CS 678 - Advanced Machine Learning and Neural Networks

Syllabus

 

Winter 2017, TuTh 1:35-2:50pm, 134 TMCB

Professor: Tony Martinez, 3326 TMCB, x6464, http://axon.cs.byu.edu/~martinez

martinez@cs.byu.edu

Office Hours: by appointment

 

 Course Website: http://axon.cs.byu.edu/~martinez/classes/678/

 

Goals:  Continuation in the study of the philosophy, utility, and models of machine learning, such that students are able to propose original research with potential follow-up in a graduate research program.  Expand the creativity of the students in all aspects of computing.

 

Prerequisites:  CS 478 (Introduction to Neural Networks and Machine Learning)

 

Text:  Papers available from the class website.   Also, we will read a few chapters from Machine Learning by Tom Mitchell.  You are expected to read the assigned literature before and optionally after the scheduled lecture.

 

Assignments:  We will have three projects during the semester allowing you to build and experiment with some new machine learning models.  You will also present a model of your choice to the class.  There will be a few small homeworks.  There will be a midterm and a final.

 

Grading (~):

Homeworks

7%

Your Model Readings

6%

Model of your choice Project

25%

Deep Learning Project

18%

Midterm

22%

Final

22%

 

Grading is on a curve and some amount of subjectivity is allowed for attendance, participation, perceived effort, etc.  If you think, you'll be all right.  The mid-term exam will be in the testing center Feb. 27-Mar 1 and the final exam will be in class on Monday, April 24 from 2:30pm-5:30pm.

 

Late assignments:  Assignments are expected on time (hard copy at the beginning of class on the due date).  Late papers will be marked off at 5%/school day late up to a maximum of 50% off.  However, if you have any unusual circumstances (sick, out of town, unique from what all the other students have, etc.), which you inform me of, then I will not take off any late points.  Nothing can be accepted after the last day of class instruction.

 

Topics (Order is approximate):

      Von Neumann bottleneck/neurobiology primer

      Advanced Backpropagation Concepts

o   On-line vs. Batch

o   Classification Based Learning

o   Other (Higher Order nets, Ontogenic Nets)

      Hopfield Networks

      Boltzmann Machines

      Recurrent Neural Networks (Elman Nets, BPTT, RTRL)

      Deep Learning

      Support Vector Machines (with brief review of Quadric/Higher Order Machines and RBF networks)

      HMMs (with Baum Welch Learning - EM algorithm), with detailed speech recognition as the example platform

      MULTCONS, Hopfield Extensions

      Rule Based Learning (Sequential Covering, CN2)

      Semi-Supervised Learning

 

Next Group of Topics as Time Allows (Based on Needs):

      Ensembles (Variations, BMC vs BMA, Oracle Learning, etc.)

      Bias: Interesting/computable problems, Bias-Variance Decomposition

      ADIB (Automatic Discovery of Inductive Bias)/Latest lab Research

      Structured Prediction

      Manifold Learning/Non-Linear Dimensionality Reduction

      Record Linkage/Family History Directions

      Meta-Learning

      Feature Selection

      Computational Learning Theory

      Transfer Learning

      Transduction

      Reinforcement Learning

      Other Unsupervised Learning Models

 

Topics and Readings Schedule:

Assignments:

Readings Presentations Schedule:

Project Presentations Schedule:          

University and Other Items: