diff --git a/fa24/introml/calendar.bup b/fa24/introml/calendar.bup deleted file mode 100644 index 62fc0f36..00000000 --- a/fa24/introml/calendar.bup +++ /dev/null @@ -1,53 +0,0 @@ - - Introductory Machine Learning - - - - - -![neuro-datascience](./data-neuroscience.jpg) - - -Introductory Machine Learning -==== - -S&DS 265 introduces some of the key ideas and techniques in machine learning. Algorithms and concepts are presented to build intuition for how different methods work, without advanced mathematics. Assignments give students hands-on experience with the methods on different types of data. Topics include linear regression and classification, tree-based methods, topic models, language models, word embeddings, two-layer and recurrent neural networks, reinforcement learning, and an introduction to deep learning. Examples come from a variety of sources including political speeches, archives of scientific articles, real estate listings, and natural images. Programming is central to the course, and is based on the Python programming language. - -Computing for the course uses Python in Jupyter notebooks. These can be run using [Anaconda](https://www.anaconda.com/products/individual) with the [iML environment](https://raw.githubusercontent.com/YData123/sds265-fa22/master/env/iml_env.yml) adopted by the course (click here to download) -; instructions for installing this environment are available on [Yale Canvas](https://canvas.yale.edu). The notebooks can also be run in [Google Colab](https://colab.research.google.com) by clicking on the [](https://colab.research.google.com) icon. - - -
- -Calendar Fall 2022 ---- -Lectures: Tuesday/Thursday 9:00-10:15am -
-[Davies Auditorium](https://map.yale.edu/?id=1910#!m/563685?ct/52707) - -Complementary readings marked ISL refer to sections in the book [An Introduction to Statistical Learning](https://www.statlearning.com/) (second edition). This text uses the R language, but the treatment of concepts is at an appropriate level for iML. -
- - - - - - Week | Dates | Topics | Demos & Tutorials | Lecture Slides | Readings and Notes | Assignments & Exams ------------ | ----------- | ------------- | ------------ | ------------- | ----------- | ------------ -1 | Sept 1 | Course overview | | Sept 1: [Course overview](https://github.com/YData123/sds265-fa22/raw/master/lectures/lecture-sept-01.pdf) | -2 | Sept 6, 8 | Python and background concepts | [](https://colab.research.google.com/github/YData123/sds265-fa22/blob/master/demos/python/python-elements.ipynb) [Python elements](https://github.com/YData123/sds265-fa22/raw/master/demos/python/python-elements.zip)
[](https://colab.research.google.com/github/YData123/sds265-fa22/blob/master/demos/covid-trends/covid-trends.ipynb) [Covid trends](https://github.com/YData123/sds265-fa22/raw/master/demos/covid-trends/covid-trends.zip)
| Sept 6: [Python elements](https://github.com/YData123/sds265-fa22/raw/master/lectures/lecture-sept-06.pdf)
Sept 8: [Pandas and linear regression](https://github.com/YData123/sds265-fa22/raw/master/lectures/lecture-sept-08.pdf) | [Data8 Chapters 3](https://www.inferentialthinking.com/chapters/03/programming-in-python.html), [4](https://www.inferentialthinking.com/chapters/04/Data_Types.html), [5](https://www.inferentialthinking.com/chapters/05/Sequences.html) | Thu: [Quiz 1](https://yale.instructure.com/courses/79950/quizzes) | -3 | Sept 13, 15 | Linear regression and classification | [](https://colab.research.google.com/github/YData123/sds265-fa22/blob/master/demos/covid-trends/covid-trends-revisited.ipynb) [Covid trends (revisited)](https://github.com/YData123/sds265-fa22/raw/master/demos/covid-trends/covid-trends-revisited.zip)
[](https://colab.research.google.com/github/YData123/sds265-fa22/blob/master/demos/classification/classification.ipynb) [Classification examples](https://github.com/YData123/sds265-fa22/raw/master/demos/classification/classification.zip) | Sept 13: [Regression concepts](https://github.com/YData123/sds265-fa22/raw/master/lectures/lecture-sept-13.pdf)
Sept 15: [Classification](https://github.com/YData123/sds265-fa22/raw/master/lectures/lecture-sept-15.pdf) | ISL Sections 3.1, 3.2, 3.5
Notes on [regression](https://github.com/YData123/sds265-fa22/raw/master/notes/linear_regression.pdf)
ISL Sections 4.3, 4.4
[Notes on classification](https://github.com/YData123/sds265-fa22/raw/master/notes/linear_classification.pdf) | Thu: [](https://colab.research.google.com/github/YData123/sds265-fa22/blob/master/assignments/assn1/assn1.ipynb) [Assn 1](https://github.com/YData123/sds265-fa22/raw/master/assignments/assn1/assn1.zip) -4 | Sept 20, 22 | Stochastic gradient descent | [](https://colab.research.google.com/github/YData123/sds265-fa22/blob/master/demos/sgd/sgd.ipynb) [SGD examples](https://github.com/YData123/sds265-fa22/raw/master/demos/sgd/sgd.zip) | Sept 20: [Classification (continued)](https://github.com/YData123/sds265-fa22/raw/master/lectures/lecture-sept-20.pdf)
Sept 22: [Stochastic gradient descent](https://github.com/YData123/sds265-fa22/raw/master/lectures/lecture-sept-22.pdf) | ISL Section 6.2.2
ISL Section 10.7.2 | Thu: [Quiz 2](https://yale.instructure.com/courses/79950/quizzes)
| -5 | Sept 27, 29 | Bias and variance, cross-validation | [](https://colab.research.google.com/github/YData123/sds265-fa22/blob/master/demos/bias-variance/bias-variance.ipynb) [Bias-variance tradeoff](https://github.com/YData123/sds265-fa22/raw/master/demos/bias-variance/bias-variance.zip)
[](https://colab.research.google.com/github/YData123/sds265-fa22/blob/master/demos/covid-trends-bias-variance/covid-trends-bias-variance.ipynb) [Covid trends (revisited)](https://github.com/YData123/sds265-fa22/raw/master/demos/covid-trends-bias-variance/covid-trends-bias-variance.zip)
[](https://colab.research.google.com/github/YData123/sds265-fa22/blob/master/demos/cross-validation/california-housing.ipynb) [California housing](https://github.com/YData123/sds265-fa22/raw/master/demos/cross-validation/california-housing.zip) | Sept 27: [Bias and variance](https://github.com/YData123/sds265-fa22/raw/master/lectures/lecture-sept-27.pdf)
Sept 29: [Cross-validation](https://github.com/YData123/sds265-fa22/raw/master/lectures/lecture-sept-29.pdf) | ISL Section 2.2
ISL Section 5.1 | Thu: Assn 1 in
[](https://colab.research.google.com/github/YData123/sds265-fa22/blob/master/assignments/assn2/assn2.ipynb) [Assn 2 out](https://github.com/YData123/sds265-fa22/raw/master/assignments/assn2/assn2.zip) | -6 | Oct 4, 6 | Tree-based methods | [](https://colab.research.google.com/github/YData123/sds265-fa22/blob/master/demos/trees/trees.ipynb) [Trees and forests](https://github.com/YData123/sds265-fa22/raw/master/demos/trees/trees.zip)
[Visualizing trees](http://www.r2d3.us/visual-intro-to-machine-learning-part-1/)
[](https://colab.research.google.com/github/YData123/sds265-fa22/blob/master/demos/trees/bagging.ipynb) [Bagging operations](https://github.com/YData123/sds265-fa22/raw/master/demos/trees/bagging.zip) | Oct 4: [Trees](https://github.com/YData123/sds265-fa22/raw/master/lectures/lecture-oct-4.pdf)
Oct 6: [Forests](https://github.com/YData123/sds265-fa22/raw/master/lectures/lecture-oct-6.pdf) | ISL Sections 8.1, 8.2 | Thu: [Quiz 3](https://yale.instructure.com/courses/79950/quizzes)
| -7 | Oct 11, 13 | PCA and dimension reduction | [](https://colab.research.google.com/github/YData123/sds265-fa22/blob/master/demos/pca/pca.ipynb) [PCA examples](https://github.com/YData123/sds265-fa22/raw/master/demos/pca/pca.zip)
[](https://colab.research.google.com/github/YData123/sds265-fa22/blob/master/demos/pca/pca-demo-redux.ipynb) [PCA revisited](https://github.com/YData123/sds265-fa22/raw/master/demos/pca/pca-demo-redux.zip)
[](https://colab.research.google.com/github/YData123/sds265-fa22/blob/master/demos/pca/iris-pca.ipynb) [Used for regression](https://github.com/YData123/sds265-fa22/raw/master/demos/pca/iris-pca.zip) | Oct 11: [PCA](https://github.com/YData123/sds265-fa22/raw/master/lectures/lecture-oct-11.pdf)
Oct 13: [PCA and review](https://github.com/YData123/sds265-fa22/raw/master/lectures/lecture-oct-13.pdf) | ISL Section 12.2 | Thu: Assn 2 in
[](https://colab.research.google.com/github/YData123/sds265-fa22/blob/master/assignments/assn3/assn3.ipynb) [Assn 3 out](https://github.com/YData123/sds265-fa22/raw/master/assignments/assn3/assn3.zip) -8 | Oct 18 | Midterm exam (in class) | | | On Canvas:
[Practice midterms](https://yale.instructure.com/courses/79950/files/folder/practice_midterms) / [Sample solns](https://yale.instructure.com/courses/79950/files/folder/practice_midterms/)
[Midterm](https://yale.instructure.com/courses/79950/files/folder/midterm/) / [Sample soln](https://yale.instructure.com/courses/79950/files/folder/midterm/) -9 | Oct 25, 27 | Language models, word embeddings | [](https://colab.research.google.com/github/YData123/sds265-fa22/blob/master/demos/language-models/hello_gpt3.ipynb) [GPT-3 demo](https://github.com/YData123/sds265-fa22/raw/master/demos/language-models/hello_gpt3.zip)
[](https://colab.research.google.com/github/YData123/sds265-fa22/blob/master/demos/embeddings/embeddings.ipynb) [Word embeddings](https://github.com/YData123/sds265-fa22/raw/master/demos/embeddings/embeddings.zip) | Oct 25: [Language models](https://github.com/YData123/sds265-fa22/raw/master/lectures/lecture-oct-25.pdf)
Oct 27: [Word embeddings](https://github.com/YData123/sds265-fa22/raw/master/lectures/lecture-oct-27.pdf) | [OpenAI: Better language models](https://openai.com/blog/better-language-models/) (GPT-2) | [](https://colab.research.google.com/github/YData123/sds265-fa22/blob/master/assignments/assn4/assn4.ipynb) [Assn 4 out](https://github.com/YData123/sds265-fa22/raw/master/assignments/assn4/assn4.zip) -10 | Nov 1, 3 | Bayesian inference, topic models | [](https://colab.research.google.com/github/YData123/sds265-fa22/blob/master/demos/bayes/mix.ipynb) [Mixtures](https://github.com/YData123/sds265-fa22/raw/master/demos/bayes/mix.zip)
[](https://colab.research.google.com/github/YData123/sds265-fa22/blob/master/demos/bayes/bayes.ipynb) [Bayesian inference](https://github.com/YData123/sds265-fa22/raw/master/demos/bayes/bayes.zip)
[](https://colab.research.google.com/github/YData123/sds265-fa22/blob/master/demos/topic-models/topic-models.ipynb) [Topic models](https://github.com/YData123/sds265-fa22/raw/master/demos/topic-models/topic-models.zip) | Nov 1: [Bayesian inference](https://github.com/YData123/sds265-fa22/raw/master/lectures/lecture-nov-1.pdf)
Nov 3: [Bayes and topic models](https://github.com/YData123/sds265-fa22/raw/master/lectures/lecture-nov-3.pdf) | [Notes on Bayesian inference](https://github.com/YData123/sds265-fa22/raw/master/notes/bayes-notes.pdf) | Tue: Assn 3 in
Thu: [Quiz 4](https://yale.instructure.com/courses/79950/quizzes) -11 | Nov 8, 10 | Introduction to neural networks | [](https://colab.research.google.com/github/YData123/sds265-fa22/blob/master/demos/neural-nets/sanity-check.ipynb) [Sanity check](https://github.com/YData123/sds265-fa22/raw/master/demos/neural-nets/sanity-check.zip)
[](https://colab.research.google.com/github/YData123/sds265-fa22/blob/master/demos/neural-nets/neural-nets.ipynb) [Minimal neural network](https://github.com/YData123/sds265-fa22/raw/master/demos/neural-nets/neural-nets.zip)
[](https://colab.research.google.com/github/YData123/sds265-fa22/blob/master/demos/neural-nets/neural-nets-regress.ipynb) [Regression examples](https://github.com/YData123/sds265-fa22/raw/master/demos/neural-nets/neural-nets-regress.zip) | Nov 8: [Topic models](https://github.com/YData123/sds265-fa22/raw/master/lectures/lecture-nov-8.pdf)
Nov 10: [Neural networks](https://github.com/YData123/sds265-fa22/raw/master/lectures/lecture-nov-10.pdf) | ISL Sections 10.1, 10.2 | Thu: Assn 4 in
[](https://colab.research.google.com/github/YData123/sds265-fa22/blob/master/assignments/assn5/assn5.ipynb) [Assn 5 out](https://github.com/YData123/sds265-fa22/raw/master/assignments/assn5/assn5.zip) -12 | Nov 15, 17 | Deep neural networks | [Tensorflow playground](https://playground.tensorflow.org/)
[](https://colab.research.google.com/github/YData123/sds265-fa22/blob/master/demos/deep-nets/deep-nets.ipynb) [Autoencoder examples](https://github.com/YData123/sds265-fa22/raw/master/demos/deep-nets/deep-nets.zip) | Nov 15: [Neural networks (continued)](https://github.com/YData123/sds265-fa22/raw/master/lectures/lecture-nov-15.pdf) Nov 17: [Autoencoders](https://github.com/YData123/sds265-fa22/raw/master/lectures/lecture-nov-17.pdf) | ISL Section 10.7
[Notes on backpropagation](https://github.com/YData123/sds265-fa22/raw/master/notes/backprop.pdf) | Thu: [Quiz 5]() -13 | Nov 22, 24 | No class, Thanksgiving break | | | -14 | Nov 29, Dec 1 | Reinforcement learning | [](https://colab.research.google.com/github/YData123/sds265-fa22/blob/master/demos/reinforcement-learning/reinforcement-learning.ipynb) [Q-learning](https://github.com/YData123/sds265-fa22/raw/master/demos/reinforcement-learning/reinforcement-learning.zip) | Nov 29: [Reinforcement learning](https://github.com/YData123/sds265-fa22/raw/master/lectures/lecture-nov-29.pdf)
Dec 1: [Deep reinforcement learning](https://github.com/YData123/sds265-fa22/raw/master/lectures/lecture-dec-1.pdf) | | Thu: Assn 5 in
[](https://colab.research.google.com/github/YData123/sds265-fa22/blob/master/assignments/assn6/assn6.ipynb) [Assn 6 out](https://github.com/YData123/sds265-fa22/raw/master/assignments/assn6/assn6.zip) -15 | Dec 6, 8 | Societal issues for machine learning | | Dec 6: [Societal issues](https://github.com/YData123/sds265-fa22/raw/master/lectures/lecture-dec-6.pdf)
Dec 8: [Course wrap up](https://github.com/YData123/sds265-fa22/raw/master/lectures/lecture-dec-8.pdf) | | Tue: [Quiz 6]() -16 | Dec 15 | | | | | Thu: Assn 6 in -17 | Mon, Dec 19, 7pm, Davies Aud | Final exam | | | [Registrar: Final exam schedule](https://registrar.yale.edu/general-information/final-exams/)
[Practice final](https://yale.instructure.com/courses/79950/files/folder/practice_finals/) diff --git a/fa24/introml/calendar.md.bup b/fa24/introml/calendar.md.bup deleted file mode 100644 index e4e16223..00000000 --- a/fa24/introml/calendar.md.bup +++ /dev/null @@ -1,52 +0,0 @@ - - Introductory Machine Learning - - - - - -![neuro-datascience](./data-neuroscience.jpg) - - -Introductory Machine Learning -==== - -S&DS 265 introduces some of the key ideas and techniques in machine learning. Algorithms and concepts are presented to build intuition for how different methods work, without advanced mathematics. Assignments give students hands-on experience with the methods on different types of data. Topics include linear regression and classification, tree-based methods, topic models, language models, word embeddings, two-layer and recurrent neural networks, reinforcement learning, and an introduction to deep learning. Examples come from a variety of sources including political speeches, archives of scientific articles, real estate listings, and natural images. Programming is central to the course, and is based on the Python programming language. - -Computing for the course uses Python in Jupyter notebooks. These can be run using [Anaconda](https://www.anaconda.com/products/individual) with the [iML environment](https://raw.githubusercontent.com/YData123/sds265-fa22/master/env/iml_env.yml) adopted by the course (click here to download) -; instructions for installing this environment are available on [Yale Canvas](https://canvas.yale.edu). The notebooks can also be run in [Google Colab](https://colab.research.google.com) by clicking on the [](https://colab.research.google.com) icon. - - -
- -Calendar Fall 2023 ---- -Lectures: Tuesday/Thursday 11:35-12:50pm -
-[Davies Auditorium](https://map.yale.edu/?id=1910#!m/563685?ct/52707) - -Complementary readings marked ISL refer to sections in the book [An Introduction to Statistical Learning](https://hastie.su.domains/ISLP/ISLP_website.pdf) (Python version, July 2023). Assignments and quizzes are posted and due on Thursday in a given week. -
- - - - - - Week | Dates | Topics | Demos & Tutorials | Lecture Slides | Readings and Notes | Assignments & Exams ------------ | ----------- | ------------- | ------------ | ------------- | ----------- | ------------ -1 | Aug 31 | Course overview | | Thu: [Course overview](https://github.com/YData123/sds265-fa23/raw/main/lectures/lecture-aug-31.pdf) | -2 | Sept 5, 7 | Python and background concepts | [](https://colab.research.google.com/github/YData123/sds265-fa23/blob/main/demos/python/python-elements.ipynb) [Python elements](https://github.com/YData123/sds265-fa23/raw/main/demos/python/python-elements.zip)
[](https://colab.research.google.com/github/YData123/sds265-fa22/blob/master/demos/covid-trends/covid-trends.ipynb) [Covid trends](https://github.com/YData123/sds265-fa22/raw/master/demos/covid-trends/covid-trends.zip)
| Tue: [Python elements](https://github.com/YData123/sds265-fa23/raw/main/lectures/lecture-sept-5.pdf)
Thu: [Pandas and linear regression](https://github.com/YData123/sds265-fa23/raw/main/lectures/lecture-sept-7.pdf) | [Data8 Chapters 3](https://www.inferentialthinking.com/chapters/03/programming-in-python.html), [4](https://www.inferentialthinking.com/chapters/04/Data_Types.html), [5](https://www.inferentialthinking.com/chapters/05/Sequences.html) | [Quiz 1](https://yale.instructure.com/courses/88623/quizzes)
[](https://colab.research.google.com/github/YData123/sds265-fa23/blob/main/assignments/assn1/assn1.ipynb) [Assn 1 out](https://github.com/YData123/sds265-fa23/raw/main/assignments/assn1/assn1.zip) | -3 | Sept 12, 14 | Linear regression and classification | [](https://colab.research.google.com/github/YData123/sds265-fa23/blob/main/demos/covid-trends/covid-trends-revisited.ipynb) [Covid trends (revisited)](https://github.com/YData123/sds265-fa23/raw/main/demos/covid-trends/covid-trends-revisited.zip)
[](https://colab.research.google.com/github/YData123/sds265-fa23/blob/main/demos/classification/classification.ipynb) [Classification examples](https://github.com/YData123/sds265-fa23/raw/main/demos/classification/classification.zip) | Tue: [Regression concepts](https://github.com/YData123/sds265-fa23/raw/main/lectures/lecture-sept-12.pdf)
Thu: [Classification](https://github.com/YData123/sds265-fa23/raw/main/lectures/lecture-sept-14.pdf) | ISL Sections 3.1, 3.2, 3.5
Notes on [regression](https://github.com/YData123/sds265-fa22/raw/master/notes/linear_regression.pdf)
ISL Sections 4.3, 4.4
[Notes on classification](https://github.com/YData123/sds265-fa22/raw/master/notes/linear_classification.pdf) | -4 | Sept 19, 21 | Stochastic gradient descent | [](https://colab.research.google.com/github/YData123/sds265-fa22/blob/master/demos/sgd/sgd.ipynb) [SGD examples](https://github.com/YData123/sds265-fa22/raw/master/demos/sgd/sgd.zip) | Tue: [Classification (continued)](https://github.com/YData123/sds265-fa23/raw/main/lectures/lecture-sept-19.pdf)
Thu: [Stochastic gradient descent](https://github.com/YData123/sds265-fa23/raw/main/lectures/lecture-sept-21.pdf) | ISL Section 6.2.2
ISL Section 10.7.2 | Assn 1 in
[](https://colab.research.google.com/github/YData123/sds265-fa23/blob/main/assignments/assn2/assn2.ipynb) [Assn 2 out](https://github.com/YData123/sds265-fa23/raw/main/assignments/assn2/assn2.zip)
| -5 | Sept 26, 28 | Bias and variance, cross-validation | [](https://colab.research.google.com/github/YData123/sds265-fa22/blob/master/demos/bias-variance/bias-variance.ipynb) [Bias-variance tradeoff](https://github.com/YData123/sds265-fa22/raw/master/demos/bias-variance/bias-variance.zip)
[](https://colab.research.google.com/github/YData123/sds265-fa22/blob/master/demos/covid-trends-bias-variance/covid-trends-bias-variance.ipynb) [Covid trends (revisited)](https://github.com/YData123/sds265-fa22/raw/master/demos/covid-trends-bias-variance/covid-trends-bias-variance.zip)
[](https://colab.research.google.com/github/YData123/sds265-fa22/blob/master/demos/cross-validation/california-housing.ipynb) [California housing](https://github.com/YData123/sds265-fa22/raw/master/demos/cross-validation/california-housing.zip) | Tue: [Bias and variance](https://github.com/YData123/sds265-fa23/raw/main/lectures/lecture-sept-26.pdf)
Thu: [Cross-validation](https://github.com/YData123/sds265-fa23/raw/main/lectures/lecture-sept-28.pdf) | ISL Section 2.2
ISL Section 5.1 | [Quiz 2](https://yale.instructure.com/courses/88623/quizzes) | -6 | Oct 3, 5 | Tree-based methods and
principal components | [](https://colab.research.google.com/github/YData123/sds265-fa22/blob/master/demos/trees/trees.ipynb) [Trees and forests](https://github.com/YData123/sds265-fa22/raw/master/demos/trees/trees.zip)
[Visualizing trees](http://www.r2d3.us/visual-intro-to-machine-learning-part-1/)
[](https://colab.research.google.com/github/YData123/sds265-fa22/blob/master/demos/pca/pca.ipynb) [PCA examples](https://github.com/YData123/sds265-fa22/raw/master/demos/pca/pca.zip) | Tue: [Trees and Forests](https://github.com/YData123/sds265-fa23/raw/main/lectures/lecture-oct-3.pdf)
Thu: [PCA](https://github.com/YData123/sds265-fa23/raw/main/lectures/lecture-oct-5.pdf) | ISL Sections 8.1, 8.2
ISL Section 12.2 | Assn 2 in
[](https://colab.research.google.com/github/YData123/sds265-fa23/blob/main/assignments/assn3/assn3.ipynb) [Assn 3 out](https://github.com/YData123/sds265-fa23/raw/main/assignments/assn3/assn3.zip)
| -7 | Oct 10, 12 | PCA and dimension reduction | [](https://colab.research.google.com/github/YData123/sds265-fa23/blob/main/demos/pca/pca-demo-redux.ipynb) [PCA revisited](https://github.com/YData123/sds265-fa23/raw/main/demos/pca/pca-demo-redux.zip)
[](https://colab.research.google.com/github/YData123/sds265-fa23/blob/main/demos/pca/iris-pca.ipynb) [Used for dimension reduction](https://github.com/YData123/sds265-fa23/raw/main/demos/pca/iris-pca.zip)
[](https://colab.research.google.com/github/YData123/sds265-fa23/blob/main/demos/embeddings/embeddings.ipynb) [Word embeddings](https://github.com/YData123/sds265-fa23/raw/main/demos/embeddings/embeddings.zip)| Tue: [PCA and word embeddings](https://github.com/YData123/sds265-fa23/raw/main/lectures/lecture-oct-10.pdf)
Thu: [Embeddings and review](https://github.com/YData123/sds265-fa23/raw/main/lectures/lecture-oct-12.pdf) | ISL Section 12.2 | [Quiz 3](https://yale.instructure.com/courses/88623/quizzes) -8 | Oct 17 | Midterm exam (in class) | | | On Canvas:
[Practice midterms](https://yale.instructure.com/courses/88623/files/folder/practice_midterms) / [Sample solns](https://yale.instructure.com/courses/88623/files/folder/practice_midterms/)
[Midterm](https://yale.instructure.com/courses/88623/files/folder/midterm/) / [Sample soln](https://yale.instructure.com/courses/88623/files/folder/midterm/) -9 | Oct 24, 26 | Language models, word embeddings | [](https://colab.research.google.com/github/YData123/sds265-fa22/blob/master/demos/language-models/hello_gpt3.ipynb) [GPT-3 demo](https://github.com/YData123/sds265-fa22/raw/master/demos/language-models/hello_gpt3.zip)
[](https://colab.research.google.com/github/YData123/sds265-fa22/blob/master/demos/embeddings/embeddings.ipynb) [Word embeddings](https://github.com/YData123/sds265-fa22/raw/master/demos/embeddings/embeddings.zip) | Tue: [Language models](https://github.com/YData123/sds265-fa23/raw/main/lectures/lecture-oct-25.pdf)
Thu: [Word embeddings](https://github.com/YData123/sds265-fa23/raw/main/lectures/lecture-oct-27.pdf) | [OpenAI: Better language models](https://openai.com/blog/better-language-models/) (GPT-2) | Assn 3 in
[]() [Assn 4 out]() -10 | Oct 31, Nov 2 | Bayesian inference, topic models | [](https://colab.research.google.com/github/YData123/sds265-fa22/blob/master/demos/bayes/mix.ipynb) [Mixtures](https://github.com/YData123/sds265-fa22/raw/master/demos/bayes/mix.zip)
[](https://colab.research.google.com/github/YData123/sds265-fa22/blob/master/demos/bayes/bayes.ipynb) [Bayesian inference](https://github.com/YData123/sds265-fa22/raw/master/demos/bayes/bayes.zip)
[](https://colab.research.google.com/github/YData123/sds265-fa22/blob/master/demos/topic-models/topic-models.ipynb) [Topic models](https://github.com/YData123/sds265-fa22/raw/master/demos/topic-models/topic-models.zip) | Tue: [Bayesian inference](https://github.com/YData123/sds265-fa23/raw/main/lectures/lecture-nov-1.pdf)
Thu: [Topic models](https://github.com/YData123/sds265-fa23/raw/main/lectures/lecture-nov-3.pdf) | [Notes on Bayesian inference](https://github.com/YData123/sds265-fa22/raw/master/notes/bayes-notes.pdf) | [Quiz 4]() -11 | Nov 7, 9 | Introduction to neural networks | [](https://colab.research.google.com/github/YData123/sds265-fa22/blob/master/demos/neural-nets/sanity-check.ipynb) [Sanity check](https://github.com/YData123/sds265-fa22/raw/master/demos/neural-nets/sanity-check.zip)
[](https://colab.research.google.com/github/YData123/sds265-fa22/blob/master/demos/neural-nets/neural-nets.ipynb) [Minimal neural network](https://github.com/YData123/sds265-fa22/raw/master/demos/neural-nets/neural-nets.zip)
[](https://colab.research.google.com/github/YData123/sds265-fa22/blob/master/demos/neural-nets/neural-nets-regress.ipynb) [Regression examples](https://github.com/YData123/sds265-fa22/raw/master/demos/neural-nets/neural-nets-regress.zip) | Tue: [Neural networks](https://github.com/YData123/sds265-fa23/raw/main/lectures/lecture-nov-8.pdf)
Thu: [Neural networks](https://github.com/YData123/sds265-fa23/raw/main/lectures/lecture-nov-10.pdf) | ISL Sections 10.1, 10.2 | Assn 4 in
[]() [Assn 5 out]() -12 | Nov 14, 16 | Reinforcement learning | [](https://colab.research.google.com/github/YData123/sds265-fa22/blob/master/demos/reinforcement-learning/reinforcement-learning.ipynb) [Q-learning](https://github.com/YData123/sds265-fa22/raw/master/demos/reinforcement-learning/reinforcement-learning.zip) | Tue: [Reinforcement learning](https://github.com/YData123/sds265-fa23/raw/main/lectures/lecture-nov-29.pdf)
Thu: [Deep reinforcement learning](https://github.com/YData123/sds265-fa23/raw/main/lectures/lecture-dec-1.pdf) | | [Quiz 5]() -13 | Nov 21, 23 | No class, Thanksgiving break | | | -14 | Nov 28, 30 | Deep neural networks | [Tensorflow playground](https://playground.tensorflow.org/)
[](https://colab.research.google.com/github/YData123/sds265-fa22/blob/master/demos/deep-nets/deep-nets.ipynb) [Autoencoder examples](https://github.com/YData123/sds265-fa22/raw/master/demos/deep-nets/deep-nets.zip) | Tue: [Deep neural networks](https://github.com/YData123/sds265-fa23/raw/main/lectures/lecture-nov-15.pdf)
Thu: [Autoencoders](https://github.com/YData123/sds265-fa23/raw/main/lectures/lecture-nov-17.pdf) | ISL Section 10.7
[Notes on backpropagation](https://github.com/YData123/sds265-fa22/raw/master/notes/backprop.pdf) | Assn 5 in
-15 | Dec 5, 7 | Societal issues for machine learning | | Tue: [Societal issues](https://github.com/YData123/sds265-fa23/raw/main/lectures/lecture-dec-6.pdf)
Thu: [Course wrap up](https://github.com/YData123/sds265-fa23/raw/main/lectures/lecture-dec-8.pdf) | | [Quiz 6]()
-16 | Fri, Dec 15, 2pm, Room TBA | Final exam | | | [Registrar: Final exam schedule](https://registrar.yale.edu/general-information/final-exams/)
[Practice final](https://yale.instructure.com/courses/88623/files/folder/practice_finals/) diff --git a/fa24/introml/test.md b/fa24/introml/test.md deleted file mode 100644 index d00632bb..00000000 --- a/fa24/introml/test.md +++ /dev/null @@ -1,20 +0,0 @@ - - Introductory Machine Learning - - - - - -![neuro-datascience](./data-neuroscience.jpg) - - -Introductory Machine Learning -==== - -S&DS 265 introduces some of the key ideas and techniques in machine learning. Algorithms and concepts are presented to build intuition for how different methods work, without advanced mathematics. Assignments give students hands-on experience with the methods on different types of data. Topics include linear regression and classification, tree-based methods, topic models, language models, word embeddings, two-layer and recurrent neural networks, reinforcement learning, and an introduction to deep learning. Examples come from a variety of sources including political speeches, archives of scientific articles, real estate listings, and natural images. Programming is central to the course, and is based on the Python programming language and Jupyter notebooks. - -Computing for the course uses Python in Jupyter notebooks. These can be run using [Anaconda](https://www.anaconda.com/products/individual) with the [iML environment](https://raw.githubusercontent.com/YData123/sds265-fa21/main/env/iml_env.yml) adopted by the course (click here to download) -; instructions for installing this environment are available on [Yale Canvas](https://canvas.yale.edu). The notebooks can also be run in [Google Colab](https://colab.research.google.com) by clicking on the [](https://colab.research.google.com) icon. - - -[![Alternate Text](./data-neuroscience.jpg)](https://github.com/ClarkLabCode/LoomDetectionANN/blob/main/results/movies_exp/video2_combined_movies_M1_miss.mp4 "Link Title") diff --git a/fa24/introml/texput.log b/fa24/introml/texput.log deleted file mode 100644 index 7f483b45..00000000 --- a/fa24/introml/texput.log +++ /dev/null @@ -1,21 +0,0 @@ -This is pdfTeX, Version 3.14159265-2.6-1.40.19 (TeX Live 2018) (preloaded format=pdflatex 2018.4.16) 7 NOV 2023 07:50 -entering extended mode - restricted \write18 enabled. - %&-line parsing enabled. -**lecture-nov-7 - -! Emergency stop. -<*> lecture-nov-7 - -End of file on the terminal! - - -Here is how much of TeX's memory you used: - 4 strings out of 492649 - 112 string characters out of 6129622 - 56311 words of memory out of 5000000 - 3988 multiletter control sequences out of 15000+600000 - 3640 words of font info for 14 fonts, out of 8000000 for 9000 - 1141 hyphenation exceptions out of 8191 - 0i,0n,0p,20b,6s stack positions out of 5000i,500n,10000p,200000b,80000s -! ==> Fatal error occurred, no output PDF file produced!