Differences

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

--- start [2022/10/01 17:21] – anderson
+++ start [2023/09/06 12:01] – [September] anderson
@@ Line 6: / Line 6: @@
 ***/
+/***
+Please send your suggestions regarding lecture topics to Chuck using [[https://tinyurl.com/2nyfzc36|this Google Docs form]].  Questions regarding assignments should be entered in Canvas discussions.
+***/
+ \\
+ \\
+ \\
 The following schedule is **tentative and is being updated**.
-Please send your suggestions regarding lecture topics to Chuck using [[https://tinyurl.com/2nyfzc36|this Google Docs form]].  Questions regarding assignments should be entered in Canvas discussions.
 ===== August =====
 |< 100% 18% 20% 22% 20% 20%  >|
-^  Week      ^  Topic      ^  Material  ^  Reading          ^  Assignments  ^
+^  Week      ^  Topic      ^  Lecture Notes  ^  Reading          ^  Assignments  ^
-| Week 1:\\  Aug 23, 256   | Overview of course. Review of neural networks training and use.  | [[https://nbviewer.ipython.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/01 Introduction to CS545.ipynb|01 Introduction to CS545]]\\ [[https://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]]   | [[https://jupyterlab.readthedocs.io/en/stable/getting_started/overview.html|JupyterLab Introduction]], watch the video then play with jupyter lab.  \\ [[https://tinyurl.com/2qw45tlp|The Batch]] from DeepLearning.AI. Yay, Colorado!   |   |
+| Week 1:\\  Aug 22, 24   | Course overview. Jupyter notebooks.    | [[https://nbviewer.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/01 Introduction to CS545.ipynb|01 Introduction to CS545]]\\ [[https://nbviewer.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]]  | [[https://jupyterlab.readthedocs.io/en/stable/getting_started/overview.html|JupyterLab Introduction]], watch the video then play with jupyter lab.  \\ [[https://tinyurl.com/2qw45tlp|The Batch]] from DeepLearning.AI. Yay, Colorado!  \\  [[https://www.freecodecamp.org/news/exploratory-data-analysis-with-numpy-pandas-matplotlib-seaborn/|What is Data Analysis? How to Visualize Data with Python, Numpy, Pandas, Matplotlib & Seaborn Tutorial]], by Aakash NS| Not graded: Please fill out [[https://forms.gle/hppJ5QuRFuRn1L2h7|this anonymous survey]] before Thursday class.  |
-| Week 2:\\  Aug 30, Sept 1  | Thursday lecture cancelled. Please watch pre-recorded lecture in Echo360. Quiz1 and A1 questions. Regression with neural networks.  | [[https://nbviewer.ipython.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/03 Fitting Simple Models Using Gradient Descent in the Squared Error.ipynb|03 Fitting Simple Models Using Gradient Descent in the Squared Error]]  |  |[[https://nbviewer.ipython.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/Quiz1.ipynb|Quiz 1]] due Wednesday, August 31, 10:00 PM, in Canvas  |
+| Week 2:\\  Aug 29, 31  | Jupyter notebook animations. Optimization algorithms. Simple linear and nonlinear models.   | [[https://nbviewer.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/01a Simple Animations.ipynb|01a Simple Animations]] \\ [[https://nbviewer.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]] \\  [[https://nbviewer.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/02a Generative AI--Friend or Foe.ipynb|02a Generative AI--Friend or Foe]] \\ [[https://nbviewer.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/03 Fitting Simple Models Using Gradient Descent in the Squared Error.ipynb|03 Searching for Good Weights in a Linear Model]]  |   |  |
 ===== September =====
 |< 100% 18% 20% 22% 20% 20%  >|
-^  Week      ^  Topic      ^  Material  ^  Reading          ^  Assignments  ^
+^  Week      ^  Topic      ^  Lecture Notes  ^  Reading          ^  Assignments  ^
-| Week 3:\\  Sept 6, 8  | Introduction to Neural Networks  | [[https://nbviewer.ipython.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/04 Introduction to Neural Networks.ipynb|04 Introduction to Neural Networks]]\\ [[https://nbviewer.ipython.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/04a Simple Animations.ipynb|04a Simple Animations]]\\   | [[https://doi.org/10.1016/j.neucom.2022.06.111|Activation functions in deep learning: A comprehensive survey and benchmark]], Neurocomputing, volume 503, 2022, pp. 92-108  |   |
+| Week 3:\\  Sept 5, 7\\ Chuck's office hours Thursday will be from 2 to 3:30.  | Confidence intervals. Introduction to neural networks.  | [[https://nbviewer.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/04 Training Multiple Models to Obtain Confidence Intervals.ipynb|04 Training Multiple Models to Obtain Confidence Intervals]]\\ [[https://nbviewer.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/05 Introduction to Neural Networks.ipynb|05 Introduction to Neural Networks]]| | [[https://nbviewer.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/A1.ipynb|A1]] due Friday, September 8th, 10:00 PM  |
-| Week 4:\\  Sept 13, 15\\   |  Python classes.  A2.    | [[https://nbviewer.ipython.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/04b Introduction to Python Classes.ipynb|04b Introduction to Python Classes]]  | [[https://docs.python.org/3/tutorial/classes.html|Classes Tutorial]]  | [[https://nbviewer.ipython.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/A1 Three-Layer Neural Network.ipynb|A1 Three-Layer Neural Network]] due Monday, Sept 12th, at 10:00 PM\\  [[https://nbviewer.ipython.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/solutions/Anderson-Solution-A1.ipynb|Anderson-Solution-A1]]  |
+| Week 4:\\  Sept 12, 14   | Design of NeuralNetwork class. Optimizers.  | | |
-| Week 5:\\  Sept 20, 22  | Optimizers. Autoencoders.  | [[https://nbviewer.ipython.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/05 Optimizers.ipynb|05 Optimizers]] <color red>Updated Sept. 27th</color> \\ [[https://nbviewer.ipython.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/05a Collecting All Weights into One-Dimensional Vector for Use in Optimizers.ipynb|05a Collecting All Weights into One-Dimensional Vector for Use in Optimizers]]\\ [[https://nbviewer.ipython.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/06 Autoencoders.ipynb|06 Autoencoders]]\\ [[https://nbviewer.ipython.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/06a Visualizing Weights.ipynb|06a Visualizing Weights]] <color red>New</color>  | [[https://pandas.pydata.org/Pandas_Cheat_Sheet.pdf|Pandas Cheat Sheet]]  | [[https://nbviewer.ipython.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/A2 NeuralNetwork Class.ipynb|A2 NeuralNetwork Class]] due Thursday, Sept 22nd, at 10:00 PM\\ [[https://nbviewer.ipython.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/solutions/Anderson-A2-Solution.ipynb|Anderson-A2-Solution]]  |
+| Week 5:\\  Sept 19, 21  | Introduction to classification.  | | |
-| Week 6:\\  Sept 27, 29  |  A3. Classification  | [[https://nbviewer.ipython.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/07 Introduction to Classification.ipynb|07 Introduction to Classification]]  | [[https://moocaholic.medium.com/jax-a13e83f49897|JAX Ecosystem]]\\ [[https://streamlit.io/|Streamlit]]  |  |
+| Week 6:\\  Sept 26, 28  | Classification. Convolutional neural networks.  | | |
 ===== October =====
 |< 100% 18% 20% 22% 20% 20%  >|
-^  Week      ^  Topic      ^  Material  ^  Reading          ^  Assignments  ^
+^  Week      ^  Topic      ^  Lecture Notes  ^  Reading          ^  Assignments  ^
-| Week 7:\\  Oct 4, 6  | Classification. Convolutional neural networks.  | [[https://nbviewer.ipython.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/08 Classification with Linear Logistic Regression.ipynb|08 Classification with Linear Logistic Regression]]\\ [[https://nbviewer.ipython.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/09 Classification with Nonlinear Logistic Regression Using Neural Networks.ipynb|09 Classification with Nonlinear Logistic Regression Using Neural Networks]]\\ [[https://nbviewer.ipython.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/10 JAX.ipynb|10 JAX]]\\ [[https://www.cs.colostate.edu/~anderson/cs545/notebooks/neuralnetworks_app.tar|neuralnetworks_app.tar]]\\ [[https://nbviewer.ipython.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/11 Convolutional Neural Networks.ipynb|11 Convolutional Neural Networks]]\\ [[https://www.cs.colostate.edu/~anderson/cs545/notebooks/CNN Backprop.pdf|CNN Backpropagation Notes]]  | [[https://spectrum.ieee.org/special-reports/the-great-ai-reckoning/|The Great AI Reckoning]]  | [[https://nbviewer.ipython.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/A3 NeuralNetwork Class Using Optimizers.ipynb|A3 NeuralNetwork Class Using Optimizers]] due Tuesday, October 4th, at 10:00 PM. <color red>Updated Sept. 27th.</color>   |
+| Week 7:\\  Oct 3, 5  | Introduction to Jax and Pytorch.  | | |
-| Week 8:\\  Oct 11, 13  | Pytorch. Convolutional neural nets  | [[https://nbviewer.ipython.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/12 Introduction to Pytorch.ipynb|12 Introduction to Pytorch]]\\ [[https://nbviewer.ipython.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/13 Convolutional Neural Networks in Pytorch.ipynb|13 Convolutional Neural Networks in Pytorch]]\\ [[https://nbviewer.ipython.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/14 Convolutional Neural Networks in Numpy.ipynb|14 Convolutional Neural Networks in Numpy]]  |
+| Week 8:\\  Oct 10, 12  | More convolutional neural networks.  | | |
-| Week 9:\\  Oct 18, 20  | Reinforcement Learning  | [[https://nbviewer.ipython.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/15 Introduction to Reinforcement Learning.ipynb|15 Introduction to Reinforcement Learning]]\\ [[https://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]]  | |   |
+| Week 9:\\  Oct 17, 19  | Introduction to reinforcement leanring. Learning to play games. | | |
-| Week 10:\\  Oct 25, 27  | Reinforcement Learning  | [[https://nbviewer.ipython.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/17 Reinforcement Learning for Two Player Games.ipynb|17 Reinforcement Learning for Two Player Games]]\\ [[https://nbviewer.ipython.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/18 Reinforcement Learning to Control a Marble.ipynb|18 Reinforcement Learning to Control a Marble]]\\ [[https://nbviewer.ipython.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/19 Reinforcement Learning Modular Framework.ipynb|19 Reinforcement Learning Modular Framework]] |
+| Week 10:\\  Oct 24, 26  | Reinforcement learning for control of dynamic systems.  | | |
 ===== November =====
 |< 100% 18% 20% 22% 20% 20%  >|
-^  Week      ^  Topic      ^  Material  ^  Reading          ^  Assignments  ^
+^  Week      ^  Topic      ^  Lecture Notes  ^  Reading          ^  Assignments  ^
-| Week 11:\\  Nov 1, 3  | Transfer learning in Reinforcement Learning.\\ Brain-Computer Interfaces  | Slide presentations  | [[http://www.cs.colostate.edu/~anderson/wp/pubs/pretrainijcnn15.pdf|Faster Reinforcement Learning After Pretraining Deep Networks to Predict State Dynamics]], [[https://ieeexplore.ieee.org/document/9533751|Increased Reinforcement Learning Performance through Transfer of Representation Learned by State Prediction Model]]
+| Week 11:\\  Oct 31 Nov 2  | Recurrent neural networks.  | | |
-| Week 12:\\  Nov 8, 10  | BCI. Recurrent Neural Networks. | [[https://nbviewer.ipython.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/20 Recurrent Networks in Numpy.ipynb|20 Recurrent Networks in Numpy]]\\ [[https://nbviewer.ipython.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/21 Recurrent Networks in Pytorch.ipynb|21 Recurrent Networks in Pytorch]]\\ [[https://nbviewer.ipython.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/22 Classifying EEG Using Recurrent Neural Networks.ipynb|22 Classifying EEG Using Recurrent Neural Networks]]  | |  |
+| Week 12:\\  Nov 7, 9  | Unsupervised learning. Dimensionality reduction. Autoencorders. | | |
-| Week 13:\\  Nov 15, 17  | K-means clustering. K-nearest-neighbor classification. Support Vector Machines.   | [[https://nbviewer.ipython.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/23 K-Means Clustering, K-Nearest-Neighbor Classification.ipynb|23 K-Means Clustering, K-Nearest-Neighbor Classification]]\\ [[https://nbviewer.ipython.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/24 Support Vector Machines.ipynb|24 Support Vector Machines]]    |
+| Week 13:\\  Nov 14, 16  | Clustering.  | | |
-| Week 14:\\  Nov 29, Dec 1  | Introduction to Transformers  | [[https://nbviewer.ipython.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/25 Introduction to Transformers.ipynb|25 Introduction to Transformers]] |
+| Fall Break:\\ Nov 20-24 | No classes  |
+| Week 14:\\  Nov 28, 30  | Ensemble methods. Mixture-of-experts. Transformers.  | | |
 ===== December =====
 |< 100% 18% 20% 22% 20% 20%  >|
-^  Week      ^  Topic      ^  Material  ^  Reading          ^  Assignments  ^
+^  Week      ^  Topic      ^  Lecture Notes  ^  Reading          ^  Assignments  ^
-| Week 15:\\  Dec 6, 8  | Transformers: Self-Attention Replaced by Fourier Transform.\\ Cascade Ensemble Network   | [[https://nbviewer.ipython.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/26 FNet--Replace Self-Attention with Fourier Transform.ipynb|26 FNet--Replace Self-Attention with Fourier Transform]]\\ [[https://nbviewer.ipython.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/27 Cascade Ensemble Network.ipynb|27 Cascade Ensemble Network]] |
+| Week 15:\\  Dec 5, 7  | Other topics in current research.  | | [[https://www.cs.colostate.edu/~anderson/cs545/notebooks/2023_AI-scientists-topline-report81.pdf|AI Scientists’ Perspectives on AI]]  |
-| Dec 12-16  |  Final Exam Week  |  No Exams in this course  |
+| Dec 11-15  |  Final Exam Week  |  No Exams in this course  |