User Tools

Site Tools


schedule-spring18

Differences

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

Link to this comparison view

schedule-spring18 [2019/01/03 15:03] (current)
Line 1: Line 1:
 +====== Schedule ======
 +
 +===== Announcements =====
 +
 +
 +Lecture videos are available at this [[https://​colostate.instructure.com/​courses/​61937/​external_tools/​2755|CS445 video recordings site]].
 +
 +
 +===== January =====
 +
 +|< 100% 10% 20% 30% 20% 20%  >|
 +^  Week      ^  Topic      ^  Material ​ ^  Reading ​         ^  Assignments ​ ^
 +| 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 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 =====
 +
 +|< 100% 10% 20% 30% 20% 20%  >|
 +^  Week      ^  Topic      ^  Material ​ ^  Reading ​         ^  Assignments ​ ^
 +| 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 5:\\ Feb 12 - Feb 16  | <color red>​Lectures on Feb 12th and 14th are canceled.</​color> ​ Friday, more 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 6:\\ Feb 19 - Feb 23  | Autoencoders. Activation functions. ​ | [[http://​nbviewer.ipython.org/​url/​www.cs.colostate.edu/​~anderson/​cs445/​notebooks/​11 Autoencoder Neural Networks.ipynb|11 Autoencoder Neural Networks]] ​ | [[https://​arxiv.org/​pdf/​1710.05941.pdf|Searching for Activation Functions]],​ by Ramachandran,​ Zoph, and Le  | [[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. Here are some [[http://​www.cs.colostate.edu/​~anderson/​cs445/​goodSolutions|good solutions.]] ​ |
 +| Week 7:\\ Feb 26 - Mar 2  | Classification. LDA and QDA. K-Nearest Neighbors. ​ | [[http://​nbviewer.ipython.org/​url/​www.cs.colostate.edu/​~anderson/​cs445/​notebooks/​12 Introduction to Classification.ipynb|12 Introduction to Classification]] <color red>​(qdalda.py updated March 20)</​color>​\\ [[http://​nbviewer.ipython.org/​url/​www.cs.colostate.edu/​~anderson/​cs445/​notebooks/​13 Gaussian Distributions.ipynb|13 Gaussian Distributions]] ​  ​| ​ |[[http://​nbviewer.ipython.org/​url/​www.cs.colostate.edu/​~anderson/​cs445/​notebooks/​A3 Activation Functions.ipynb|A3 Activation Functions]] due Thursday, March 1, 10:00 PM.  Here are some [[http://​www.cs.colostate.edu/​~anderson/​cs445/​goodSolutions|good solutions.]] ​ |
 +
 +===== March =====
 +
 +|< 100% 10% 20% 30% 20% 20%  >|
 +^  Week      ^  Topic      ^  Material ​ ^  Reading ​         ^  Assignments ​ ^
 +| Week 8:\\ Mar 5 - Mar 9   | Classification with Neural Networks ​ | [[http://​nbviewer.ipython.org/​url/​www.cs.colostate.edu/​~anderson/​cs445/​notebooks/​14 Classification with Linear Logistic Regression.ipynb|14 Classification with Linear Logistic Regression]]\\ [[http://​nbviewer.ipython.org/​url/​www.cs.colostate.edu/​~anderson/​cs445/​notebooks/​15 Classification with Nonlinear Logistic Regression Using Neural Networks.ipynb|15 Classification with Nonlinear Logistic Regression Using Neural Networks]] ​ <color red>​(updated March 18)</​color>​\\ [[http://​nbviewer.ipython.org/​url/​www.cs.colostate.edu/​~anderson/​cs445/​notebooks/​16 Introduction to Pytorch.ipynb|16 Introduction to Pytorch]] ​ |
 +|  Mar 12 - Mar 16  |  Spring Break  |
 +| Week 9:\\ Mar 19 - Mar 23 | Analysis of Trained Networks. Bottleneck Networks. Classifying Hand-Drawn Digits. ​ | [[http://​nbviewer.ipython.org/​url/​www.cs.colostate.edu/​~anderson/​cs445/​notebooks/​17 Analysis of Neural Network Classifiers and Bottleneck Networks.ipynb|17 Analysis of Neural Network Classifiers and Bottleneck Networks]] ​ <color red>​(updated March 19, 10:20 AM)</​color>​\\ [[http://​nbviewer.ipython.org/​url/​www.cs.colostate.edu/​~anderson/​cs445/​notebooks/​18 Dealing with Time Series by Time-Embedding.ipynb|18 Dealing with Time Series by Time-Embedding]]\\ [[http://​nbviewer.ipython.org/​url/​www.cs.colostate.edu/​~anderson/​cs445/​notebooks/​19 Recurrent Neural Networks.ipynb|19 Recurrent Neural Networks]] ​ | | |
 +| Week 10:\\ Mar 26 - Mar 30  | Convolutional Neural Networks ​ | [[http://​nbviewer.ipython.org/​url/​www.cs.colostate.edu/​~anderson/​cs445/​notebooks/​20 Classifying Hand-drawn Digits.ipynb|20 Classifying Hand-drawn Digits]]\\ [[http://​nbviewer.ipython.org/​url/​www.cs.colostate.edu/​~anderson/​cs445/​notebooks/​21 Convolutional Neural Networks.ipynb|21 Convolutional Neural Networks]]\\ [[http://​nbviewer.ipython.org/​url/​www.cs.colostate.edu/​~anderson/​cs445/​notebooks/​22 Introduction to Reinforcement Learning.ipynb|22 Introduction to Reinforcement Learning]] ​ | [[https://​drive.google.com/​file/​d/​1xeUDVGWGUUv1-ccUMAZHJLej2C7aAFWY/​view|Reinforcement Learning: An Introduction]],​ by Sutton and Barto   | [[http://​nbviewer.ipython.org/​url/​www.cs.colostate.edu/​~anderson/​cs445/​notebooks/​A4 Classification with QDA, LDA, and Logistic Regression.ipynb|A4 Classification with QDA, LDA, and Logistic Regression]] <color red>​(use() return value updated March 20)</​color>​ due Tuesday, March 27, 10:00 PM. Here are some [[http://​www.cs.colostate.edu/​~anderson/​cs445/​goodSolutions|good solutions.]] ​   |
 +
 +===== April =====
 +
 +|< 100% 10% 20% 30% 20% 20%  >|
 +^  Week      ^  Topic      ^  Material ​ ^  Reading ​         ^  Assignments ​ ^
 +| Week 11:\\ Apr 2 - Apr 6   | Reinforcement Learning. Games using Tabular Q functions. ​ | [[http://​nbviewer.ipython.org/​url/​www.cs.colostate.edu/​~anderson/​cs445/​notebooks/​23 Reinforcement Learning with Neural Network as Q Function.ipynb|23 Reinforcement Learning with Neural Network as Q Function]] ​ |  | [[https://​drive.google.com/​open?​id=1KHAxeIwL3ait2ZUbILdbJjCLW47JwxKpdjsAr5kkkZk|Project proposal]] due at 10 pm Friday evening. You are welcome to start with a copy of the linked Google Doc.   |
 +| Week 12:\\ Apr 9 - Apr 13  | Reinforcement Learning using Neural Networks as Q functions. ​ | [[http://​nbviewer.ipython.org/​url/​www.cs.colostate.edu/​~anderson/​cs445/​notebooks/​24 Reinforcement Learning to Control a Marble.ipynb|24 Reinforcement Learning to Control a Marble]]\\ [[http://​nbviewer.ipython.org/​url/​www.cs.colostate.edu/​~anderson/​cs445/​notebooks/​25 Reinforcement Learning for Two Player Games.ipynb|25 Reinforcement Learning for Two Player Games]] ​  |
 +| Week 13:\\ Apr 16 - Apr 20  | Unsupervised Learning. Dimensionality Reduction. ​ Clustering. ​ | [[http://​nbviewer.ipython.org/​url/​www.cs.colostate.edu/​~anderson/​cs445/​notebooks/​26 Linear Dimensionality Reduction.ipynb|26 Linear Dimensionality Reduction]]\\ [[http://​nbviewer.ipython.org/​url/​www.cs.colostate.edu/​~anderson/​cs445/​notebooks/​27 Examples of Linear Dimensionality Reduction.ipynb|27 Examples of Linear Dimensionality Reduction]]\\ [[http://​nbviewer.ipython.org/​url/​www.cs.colostate.edu/​~anderson/​cs445/​notebooks/​28 K-Means Clustering.ipynb|28 K-Means Clustering]] ​ |
 +| Week 14:\\ Apr 23 - Apr 27  | Hierarchical clustering. K Nearest Neighbors Classification. Support Vector Machines. ​ | [[http://​nbviewer.ipython.org/​url/​www.cs.colostate.edu/​~anderson/​cs445/​notebooks/​29 Hierarchical Clustering.ipynb|29 Hierarchical Clustering]]\\ [[http://​nbviewer.ipython.org/​url/​www.cs.colostate.edu/​~anderson/​cs445/​notebooks/​30 Nonparametric Classification with K Nearest Neighbors.ipynb|30 Nonparametric Classification with K Nearest Neighbors]]\\ [[http://​nbviewer.ipython.org/​url/​www.cs.colostate.edu/​~anderson/​cs445/​notebooks/​31 Support Vector Machines.ipynb|31 Support Vector Machines]] ​ |  | [[http://​nbviewer.ipython.org/​url/​www.cs.colostate.edu/​~anderson/​cs445/​notebooks/​A5 Control a Marble with Reinforcement Learning.ipynb|A5 Control a Marble with Reinforcement Learning]] due Tuesday, April 24th, 10:00 PM  |
 +
 +===== May =====
 +
 +|< 100% 10% 20% 30% 20% 20%  >|
 +^  Week      ^  Topic      ^  Material ​ ^  Reading ​         ^  Assignments ​ ^
 +| Week 15:\\ Apr 30 - May 4  | Ensembles. ​ Other topics. ​ | [[http://​nbviewer.ipython.org/​url/​www.cs.colostate.edu/​~anderson/​cs445/​notebooks/​32 Ensembles of Convolutional Neural Networks.ipynb|32 Ensembles of Convolutional Neural Networks]]\\ [[http://​nbviewer.ipython.org/​url/​www.cs.colostate.edu/​~anderson/​cs445/​notebooks/​33 Machine Learning for Brain-Computer Interfaces.ipynb|33 Machine Learning for Brain-Computer Interfaces]]\\ ​ [[http://​nbviewer.ipython.org/​url/​www.cs.colostate.edu/​~anderson/​cs445/​notebooks/​34 Modeling Global Climate Change.ipynb|34 Modeling Global Climate Change]] ​ |
 +| May 7 - May 10  |  Final Exams  |  |  | Final Project Report due Wednesday, May 9, 10:00 PM. Here is a [[http://​nbviewer.ipython.org/​url/​www.cs.colostate.edu/​~anderson/​cs445/​notebooks/​Project Report Example.ipynb|Project Report Example]] ​ |
 +
 +
  
schedule-spring18.txt ยท Last modified: 2019/01/03 15:03 (external edit)