analysis;
  • Fisher Discrimination.
  • Linear models for regression.
  • Linear models for classification and support vector machines.
  • Bagging, Random Forests and Boosting.
  • Introduction to Neural Networks and Multilayer Neural Network
  • Introduction to deep learning: Deep Feedforward Network and Convolutional Neural Network.
  • Unsupervised learning and clustering.


Course schedule:

ClassDateTopicReadingHomework/ProjectSlides
01/16/2018Short class
11/19/2018Introduction to Pattern RecognitionDuda Ch. 1Lecture_1
21/23/2018Probability theory and Linear algebra reviewDuda Ch. 2Lecture_2
31/26/2018Bayesian decision theoryDuda Ch. 2.3-4Lecture_3
41/30/2018Bayesian decision theory and Max Likelihood EstimationDuda Ch. 2.5-6, 3.1-2, Barber Ch 8Lecture_4
52/2/2018 Bayesian Esitmation Methods and Naive Bayes ClassifierDuda Ch. 3.3-5, Barber Ch 13HW 1 assignedLecture_5
62/6/2018Non-Parametric Methods – Parzen EstimationDuda Ch. 4.1-3Lecture_6
72/9/2018Non-Parametric Methods – KNNDuda Ch. 4.4-5HW 1 dueLecture_7
82/13/2018Dimensionality – PCA and Fisher DiscriminationDuda Ch. 3.7-8, Barber Ch. 15-16HW 2 assignedLecture_8
92/16/2018Linear Discriminant Functions (1)Duda Ch. 5.1-2, Barber Ch. 17Lecture_9
2/20/2018No class with the schedule of the President's Day
102/23/2018Linear Discriminant Functions (2)Duda Ch. 5.3-7, Barber Ch. 17, HTF Ch. 12 HW 2 dueLecture_10
112/27/2018Support Vector Machine Duda Ch. 5.8-9HW 3 assignedLecture_11
3/2/2018No class due to the snow storm
123/6/2018Midterm Exam ReviewLecture_12
133/9/2018Midterm examMidterm exam and HW 3 due
3/13/2018Spring break
3/16/2018Spring break
143/20/2018Bagging; Random Forests; Boosting (1)HTF Ch. 10 and 15Lecture_13
153/23/2018Bagging; Random Forests; Boosting (2)HTF Ch. 10 and 15Project Proposal SubmissionLecture_14
163/27/2018Basic graph concepts, Belief Network and Hidden Markov ModelsDuda Ch. 2.5-6, 3.10Lecture_15
173/30/2018Final Project Proposal PresentationDuda Ch. 6.1Final Project Proposal Presentation
184/3/2018Introduction to Nueral Networks, Multilayer Neural Networks and Back-propagationDuda Ch. 6.2-8Lecture_16
194/6/2018Convolutional Neural NetworksIan Ch. 9Lecture_17
204/10/2018Case Study on ConvNets and Train Neural NetworksIan Ch. 6-9Lecture_18
214/13/2018Concept of Neural NetworksIan Ch. 6-9Lecture_19
224/17/2018RegressionDuda Ch. 6, Barber Ch. 17, HTF Ch. 3HW 4 assignedLecture_20
234/20/2018Unsupervised learning and Clustering AlgorithmsDuda Ch. 10.1-14, HTF Ch. 14Lecture_21
244/24/2018Gaussian Mixture Model and EM algorithmDuda Ch. 10.9-14, HTF Ch. 14.3Lecture_22
254/27/2018Final Exam ReviewHW4 dueLecture_23
265/1/2018Presentation of Project Reports to ClassFinal Project Presentation
275/7/2018Final examFinal exam








Description: Free Hit Counter
© By Chengjiang Long since Mar 21, 2012.