/*** To use jupyter notebooks on our CS department machines, you must add this line to your .bashrc file: export PATH=/usr/local/anaconda3/latest/bin:$PATH ***/ /*** 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**. ===== August ===== |< 100% 18% 20% 22% 20% 20% >| ^ Week ^ Topic ^ Lecture Notes ^ Reading ^ Assignments ^ | 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 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 ^ Lecture Notes ^ Reading ^ Assignments ^ | 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 12, 14 | Design of NeuralNetwork class. Optimizers. | [[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.ipynb|07 Optimizers]] | [[https://machinelearningmastery.com/weight-initialization-for-deep-learning-neural-networks/|Weight Initialization for Deep Learning Neural Networks]], by Jason Brownlee | | Week 5:\\ Sept 19, 21 | Using optimizers. | [[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/A2 NeuralNetwork Class.ipynb|A2 NeuralNetwork Class]] due Thursday, September 21st, 10:00 PM. Examples of good A2 solutions can be [[https://www.cs.colostate.edu/~anderson/cs545/notebooks/goodones|found here]] | | Week 6:\\ Sept 26, 28 | Early stopping (new version of optimizers). A3. Introduction to classification. | [[https://nbviewer.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/07a Optimizers2.ipynb|07a Optimizers2]]\\ [[https://nbviewer.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/09 Introduction to Classification.ipynb|09 Introduction to Classification]]\\ Tuesday lecture pre-recorded and available now on Echo360. | ===== October ===== |< 100% 18% 20% 22% 20% 20% >| ^ Week ^ Topic ^ Lecture Notes ^ Reading ^ Assignments ^ | Week 7:\\ Oct 3, 5 | Classification with QDA, LDA, and linear 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/A3 NeuralNetwork Class Using Optimizers.ipynb|A3 NeuralNetwork Class Using Optimizers]] due Thursday, October 5th, 10:00 PM\\ Examples of good A3 solutions can be [[https://www.cs.colostate.edu/~anderson/cs545/notebooks/goodones|found here]] | | Week 8:\\ Oct 10, 12 | Classification with Nonlinear Logistic Regression. Introduction to Reinforcement Learning. | [[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]]\\ [[https://nbviewer.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/12 Introduction to Reinforcement Learning.ipynb|12 Introduction to Reinforcement Learning]] | | | Week 9:\\ Oct 17, 19 | Reinforcement learning with Q Function as Neural Network. Learning to play games. | [[https://nbviewer.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/13 Reinforcement Learning with Neural Networks as Q Function.ipynb|13 Reinforcement Learning with Neural Networks as Q Function]]\\ [[https://nbviewer.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/14 Targets and Deltas Summary.ipynb|14 Targets and Deltas Summary]]\\ [[https://nbviewer.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/15 Reinforcement Learning for Two Player Games.ipynb|15 Reinforcement Learning for Two Player 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]] | [[https://nbviewer.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/A4 Neural Network Classifier.ipynb|A4 Neural Network Classifier]] due Wednesday, October 18th, 10:00 PM\\ Examples of good A4 solutions can be [[https://www.cs.colostate.edu/~anderson/cs545/notebooks/goodones|found here]]\\ And here are [[https://www.cs.colostate.edu/~anderson/cs545/notebooks/neuralnetworksA4.zip|python script files]] as A4 answer. | | Week 10:\\ Oct 24, 26 | Modular framework for reinforcement learning. Convolutional Neural Networks. | [[https://nbviewer.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/16 Modular Framework for Reinforcement Learning.ipynb|16 Modular Framework for Reinforcement Learning]]\\ [[https://nbviewer.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/17 Convolutional Neural Networks.ipynb|17 Convolutional Neural Networks]] | | [[https://nbviewer.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/Project Proposal and Report Example.ipynb|Project proposal]] due at 10 pm Friday evening, October 27th. | ===== November ===== |< 100% 18% 20% 22% 20% 20% >| ^ Week ^ Topic ^ Lecture Notes ^ Reading ^ Assignments ^ | Week 11:\\ Oct 31 Nov 2 | Ray. Pytorch. Convolutional Neural Networks. | [[https://nbviewer.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/18 Ray for Parallel Processing.ipynb|18 Ray for Parallel Processing]]\\ [[https://nbviewer.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/19 Introduction to Pytorch.ipynb|19 Introduction to Pytorch]]\\ [[https://nbviewer.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/20 Steps Towards Convolutional Nets in Pytorch.ipynb|20 Steps Towards Convolutional Nets in 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]] | [[https://nbviewer.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/A5 Reinforcement Learning.ipynb|A5 Reinforcement Learning]] due Friday, Nov 3rd, 10:00 PM. This notebook and a5.zip were updated slightly Oct. 26th, 11:00 AM. | | Week 12:\\ Nov 7, 9 | Convolutional Neural Networks. Ensembles. | [[https://nbviewer.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/21 Convolutional Neural Network Class in Pytorch.ipynb|21 Convolutional Neural Network Class in Pytorch]]\\ [[https://nbviewer.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/22 Ensembles.ipynb|22 Ensembles]] | | | Week 13:\\ Nov 14, 16 | Clustering. K-Nearest Neighbors. Jax. | [[https://nbviewer.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.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/24 Introduction to Jax.ipynb|24 Introduction to Jax]] | [[https://www.science.org/doi/10.1126/science.adi2336|Learning skillful medium-range global weather forecasting]] by DeepMind, using graph-convolutional_networks (GNNs) implemented in with jax. | | Fall Break:\\ Nov 20-24 | No classes. | | Week 14:\\ Nov 28, 30 | Support Vector Machines. Web Apps with Streamlit. Word Embeddings. | [[https://nbviewer.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/25 Support Vector Machines.ipynb|25 Support Vector Machines]]\\ [[https://nbviewer.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/26 Web Apps with Streamlit.ipynb|26 Web Apps with Streamlit]]\\ [[https://nbviewer.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/27 Word Embeddings.ipynb|27 Word Embeddings]] | [[https://www.nature.com/articles/d41586-023-03635-w|ChatGPT generates fake data set to support scientific hypothesis]] | [[https://nbviewer.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/A6 Convolutional Neural Networks.ipynb|A6 Convolutional Neural Networks]] due Friday, Dec. 1, 10:00 PM. | ===== December ===== |< 100% 18% 20% 22% 20% 20% >| ^ Week ^ Topic ^ Lecture Notes ^ Reading ^ Assignments ^ | Week 15:\\ Dec 5, 7 | Transformers. | [[https://nbviewer.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/28 Introduction to Transformers.ipynb|28 Introduction to Transformers]]\\ [[https://nbviewer.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/29 Transformers Predicting Text.ipynb|29 Transformers Predicting Text]]\\ Chuck's Recent Projects:\\ 1. Pretraining Speeds Up RL\\ 2. Brain-Computer Interfaces\\ 3. Explaining a Neural Network's Decisions | [[https://colab.research.google.com/drive/1Qhq2FO4FFX_MKN5IEgia_PrBEttxCQG4?usp=sharing&utm_source=substack&utm_medium=email#scrollTo=r_20uEgdp4W_|Automatic detection of hallucination with SelfCheckGPT]]\\ [[https://arxiv.org/pdf/2309.13638.pdf|Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve]] | | | Dec 11-15 | Final Exam Week | No Exams in this course | | [[https://nbviewer.org/url/www.cs.colostate.edu/~anderson/cs545/notebooks/Project Proposal and Report Example.ipynb|Project Report]] due at 10 pm Tuesday evening, December 12th. |