Textbooks

Other materials

The following is a tentative schedule for the course. Please check back regularly for updates as the term progresses.

Thu Jun 20

No class

Fri Jun 21

Lecture: Artificial intelligence: Ideas and their evolution

Keywords: Turing test, Dartmouth workshop, expert systems, strong AI, weak AI, artificial general intelligence (AGI)

Reading material:

Mon Jun 24

Lecture: Knowledge and reason

Keywords: tables, functions, frames, semantic networks, knowledge graphs

Reading material:

Wed Jun 26

Lecture: Probabilistic graphical models

Keywords: directed acyclic graphs, Bayesian networks, Markov random fields (MRFs), factor graphs

Reading material:

Thu Jun 27

Lecture: Inference on probabilistic graphical models

Keywords: conditional probabilities, random variables, Bayes' theorem, message passing / belief propagation

Reading material:

Fri Jun 28

Lecture: Linear regression

Keywords: linear regression, train-test split, quality of fit, residual sum of squares (RSS), mean squared error (MSE), R squared, ordinary least squares (OLS), Gauss-Markov theorem, collinearity, heteroscedasticity

Reading material:

Mon Jul 1

Lecture: Review of linear algebra

Keywords:vectors, matrices, linear transformations, change of basis, eigenbasis, eigendecomposition, singular value decomposition

Reading material:

Wed Jul 3

Lecture: Regression and classification

Keywords: the bias-variance tradeoff, 1-hot encoding, discriminative models, logistic regression, k-nearest neighbors (KNN), generative models, decision boundary, linear discriminant analysis (LDA), quadratic discriminant analysis (QDA), naive Bayes

Reading material:

Thu Jul 4

No class on Independence Day.

Fri Jul 5

Lecture: Resampling and validation

Keywords: holdout set, validation accuracy, crossvalidation, leave-one-out crossvalidation (LOOCV), bootstrap, data leakage, imputation

Reading material:

Mon Jul 8

Lecture: Feature selection

Keywords: shrinkage, best subset selection, stepwise forward selection, stepwise backward selection

Reading material:

Wed Jul 10

Lecture: Regularization

Keywords: curse of dimensionality, Lp norm, gradient descent, ridge regression, lasso, elastic net, feature engineering, dimension reduction, principal component analysis (PCA), principal component regression (PCR)

Reading material:

Thu Jul 11

Code lab

Fri Jul 12

Lecture: Decision trees

Keywords: regression trees, classification trees, tree ensemble methods, bagging, boosting, random forests, Bayesian additive regression trees (BART)

Reading material:

Mon Jul 15

Lecture: Support vector machines

Keywords: linearly separable patterns, maximum-margin models, hard margin, soft margin, support vector classifier, loss functions for binary classification

Reading material:

Wed Jul 17

Lecture: Function approximation

Keywords:feature mapping, feature augmentations, linear classifiers with non-linear decision boundaries, manifold learning, infinite-dimensional vector spaces, function spaces, random features, Koopman operator

Reading material:

Thu Jul 18

Code lab

Fri Jul 19

Lecture: Kernel methods

Keywords: linear kernels, non-linear kernels, kernel trick, Hilbert spaces, reproducing-kernel Hilbert spaces, representer theorems

Reading material:

Mon Jul 22

Lecture: Introduction to neural networks: Perceptron and beyond

Keywords: perceptron, activation function, ReLU, perceptron learning algorithm, stochastic gradient descent, epoch, mini-batch, momentum, RMSProp, Adam

Reading material:

Wed Jul 24

Lecture: Neural network architectures and neural coding

Keywords: feed-forward neural network, softmax, deep learning, encoder, decoder, convolutional neural networks (CNNs)

Reading material:

o

Thu Jul 25

Code lab

Fri Jul 26

Lecture: Training and regularizing neural networks

Keywords: backpropagation, double descent, drop out, early stopping, regularization

Reading material:

Mon Jul 29

Lecture: Forecasting and prediction

Keywords: Taken's theorem, time-delayed embedding, recurrent neural networks (RNNs), reservoir computing

Reading material:

Wed Jul 31

Lecture: Natural language processing

Keywords: structured prediction, text classification, bag of words, self-supervised learning, word embeddings

Reading material:

Thu Aug 1

Code lab

Fri Aug 2

Lecture: Natural language processing (continued)

Keywords: long-term short-term memory, attention, transformer, generative pre-trained transformers (GPTs)

Reading material:

Mon Aug 5

Project proposals

Wed Aug 7

Lecture: Representation learning

Keywords: latent space, autoencoders, restricted Boltzmann machines (RBMs)

Reading material:

Thu Aug 8

Code lab

Fri Aug 9

Lecture: Clustering

Keywords: k-means clustering, hierarchical clustering

Reading material:

Mon Aug 12

Lecture: The topology of data

Keywords: self-organizing maps (SOMs), competitive learning, topological data analysis (TDA)

Reading material:

Wed Aug 14

Lecture: Matrix completion

Keywords: Low rank matrix completion, high rank matrix completion, link prediction, recommender systems

Reading material:

Thu Aug 15

Code lab

Fri Aug 16

Lecture: Network analysis

Keywords: centrality measures, community detection, modularity maximization, belief propagation

Reading material:

Mon Aug 19

Final project presentations

Wed Aug 21

Final project presentations

Lecture: Transfer learning

Keywords: teacher-student learning, multitask learning

Reading material:

• TBD

Lecture: Image generation and more transfer learning

Keywords: general adversarial networks (GANs), contrastive language-image pre-training (CLIP), DALL-E, diffusion

Reading material:

• TBD

TBA

In person lectures and office hours

Lectures and office hours will generally be held in person. From time to time, it may be announced in class or on CANVAS that lectures or office hours will be conducted via zoom. Individual appointments with your instructor may be held remotely via zoom, especially those made for late afternoon.

Grading

The course grade will be based upon on

• weekly in-class quizzes (total 50 points),
• weekly homework problems (total 100 points),
• class participation, which may involve presenting a blog post or research paper in class, (total 100 points),
• and a final coding project to be completed by the final week of classes (total 250 points). This project can be a group project.

Academic Honor Principle

For quizzes and all other assessments, Dartmouth's Academic Honor Principle will be upheld. Please be advised of especially

• Quizzes: Giving and/or receiving assistance during an examination violates the Academic Honor Principle.
• Homework and course projects: Collaboration is both permitted and encouraged, but it is a violation of the honor code for someone to provide the answers for you.

Student Religious Observances

Some students may wish to take part in religious observances that fall during this academic term. Should you have a religious observance that conflicts with your participation in the course, please come speak with your instructor before the end of the second week of the term to discuss appropriate accommodations.