====== Schedule ======




===== August =====

|< 100% 10% 20% 30% 20% 20%  >|
^  Week      ^  Topic      ^  Material  ^  Reading          ^  Assignments  ^
| Week 1:\\  August 26 - 30    | Overview of course and the machine learning field. Reminder of how python is used in machine learning.  | [[http://nbviewer.ipython.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/01 Introduction to CS545.ipynb|01 Introduction to CS545]]\\ [[http://nbviewer.ipython.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/02 Searching for Good Weights in a Linear Model.ipynb|02 Searching for Good Weights in a Linear Model]]   | [[http://www.labri.fr/perso/nrougier/from-python-to-numpy/|From Python to Numpy]], Chapters 1 - 2\\ [[http://www.scipy-lectures.org/|Scipy Lectures]], Section 1\\ [[https://jakevdp.github.io/PythonDataScienceHandbook/04.00-introduction-to-matplotlib.html|Visualization with Matplotlib]]\\ [[http://www.deeplearningbook.org/|Deep Learning]], Chapters 1 - 5.1.4  |


===== September =====

|< 100% 10% 20% 30% 20% 20%  >|
^  Week      ^  Topic      ^  Material  ^  Reading          ^  Assignments  ^
| Week 2:\\ September 2 - 6    | Review of gradients.  | [[http://nbviewer.ipython.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/02 Searching for Good Weights in a Linear Model.ipynb|02 Searching for Good Weights in a Linear Model]]\\ [[http://nbviewer.ipython.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/03 Three Gradient Descent Algorithms.ipynb|03 Three Gradient Descent Algorithms]]   |
| Week 3:\\ September 9 - 13\\ <color red>Class cancelled Thursday, Sept 12th</color>    | Implementing neural networks with numpy to predict real-valued variables.  Deriving gradients.  | [[http://nbviewer.ipython.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/04 Scaled Conjugate Gradient.ipynb|04 Scaled Conjugate Gradient]]\\ [[http://nbviewer.ipython.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/05 Introduction to Gradient Descent for Neural Networks.ipynb|05 Introduction to Gradient Descent for Neural Networks]] |  | [[http://nbviewer.ipython.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/A1 Gradient Descent.ipynb|A1 Gradient Descent]] due Tuesday, Sept 10th, at 10:00 PM  |
| Week 4:\\ September 16 - 20    | Error gradients for neural networks as matrix equations.  | [[http://nbviewer.ipython.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/06.1 Gradient Descent for Two-Layer Neural Networks.ipynb|06.1 Gradient Descent for Two-Layer Neural Networks]]\\ [[http://www.cs.colostate.edu/~anderson/cs545/notebooks/Handdrawn notes Sept 19.pdf|Hand drawn notes from lecture]]   |
| Week 5:\\ September 23 - 27    | Introduction to Pytorch and automatic differentation.  | [[http://nbviewer.ipython.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/07 Automatic Differentiation in Pytorch.ipynb|07 Automatic Differentation in Pytorch]]\\  [[http://nbviewer.ipython.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/08 Automatic Differentiation, SGD, and Adam with Pytorch.ipynb|08 Automatic Differentiation, SGD, and Adam with Pytorch]]   |  | [[http://nbviewer.ipython.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/A2.4 Three Layer Neural Network.ipynb|A2.4 Three Layer Neural Network]] due Wednesday, Sept 25th, at 10:00 PM  |

 ===== October =====

|< 100% 10% 20% 30% 20% 20%  >|
^  Week      ^  Topic      ^  Material  ^  Reading          ^  Assignments  ^
| Week 6:\\ September 30 - October 4   | Neural Network class. Classification.  | [[http://nbviewer.ipython.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/09.1 Neural Network Class.ipynb|09.1 Neural Network Class]]\\ [[http://nbviewer.ipython.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/10 Classification with Linear Logistic Regression.ipynb|10 Classification with Linear Logistic Regression]]  |
| Week 7:\\ October 7 - 11    | Classification with multiple labels.  | [[http://nbviewer.ipython.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/11 Classification with Neural Networks.ipynb|11 Classification with Neural Networks]] | [[https://www.wired.com/story/ai-pioneer-algorithms-understand-why/|Paper on need for causality]]  |
| Week 8:\\ October 14 - 18    | Convolutional neural networks in numpy, pytorch and tensorflow.  | [[http://nbviewer.ipython.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/12 Multilabel Classification.ipynb|12 Multilabel Classification]]\\ [[http://nbviewer.ipython.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/13.1 Pytorch nn Module.ipynb|13.1 Pytorch nn Module]]  |  | [[http://nbviewer.ipython.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/A3.4 Classification.ipynb|A3.4 Classification]] due Wednesday, Oct 16th, at 10:00 PM  |
| Week 9:\\ October 21 - 25    | Convolutional nets.\\ Reinforcement learning.  | [[http://nbviewer.ipython.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/14 NeuralNetwork_Convolutional and CIFAR-10.ipynb|14 NeuralNetwork_Convolutional and CIFAR-10]]\\ [[http://nbviewer.ipython.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/15 Introduction to Reinforcement Learning.ipynb|15 Introduction to Reinforcement Learning]]  |  | [[http://nbviewer.ipython.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/Project Proposal.ipynb|Project proposal]] due at 10 pm Wednesday evening, October 23rd.  |

===== November =====

|< 100% 10% 60% 5% 5% 20%  >|
^  Week      ^  Topic      ^  Material  ^  Reading          ^  Assignments  ^
| Week 10:\\ October 28 - November 1   | Reinforcement learning.  | [[http://nbviewer.ipython.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/16 Reinforcement Learning with Neural Network as Q Function.ipynb|16 Reinforcement Learning with Neural Network as Q Function]]\\ [[http://nbviewer.ipython.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/17 Reinforcement Learning to Control a Marble.ipynb|17 Reinforcement Learning to Control a Marble]]  | [[http://incompleteideas.net/book/the-book.html|Reinforcement Learning: An Introduction]], by Richard Sutton and Andrew Barto, 2nd edition | [[http://nbviewer.ipython.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/A4.4 Convolutional Neural Networks.ipynb|A4.4 Convolutional Neural Networks]] due Wednesday, Oct 30th, at 10:00 PM  |
| Week 11:\\ November 4 - 8    | Transfer learning in Reinforcement Learning\\ Natural language processing.  |
| Week 12:\\ November 11 - 15    | Natural Language Processing. \\ Deep learning application development.  | [[http://nbviewer.ipython.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/18 Embedding With Conv1d.ipynb|18 Embedding With Conv1d.ipynb]]\\ [[http://nbviewer.ipython.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/19 Embedding Network.ipynb|19 Embedding Network]]\\ [[http://nbviewer.ipython.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/20 Transformer Tutorial.ipynb|20 Transformer Tutorial]]\\ [[https://towardsdatascience.com/how-to-code-the-transformer-in-pytorch-24db27c8f9ec|How to Code the Transformer in Pytorch]] by Samuel Lynn-Evans  |
| Week 13:\\ November 18 - 22    | Student presentations.\\ 1. Katherine Haynes: **Icing and Low Cloud Detection from the Geostationary Operational Environmental Satellite (GOES-16) Using Neural Networks** \\ 2.  Hwankook Lee and Erica Shin: **Title Unknown**  \\ 3. Andy Dolan, Tom Cavey, Jason Stock: **Augmented Classification Motivated by Neural Network Pitfalls** \\ 4. \\ 5. \\ 6. \\ 7. Zheyi Qin and Zihui Li:  **Title Unknown**  \\ 8. Joaquin Cuomo: **Video Prediction**  \\ 9. Vidya Gaddy, Sarah Houlton, Nishant Kashiv, Saurabh Deotale: **Playing Atari games using Reinforcement Learning**  \\ 10. \\ 11. \\ 12.   | | | [[http://nbviewer.ipython.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/A5.1 Control a Marble with Reinforcement Learning.ipynb|A5.1 Control a Marble with Reinforcement Learning]] due Friday, Nov 22nd at 10:00 PM  |
| Fall Recess:\\ November 25 - 29   |  |  |   |

===== December =====

|< 100% 10% 60% 5% 5% 20%  >|
^  Week      ^  Topic      ^  Material  ^  Reading          ^  Assignments  ^
| Week 14:\\ December 2 - 6   | Student presentations. \\ 1. Sarah Hultin: **Making Fake Images with GANs** \\ 2. Sam Armstrong, Saloni Choudhary, Brandon Hua: **LSTMs on Stock Prices**  \\ 3. Vihang Narendra Bhosekar, Rakesh Battineedi and Venkata Sai Sudeep Pamulapati: **Detection of Higgs Boson** \\ 4. Ishani Gowaikar, Lekha Rane and Siddhi Sawant: **Title unknown**   \\ 5. Prerana Ghotge and Soumyadip Roy: **GANs and Face Image Augmentation**  \\ 6. Wei Chen, Zijuan Liu, Ya-Hsin Chen: **Title Unknown**      \\ 7. Eric Wendt, Nicholas Kaufold, Paul Delgado: **Embedded Machine Learning** \\ 8.  \\ 9. Md Al Amin, Long Chen, Nazia Farhat, Upakar Paudel: **Hand Written Digit Recognition**  \\ 10. Jared Crouse, Jarret Flack and Rob Petrovec: **Classification of the Million Song Data Set**  \\ 11. Vishal Anandamani, Brungesh Bangalore Eshwaraiah, Keerthi Dharam: **Twitter Sentiment Analysis using Machine Learning Algorithms** \\ 12. Rodolfo Amaya: **Comparision of ML Techniques on Semi-Conductor Data**  |
| Week 15:\\ December 9 - 13   | Student presentations. \\ 1. Hanbai Li, Qingyi Zhao, Marty Wang: **Title Unknown**      \\ 2. Shree Harini Ravichandran and Pavithra Govardhanan: **Title Unknown** \\ 3. Alperen Tercan, Aniket Tomar, Laksheen Mendis, Sanket Mehrotra: **Exploration of Some Reinforcement Learning Ideas.**  \\ 4. Saptarshi Chatterjee and Sonu Dileep: **Facial Authentication using Siamese-like CNN**  \\ 5.   \\ 6. Tim Whitaker: **Using GANs to Generate 3D Environments**   \\ 7. Kevin Bruhwiler, Alexandre Dubois and Jiping Lu: **Gravity Wave Localization in Day/Night Band Satellite Imagery**  \\ 8. Chaitanya Roygaga, Vishal Kuvar and Sandeep Ravipati: **A study in Automated Machine Learning: Neural Architecture Search**   \\ 9. Ujwal Srinivasa: **YOLO** \\ 10. Fatemeh Hashemi and Pooria Taheri: **The Causes of Internal Behavior Shifts in Predictive Coding Networks**  \\ 11. Dhruv Padalia, Golois Mouelet, Viraj Shastri: **Conversational Agent using Seq2Seq network**  \\ 12.  |
| Finals Week:\\ December 16 - 20  | One more set of Student Presentations. <color red>Tuesday 9:00 to noon, Room 452</color> \\ 1. \\ 2. \\ 3. \\ 4. \\ 5. \\ 6. \\ 7. \\ 8. \\ 9. \\ 10.   |  |  | [[http://nbviewer.ipython.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/Project Report Example.ipynb|Final Project Reports]] due 10pm Tuesday.  |