User Tools

Site Tools


start

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision
Previous revision
start [2017/04/17 13:30]
127.0.0.1 external edit
start [2018/02/15 17:19] (current)
anderson [February]
Line 1: Line 1:
 ====== Schedule ====== ====== Schedule ======
  
-/* 
-Follow this link to view all [[https://​echo.colostate.edu/​ess/​portal/​section/​37e 
-115b6-e68b-4318-89ff-d1ecf025c0b9|lecture videos]]. 
-*/ 
 ===== Announcements ===== ===== Announcements =====
  
-**March 20:** A4grader.tar linked to on the A4 web page has been updated. ​It longer checks for QDA-related functions.+**February 13:** Assignment A2 has been updated ​and now contains link to A2grader.tar.
  
-**March 18:** There will be no lecture class on Wednesday, March 22nd.  Chuck'​s office hours on March 22nd are cancelled. +Lecture videos are available at this [[https://colostate.instructure.com/courses/61937/external_tools/2755|CS445 video recordings site]].
- +
-Lecture videos are available at this [[https://echo.colostate.edu/ess/portal/section/a5759ae3-82dc-43df-b515-dd944a6c4976|CS480 video recordings site]].+
  
  
Line 18: Line 12:
 |< 100% 10% 20% 30% 20% 20%  >| |< 100% 10% 20% 30% 20% 20%  >|
 ^  Week      ^  Topic      ^  Material ​ ^  Reading ​         ^  Assignments ​ ^ ^  Week      ^  Topic      ^  Material ​ ^  Reading ​         ^  Assignments ​ ^
-| Week 1:\\  Jan 17 - Jan 20    | Overview. Intro to machine learning. Python. ​ | [[http://​nbviewer.ipython.org/​url/​www.cs.colostate.edu/​~anderson/​cs480/​notebooks/​01 Course Overview.ipynb|01 Course Overview]],\\  [[http://​nbviewer.ipython.org/​url/​www.cs.colostate.edu/​~anderson/​cs480/​notebooks/​02 Matrices and Plotting.ipynb|02 Matrices and Plotting]] | [[http://​www.nytimes.com/2016/12/14/​magazine/​the-great-ai-awakening.html?​_r=0|The Great A.I. Awakening]], by Gideon Lewis-Krause, NYT, Dec 14, 2016.\\ Section 1 of   [[http://​www.scipy-lectures.org|Scipy Lecture Notes]]      ​| ​ |  +| Week 1:\\  Jan 16 - Jan 19    | Overview. Intro to machine learning. Python. ​ | [[http://​nbviewer.ipython.org/​url/​www.cs.colostate.edu/​~anderson/​cs445/​notebooks/​01 Course Overview.ipynb|01 Course Overview]]\\ [[http://​nbviewer.ipython.org/​url/​www.cs.colostate.edu/​~anderson/​cs445/​notebooks/​02 Matrices and Plotting.ipynb|02 Matrices and Plotting]] ​ | [[http://​www.labri.fr/perso/nrougier/from-python-to-numpy/|From Python to Numpy]], Chapters 1 2\\ [[http://​www.deeplearningbook.org/|Deep Learning]], Chapters 1 - 5.1.4  | 
-| Week 2:\\ Jan 23 - Jan 27    ​| ​Probability distributions ​and regression. ​   ​| [[http://​nbviewer.ipython.org/​url/​www.cs.colostate.edu/​~anderson/​cs480/​notebooks/​03 Linear Regression.ipynb|03 Linear Regression]],\\ [[http://​nbviewer.ipython.org/​url/​www.cs.colostate.edu/​~anderson/​cs480/​notebooks/​04 ​Gaussian Distributions.ipynb|04 ​Gaussian Distributions]]    |   ​| ​   +| Week 2:\\ Jan 22 - Jan 26    ​| ​Fitting linear models to data as a direct matrix calculation, ​and incrementally using stochastic gradient descent (SGD)  ​| [[http://​nbviewer.ipython.org/​url/​www.cs.colostate.edu/​~anderson/​cs445/​notebooks/​03 Linear Regression.ipynb|03 Linear Regression]]\\ [[http://​nbviewer.ipython.org/​url/​www.cs.colostate.edu/​~anderson/​cs445/​notebooks/​04 ​Linear Regression Using Stochastic Gradient Descent (SGD).ipynb|04 ​Linear Regression Using Stochastic Gradient Descent (SGD)]]  | 
 +| Week 3:\\ Jan 29 - Feb 2    ​| ​Ridge regression. Data partitioning. ​ Probabilistic Linear Regression. Regression with fixed nonlinearities. ​  | [[http://​nbviewer.ipython.org/​url/​www.cs.colostate.edu/​~anderson/​cs445/​notebooks/​05 Linear Ridge Regression and Data Partitioning.ipynb|05 Linear Ridge Regression and Data Partitioning]]\\ [[http://​nbviewer.ipython.org/​url/​www.cs.colostate.edu/​~anderson/​cs445/​notebooks/​06 Probabilistic Linear Regression.ipynb|06 Probabilistic Linear Regression]]\\ [[http://​nbviewer.ipython.org/​url/​www.cs.colostate.edu/​~anderson/​cs445/​notebooks/​07 Linear Regression with Fixed Nonlinear Features.ipynb|07 Linear Regression with Fixed Nonlinear Features]] ​  ​|[[http://​www.deeplearningbook.org/​|Deep Learning]], Section 7.3\\  [[http://​www.nytimes.com/​2016/​12/​14/​magazine/​the-great-ai-awakening.html?​_r=0|The Great A.I. Awakening]],​ by Gideon Lewis-Krause,​ NYT, Dec 14, 2016.  | [[http://​nbviewer.ipython.org/​url/​www.cs.colostate.edu/​~anderson/​cs445/​notebooks/​A1 Linear Regression.ipynb|A1 Linear Regression]] due Wednesday, January 31, 10:00 PM.  Here are some [[http://​www.cs.colostate.edu/​~anderson/​cs445/​goodSolutions|good solutions.]] ​ |
  
 ===== February ===== ===== February =====
Line 26: Line 20:
 |< 100% 10% 20% 30% 20% 20%  >| |< 100% 10% 20% 30% 20% 20%  >|
 ^  Week      ^  Topic      ^  Material ​ ^  Reading ​         ^  Assignments ​ ^ ^  Week      ^  Topic      ^  Material ​ ^  Reading ​         ^  Assignments ​ ^
-| Week 3:\\ Jan 30 - Feb 3      ​Probabilistic Linear Regression. Ridge regression. Data partitioning. On-line, incremental ​regression. ​ | [[http://​nbviewer.ipython.org/​url/​www.cs.colostate.edu/​~anderson/​cs480/notebooks/05 Fitting Gaussians.ipynb|05 Fitting Gaussians]],\\ [[http://​nbviewer.ipython.org/​url/​www.cs.colostate.edu/​~anderson/​cs480/notebooks/06 Probabilistic Linear Regression.ipynb|06 Probabilistic Linear Regression]],\\ [[http://​nbviewer.ipython.org/​url/​www.cs.colostate.edu/​~anderson/​cs480/​notebooks/​07 Linear Ridge Regression and Data Partitioning.ipynb|07 Linear Ridge Regression and Data Partitioning]],​\\ ​[[http://​nbviewer.ipython.org/​url/www.cs.colostate.edu/​~anderson/​cs480/​notebooks/​08 Sample-by-Sample Linear Regression.ipynb|08 Sample-by-Sample Linear Regression]] ​   | | [[http://​nbviewer.ipython.org/url/​www.cs.colostate.edu/​~anderson/​cs480/​notebooks/​A1 Linear Regression.ipynb|A1 Linear Regression]] due MondayJanuary 30th at 10:00 PM  ​  ​ +| Week 4:\\ Feb 5 - Feb 9   Introduction to nonlinear ​regression ​with neural networks.  | [[http://​nbviewer.ipython.org/​url/​www.cs.colostate.edu/​~anderson/​cs445/notebooks/08 Stochastic Gradient Descent with Parameterized Activation Function.ipynb|08 Stochastic Gradient Descent with Parameterized Activation Function]]\\ [[http://​nbviewer.ipython.org/​url/​www.cs.colostate.edu/​~anderson/​cs445/notebooks/09 Scaled Conjugate Gradient for Training Neural Networks.ipynb|09 Scaled Conjugate Gradient for Training Neural Networks]]  | [[http://​www.deeplearningbook.org/|Deep Learning]], Chapter 6 (skip 6.2)  ​
-| Week 4:\\ Feb - Feb 10   Regression with fixed nonlinearities. Nonlinear regression with neural networks.\\ ​Feb 10: Guest Speaker [[https://​www.linkedin.com/in/​mike-morain-07223710|Mike Morain]]Machine Learning at Amazon, UK.  | [[http://​nbviewer.ipython.org/​url/​www.cs.colostate.edu/​~anderson/​cs480/​notebooks/​09 Linear Regression with Fixed Nonlinear Features.ipynb|09 Linear Regression with Fixed Nonlinear Features]],​\\ [[http://​nbviewer.ipython.org/​url/​www.cs.colostate.edu/​~anderson/​cs480/​notebooks/​10 Nonlinear Regression with Neural Networks.ipynb|10 Nonlinear Regression with Neural Networks]] ​  ​|   ​| ​   +| Week 5:\\ Feb 12 - Feb 16  ​<color red>​Lectures on Feb 12th and 14th are canceled.</color> ​ Fridaymore neural networks ​ | [[http://​nbviewer.ipython.org/​url/​www.cs.colostate.edu/​~anderson/​cs445/​notebooks/​10 ​More Nonlinear Regression with Neural Networks.ipynb|10 ​More Nonlinear Regression with Neural Networks]] ​ 
-| Week 5:\\ Feb 13 - Feb 17   | Neural Networks ​ ​| ​[[http://​nbviewer.ipython.org/​url/​www.cs.colostate.edu/​~anderson/​cs480/​notebooks/​10 Nonlinear Regression with Neural Networks.ipynb|10 Nonlinear Regression with Neural Networks]],​\\ ​ [[http://​nbviewer.ipython.org/​url/​www.cs.colostate.edu/​~anderson/​cs480/​notebooks/​11 More Nonlinear Regression with Neural Networks.ipynb|11 More Nonlinear Regression with Neural Networks]] ​  | | [[http://​nbviewer.ipython.org/​url/​www.cs.colostate.edu/​~anderson/​cs480/​notebooks/​A2 ​Ridge Regression ​with K-Fold Cross-Validation.ipynb|A2 ​Ridge Regression ​with K-Fold Cross-Validation]] due Monday, February ​13th at 10:00 PM.\\ Here are [[A2-good-ones|examples of good A2 reports.]] ​ | +| Week 6:\\ Feb 19 - Feb 23  ​| ​AutoencodersRecurrent neural networks.  | | | [[http://​nbviewer.ipython.org/​url/​www.cs.colostate.edu/​~anderson/​cs445/​notebooks/​A2 ​Neural Network ​Regression.ipynb|A2 ​Neural Network ​Regression]] due Tuesday, February ​20, 10:00 PM  | 
-| Week 6:\\ Feb 20 - Feb 24   | Neural Networks. Autoencoders. Guest lectures by our GTA, Jake Lee.  | [[http://​nbviewer.ipython.org/​url/​www.cs.colostate.edu/​~anderson/​cs480/​notebooks/​12 Autoencoder Neural Networks.ipynb|12 Autoencoder Neural Networks]] ​  | |   ​| ​   ​ +| Week 7:\\ Feb 26 - Mar  | Classification. ​LDA and QDAK-Nearest Neighbors.  |
-| Week 7:\\ Feb 27 - Mar 3   | Recurrent Neural Networks.\\ Conditional probabilities and Bayes Rule  ​| ​[[http://​nbviewer.ipython.org/​url/​www.cs.colostate.edu/​~anderson/​cs480/​notebooks/​13 Recurrent Neural Networks.ipynb|13 Recurrent Neural Networks]]\\ [[http://​nbviewer.ipython.org/​url/​www.cs.colostate.edu/​~anderson/​cs480/​notebooks/​14 Introduction to Classification.ipynb|14 Introduction to Classification]] ​  | | [[http://​nbviewer.ipython.org/​url/​www.cs.colostate.edu/​~anderson/​cs480/​notebooks/​A3 Neural Network Regression.ipynb|A3 Neural Network Regression]] due Wednesday, March 1st at 10:00 PM.\\ Here are [[A3-good-ones|examples of good A3 reports.]]  ​| ​   +
  
 ===== March ===== ===== March =====
Line 36: Line 29:
 |< 100% 10% 20% 30% 20% 20%  >| |< 100% 10% 20% 30% 20% 20%  >|
 ^  Week      ^  Topic      ^  Material ​ ^  Reading ​         ^  Assignments ​ ^ ^  Week      ^  Topic      ^  Material ​ ^  Reading ​         ^  Assignments ​ ^
-| Week 8:\\ Mar - Mar 10   | Classification. LDA and QDA. Linear and Nonlinear Logistic Regression. ​ | [[http://​nbviewer.ipython.org/​url/​www.cs.colostate.edu/​~anderson/​cs480/​notebooks/​15 ​Classification with Linear Logistic Regression.ipynb|15 Classification with Linear Logistic Regression]]\\ [[http://​nbviewer.ipython.org/​url/​www.cs.colostate.edu/​~anderson/​cs480/​notebooks/​16 Classification with Nonlinear Logistic Regression Using Neural Networks.ipynb|16 Classification with Nonlinear Logistic Regression Using Neural Networks]] ​  ​| ​|  | +| Week 8:\\ Mar - Mar   | Classification with Neural Networks ​ | 
-| Week 9:\\ Mar 20, Mar 24\\ <color red>No class March 22nd.</​color>  ​Classification. ​Analysis of Trained Networks. Bottleneck Networks. Hand-Drawn ​Digit Classification. ​ | [[http://​nbviewer.ipython.org/​url/​www.cs.colostate.edu/​~anderson/​cs480/​notebooks/​17 Analysis of Neural Network Classifiers and Bottleneck Networks.ipynb|17 Analysis of Neural Network Classifiers and Bottleneck Networks]]\\ [[http://​nbviewer.ipython.org/​url/​www.cs.colostate.edu/​~anderson/​cs480/​notebooks/​18 ​Digits.ipynb|18 Digits]] ​ |  |  | +|  Mar 12 - Mar 16   ​Spring Break  | 
-| Week 10:\\ Mar 27 - Mar 31  | Convolutional Neural Networks. Reinforcement Learning. ​ | [[http://​nbviewer.ipython.org/​url/​www.cs.colostate.edu/​~anderson/​cs480/​notebooks/​19 Convolutional Neural Networks.ipynb|19 Convolutional Neural Networks]]\\ [[http://​nbviewer.ipython.org/​url/​www.cs.colostate.edu/​~anderson/​cs480/​notebooks/​20 Introduction to Reinforcement Learning.ipynb|20 Introduction to Reinforcement Learning]] ​ | [[http://​incompleteideas.net/​sutton/​book/​the-book-2nd.html| Reinforcement Learning: An Introduction]],​ by Richard Sutton and Andrew Barto. 2nd edition draft. On-line and free.  |  ​| ​+| Week 9:\\ Mar 19 - Mar 23 | Analysis of Trained Networks. Bottleneck Networks. ​Classifying ​Hand-Drawn Digits. ​ | 
 +| Week 10:\\ Mar 26 - Mar 30  | Convolutional Neural Networks ​ |
  
 ===== April ===== ===== April =====
Line 44: Line 38:
 |< 100% 10% 20% 30% 20% 20%  >| |< 100% 10% 20% 30% 20% 20%  >|
 ^  Week      ^  Topic      ^  Material ​ ^  Reading ​         ^  Assignments ​ ^ ^  Week      ^  Topic      ^  Material ​ ^  Reading ​         ^  Assignments ​ ^
-| Week 11:\\ Apr - Apr   | Reinforcement Learning. ​ ​Two-player games. ​ | [[http://​nbviewer.ipython.org/​url/​www.cs.colostate.edu/​~anderson/​cs480/​notebooks/​21 Reinforcement Learning for Two Player ​Games.ipynb|21 Reinforcement Learning for Two Player Games]] ​  | [[http://​incompleteideas.net/​sutton/​book/​the-book-2nd.html| Reinforcement Learning: An Introduction]],​ by Richard Sutton and Andrew Barto. 2nd edition draft. On-line and free.  |  [[http://​nbviewer.ipython.org/​url/​www.cs.colostate.edu/​~anderson/​cs480/​notebooks/​A4 Classification with LDA and Logistic Regression.ipynb|A4 Classification with LDA and Logistic Regression]] due Wednesday, April 5th at 10:00 PM.\\ Here are [[A4-good-ones|examples of good A4 reports.]]\\ [[http://​nbviewer.ipython.org/​url/​www.cs.colostate.edu/​~anderson/​cs480/​notebooks/​Project Proposal.ipynb|Project Proposal]] due Friday, April 7th at 10:00 PM.  | +| Week 11:\\ Apr - Apr   | Reinforcement Learning. Games using Tabular Q functions.  | 
-| Week 12:\\ Apr 10 - Apr 14  ​| ​Neural networks as Q functions. ​ | [[http://​nbviewer.ipython.org/​url/​www.cs.colostate.edu/​~anderson/​cs480/​notebooks/​22 ​Reinforcement Learning ​with Neural ​Network ​as Q Function.ipynb|22 Reinforcement Learning with Neural Network as Q Function]]\\ [[http://​www.cs.colostate.edu/​~anderson/​cs480/​notebooks/​17pole.odp|Faster RL by Pre-training]] ​ | [[https://​www.technologyreview.com/​s/​604087/​the-dark-secret-at-the-heart-of-ai/​|The Dark Secret at the Heart of AI]]\\ [[https://​flipboard.com/​@flipboard/​flip.it%2FVaiyLS-the-tiny-changes-that-can-cause-ai-to-f/​f-32bef81237%2Fbbc.com|The Tiny Changes That Can Cause AI to Fail]] ​ |  | +| Week 12:\\ Apr - Apr 13  | Reinforcement Learning ​using Neural ​Networks ​as Q functions.  | 
-| Week 13:\\ Apr 17 - Apr 21  | Unsupervised Learning. ​Dimensionality reduction. ​ | [[http://​nbviewer.ipython.org/​url/​www.cs.colostate.edu/​~anderson/​cs480/​notebooks/​23 Linear ​Dimensionality Reduction.ipynb|23 Linear Dimensionality Reduction]]\\ ​ [[http://​nbviewer.ipython.org/​url/​www.cs.colostate.edu/​~anderson/​cs480/​notebooks/​24 Nonlinear Dimensionality Reduction with Digits Example.ipynb|24 Nonlinear Dimensionality Reduction with Digits Example]]\\ [[http://​nbviewer.ipython.org/​url/​www.cs.colostate.edu/​~anderson/​cs480/​notebooks/​25 K-Means ​Clustering.ipynb|25 K-Means Clustering]] ​  ​| ​ ​| ​ +| Week 13:\\ Apr 16 - Apr 20  | Unsupervised Learning. Dimensionality Reduction. ​ Clustering. ​ || 
-| Week 14:\\ Apr 24 - Apr 28  ​|  ​|  |  | [[http://​nbviewer.ipython.org/​url/​www.cs.colostate.edu/​~anderson/​cs480/​notebooks/​A5 Control a Marble with Reinforcement Learning.ipynb|A5 Control a Marble with Reinforcement Learning]] due Monday, April 24th at 10:00 PM. |+| Week 14:\\ Apr 23 - Apr 27  ​| ​Support Vector Machines. ​ |
  
 ===== May ===== ===== May =====
Line 53: Line 47:
 |< 100% 10% 20% 30% 20% 20%  >| |< 100% 10% 20% 30% 20% 20%  >|
 ^  Week      ^  Topic      ^  Material ​ ^  Reading ​         ^  Assignments ​ ^ ^  Week      ^  Topic      ^  Material ​ ^  Reading ​         ^  Assignments ​ ^
-| Week 15:\\ May 1 - May 5   ​| ​  ​| ​ ​|  ​ | +| Week 15:\\ Apr 30 - May  ​| ​Ensembles. ​ Other topics. ​ | 
-Finals Week:​\\ ​May - May 11  |   ​| ​ |  ​| ​ Final project due Tuesday, May 9, 10:00 PM.  Details on report requirements will be posted here soon.   |+| May - May 10  ​| ​ Final Exams  ​| ​
  
  
  
start.1492457424.txt.gz · Last modified: 2017/04/17 13:30 by 127.0.0.1