CS545: Machine Learning

User Tools

Site Tools

Trace: • start
start

Differences

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

Link to this comparison view

Both sides previous revisionPrevious revision
Next revision		Previous revision
start [2024/07/22 15:05] – [November] andersonstart [2024/09/26 21:12] (current) – external edit 127.0.0.1
Line 18: Line 18:
 The following schedule is **tentative and is being updated**. The following schedule is **tentative and is being updated**.
  
 +All students may attend the lecture remotely using [[https://zoom.us/j/92107238733?pwd=Wggv0JQGepdeoezMRrv0gpVImn90yl.1|this zoom link]].
  
 ===== August ===== ===== August =====
Line 23: Line 24:
 |< 100% 18% 20% 22% 20% 20%  >| |< 100% 18% 20% 22% 20% 20%  >|
 ^  Week      ^  Topic      ^  Lecture Notes  ^  Reading          ^  Assignments  ^ ^  Week      ^  Topic      ^  Lecture Notes  ^  Reading          ^  Assignments  ^
-| Week 1:\\  Aug 20, 22   | Course overview.  \\ Machine Learning and AI: History and Present Boom\\ Jupyter notebooks.    |  | [[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 1:\\  Aug 20, 22   | Course overview.  \\ Machine Learning and AI: History and Present Boom\\ 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/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://jupyterlab.readthedocs.io/en/stable/getting_started/overview.html|JupyterLab Introduction]], watch the video then play with jupyter lab.  \\ [[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 27, 29  | Jupyter notebook animations. Optimization algorithms. Simple linear and nonlinear models.   |   |   |  |+| Week 2:\\  Aug 27, 29  | Optimization algorithms. Simple linear and nonlinear models.  Confidence intervals.   | [[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 Input Importance and Generative AI---Friend or Foe.ipynb|02a Input Importance and 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 Fitting Simple Models Using Gradient Descent in the Squared Error]]\\ [[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]]   |   |  |
  
 ===== September ===== ===== September =====
Line 30: Line 31:
 |< 100% 18% 20% 22% 20% 20%  >| |< 100% 18% 20% 22% 20% 20%  >|
 ^  Week      ^  Topic      ^  Lecture Notes  ^  Reading          ^  Assignments  ^ ^  Week      ^  Topic      ^  Lecture Notes  ^  Reading          ^  Assignments  ^
-| Week 3:\\  Sept 3, 5\\ Chuck's office hours Thursday will be from 2 to 3:30.  | Confidence intervals. Introduction to neural networks.  |  | |  | +| Week 3:\\  Sept 3, 5  | Introduction to neural networks.   | [[https://nbviewer.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/05 Introduction to Neural Networks.ipynb|05 Introduction to Neural Networks]]  | [[https://www.3blue1brown.com/topics/neural-networks|3Blue1Brown Introduction to Neural Networks]] in the first five chapters provides a fun video tutorial including error backpropagation.  |   | 
-| Week 4:\\  Sept 10, 12   | Design of NeuralNetwork class. Optimizers.  |  | [[https://machinelearningmastery.com/weight-initialization-for-deep-learning-neural-networks/|Weight Initialization for Deep Learning Neural Networks]], by Jason Brownlee  | +| Week 4:\\  Sept 10, 12   | Design of NeuralNetwork class. Optimizers. Overview of A2. Memory organization for neural network parameters. Optimizers tailored for neural networks.  | [[https://nbviewer.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/06 Python Classes.ipynb|06 Python Classes]]\\ [[https://nbviewer.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/07 Optimizers Simple.ipynb|07 Optimizers Simple]]\\ [[https://nbviewer.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/08 Collecting All Weights into One-Dimensional Vector for Use in Optimizers.ipynb|08 Collecting All Weights into One-Dimensional Vector for Use in Optimizers]]\\ [[https://nbviewer.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/08a Optimizers.ipynb|08a Optimizers]]   | [[https://machinelearningmastery.com/weight-initialization-for-deep-learning-neural-networks/|Weight Initialization for Deep Learning Neural Networks]], by Jason Brownlee  | [[https://nbviewer.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/A1.ipynb|A1]] due Monday, September 9th, 10:00 PM.  | 
-| Week 5:\\  Sept 17, 19  | Using optimizers.  |   | |   | +| Week 5:\\  Sept 17, 19\\ Chuck's office hours cancelled today.  | Introduction to Classification.  | [[https://nbviewer.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/09 Introduction to Classification.ipynb|09 Introduction to Classification]]    | | [[https://nbviewer.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/A2 NeuralNetwork Class.ipynb|A2 NeuralNetwork Class]] due Thursday, September 19, 10:00 PM. Here is an example solution to A2: [[https://nbviewer.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/A2 NeuralNetwork Class Solution.ipynb|A2 NeuralNetwork Class Solution]]  | 
-| Week 6:\\  Sept 24, 26  | Early stopping (new version of optimizers). A3. Introduction to classification.   |   |+| Week 6:\\  Sept 24, 26  | Classification with Logistic Regression.   | [[https://nbviewer.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/10 Classification with Linear Logistic Regression.ipynb|10 Classification with Linear Logistic Regression]]\\ [[https://nbviewer.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/11 Classification with Nonlinear Logistic Regression Using Neural Networks.ipynb|11 Classification with Nonlinear Logistic Regression Using Neural Networks]]   |
  
 ===== October ===== ===== October =====
Line 39: Line 40:
 |< 100% 18% 20% 22% 20% 20%  >| |< 100% 18% 20% 22% 20% 20%  >|
 ^  Week      ^  Topic      ^  Lecture Notes  ^  Reading          ^  Assignments  ^ ^  Week      ^  Topic      ^  Lecture Notes  ^  Reading          ^  Assignments  ^
-| Week 7:\\  Oct 1, 3  | Classification with QDA, LDA, and linear logistic regression.  |  | |  |+| Week 7:\\  Oct 1, 3  | Classification with QDA, LDA, and linear logistic regression.  |  | | [[https://nbviewer.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/A3 NeuralNetwork Class Using Optimizers.ipynb|A3 NeuralNetwork Class Using Optimizers]] due Tuesday, October 1st, 10:00 PM. |
 | Week 8:\\  Oct 8, 10  | Classification with Nonlinear Logistic Regression. Introduction to Reinforcement Learning.  |  | | | Week 8:\\  Oct 8, 10  | Classification with Nonlinear Logistic Regression. Introduction to Reinforcement Learning.  |  | |
 | Week 9:\\  Oct 15, 17  | Reinforcement learning with Q Function as Neural Network. Learning to play games. |   | [[https://lastweekin.ai/p/241|Last Week in AI]]\\ [[https://www.cbsnews.com/news/geoffrey-hinton-ai-dangers-60-minutes-transcript/?utm_source=substack&utm_medium=email|Geoffrey Hinton: AI Dangers, on 60 Minutes]]  |    | | Week 9:\\  Oct 15, 17  | Reinforcement learning with Q Function as Neural Network. Learning to play games. |   | [[https://lastweekin.ai/p/241|Last Week in AI]]\\ [[https://www.cbsnews.com/news/geoffrey-hinton-ai-dangers-60-minutes-transcript/?utm_source=substack&utm_medium=email|Geoffrey Hinton: AI Dangers, on 60 Minutes]]  |    |
 | Week 10:\\  Oct 22, 24  | Modular framework for reinforcement learning. Convolutional Neural Networks.   |   | |   | | Week 10:\\  Oct 22, 24  | Modular framework for reinforcement learning. Convolutional Neural Networks.   |   | |   |
-| Week 11:\\  Oct 29, 31  | Ray. Pytorch.    |   | [[https://www.whitehouse.gov/briefing-room/statements-releases/2023/10/30/fact-sheet-president-biden-issues-executive-order-on-safe-secure-and-trustworthy-artificial-intelligence/|President Biden's Executive Order on Safe, Secure, and Trustworthy Artificial Intelligence]]  |   |+| Week 11:\\  Oct 29, 31  | Pytorch.\\ Jax.\\ Ray.    |   | [[https://www.whitehouse.gov/briefing-room/statements-releases/2023/10/30/fact-sheet-president-biden-issues-executive-order-on-safe-secure-and-trustworthy-artificial-intelligence/|President Biden's Executive Order on Safe, Secure, and Trustworthy Artificial Intelligence]]  |   |
  
 ===== November ===== ===== November =====
Line 49: Line 50:
 |< 100% 18% 20% 22% 20% 20%  >| |< 100% 18% 20% 22% 20% 20%  >|
 ^  Week      ^  Topic      ^  Lecture Notes  ^  Reading          ^  Assignments  ^ ^  Week      ^  Topic      ^  Lecture Notes  ^  Reading          ^  Assignments  ^
-| Week 12:\\  Nov 5, 7  |  Convolutional Neural Networks.  |  | |+| Week 12:\\  Nov 5, 7  | Convolutional Neural Networks.  |  | |
 | Week 13:\\  Nov 12, 14  | Ensembles. Mixture of Experts.   |   |   | | Week 13:\\  Nov 12, 14  | Ensembles. Mixture of Experts.   |   |   |
-| Week 14:\\  Nov 19, 21  | Clustering. K-Nearest Neighbors. Jax. Web Apps with Streamlit.  |   | [[https://www.nature.com/articles/d41586-023-03635-w|ChatGPT generates fake data set to support scientific hypothesis]]  |   |+| Week 14:\\  Nov 19, 21  | Clustering. K-Nearest Neighbors. Web Apps with Streamlit.  |   | [[https://www.nature.com/articles/d41586-023-03635-w|ChatGPT generates fake data set to support scientific hypothesis]]  |   |
 | Fall Break:\\ Nov 25-29 | No classes.  | | Fall Break:\\ Nov 25-29 | No classes.  |
  
start.1721682313.txt.gz · Last modified: 2024/07/22 15:05 by anderson