— Tuesday
— Thursday

Readings:

— Catching Crumbs from the Table, Ted Chiang
— Can Computers Create Art?, Aaron Hertzmann
— How Frightened Should We Be of A.I.?, Tad Friend
— Eulerian Video Magnification for Revealing Subtle Changes in the World, Hao-Yu Wu, Michael Rubinstein, Eugene Shih, John Guttag, Frédo Durand, and William T. Freeman
— Micromigrations, Dennis Hylynsky
— A Generative Framework of Generativity, Kate Compton and Michael Mateas
— The Wavefunction Collapse Algorithm Explained Very Clearly, Robert Heaton
— WaveFunctionCollapse is Constraint Solving in the Wild, Isaac Karth and Adam M. Smith
— Infinite Procedurally Generated City with the Wave Function Collapse Algorithm, Marian Kleineberg
— Generating Paths with WFC, Hugo Scurti and Clark Verbrugge
— Generating Worlds With Wave Function Collapse, Joseph Parker

Code:

— Eulerian Video Magnification, Hao-Yu Wu, Michael Rubinstein, Eugene Shih, John Guttag, Frédo Durand, and William T. Freeman
— WaveFunctionCollapse, Maxim Gumin
— Even Simpler Tiled Model, Robert Heaton
— Infinite City WFC, Marian Kleineberg

Assignments:

— Homework 1, due 1/14
— Project 1, due 1/17

— Tuesday
— Thursday (installing TensorFlow)

Readings:

— Trending: The Promises and the Challenges of Big Social Data, Lev Manovich
— Can We Think without Categories?, Lev Manovich
— Why Distant Reading Isn’t, Johanna Drucker
— What is Humanities Computing (and What is Not)?, John Unsworth
— Why an Age of Machine Learning Needs the Humanities, Ted Underwood

Code

— Wekinator, Software for real-time, interactive machine learning
— Python, A programming language that lets you work quickly and integrate systems more effectively
— TensorFlow, An open source machine learning framework for everyone
— Anaconda, Python data science platform
— Jupyter, Open source notebook software
— SciPy.org, Python-based ecosystem of open-source software for mathematics, science, and engineering (including NumPy, SciPy, Matplotlib, etc).

Assignments:

— Homework 2, due 1/21

— Tuesday
— Thursday (CNNs)

Readings:

— What Neural Networks See, Gene Kogan
— Dramaturgical Theorizing, Jonathan H. Turner
— Art and Science of Engineered Design: What Kind of Discipline is PCG?, Jim Whitehead
— Procedural Content Generation via Machine Learning, Adam Summerville, Sam Snodgrass, Matthew Guzdial, Christoffer Holmgård, Amy K. Hoover, Aaron Isaksen, Andy Nealen, and Julian Togelius
— Meshworks, Hierarchies and Interfaces, Manuel De Landa
— Computational and Cognitive Infrastructures of Stigma: Empowering Identity in Social Computing and Gaming, D. Fox Harrell
— The Incomputable and Instrumental Possibility, Antonia Majaca and Luciana Parisi

Code & Tutorials:

— Quick, Draw!
— Deep Playground
— An Interactive Node-Link Visualization of Convolutional Neural Networks, Adam Harley
— 3Blue1Brown’s Intro to Neural Network Series (4 episodes), Grant Sanderson
— TensorFlow for Poets
— TensorFlow’s Advanced CNN Tutorial
— CV-Trick’s Image Classifier Tutorial
— Hvass Laboratories’ CNN Video Tutorial

Events:

— The Humanities Institute’s Data and Democracy panel discussion at Kuumbwa Jazz Center, January 29th at 7pm.
— Meetup on Convolutional Neural Networks and Deep Learning at NextSpace, January 29th from 6:30pm to 8:30pm.

Assignments:

— Homework 3, due 1/30

— Tuesday (Autoencoders)
— Thursday (GANs)

Readings / Videos / Code:

— Sonic Meditations and Quantum Listening, Pauline Oliveros
— Chapter VII: Towards a Metamusic and Chapter X: Concerning Time, Space, and Music, Iannis Xenakis
— Why Do We Want Our Computers to Improvise?, George E. Lewis
— The Unreasonable Effectiveness of Recurrent Neural Networks, Andrej Karpathy
— A First Look at Music Composition Using LSTM Recurrent Neural Networks, Douglas Eck and Jurgen Schmidhuber
— Making Music Through Machine Ears, David Kant
— WaveNet: A Generative Model for Raw Audio, DeepMind
— NSynth, Google Magenta
— MusicVAE, Google Magenta

Assignments:

— Homework 4, due 2/4
— Project 2, due 2/12

— David Kant, UCSC Department of Music

Slides:

— Decomposing Music and Contemporary Trends in Music AI
— Thursday (GANs)

Readings / Videos / Code:

— Generative Adversarial Nets, Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio
— GAN Breeder, Joel Simon
— How Three French Students Used Borrowed Code to Put the First AI Portrait In Christie’s, James Vincent
— Robbie Barrat and Ronan Barrot’s Infinite Skulls, Jason Bailey
— All About the GAN, Jonathan Jeon
— GAN Timeline, Zheng Liu
— Generating Handwritten Digits with DCGAN, TensorFlow
— Image Completion with Deep Learning in TensorFlow, Brandon Amos
— Interactive Image Translation with pix2pix-tensorflow, Christopher Hesse
— Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network, Christian Ledig, Lucas Theis, Ferenc Huszar, Jose Caballero, Andrew Cunningham, Alejandro Acosta, Andrew Aitken, Alykhan Tejani, Johannes Totz, Zehan Wang, and Wenzhe Shi
— A Style-Based Generator Architecture for Generative Adversarial Networks (with TensorFlow code), Tero Karras, Samuli Laine, and Timo Aila
— #BigGAN Take Your Brain to Another Dimension, Memo Atken
— Imaginary Worlds Dreamed by BigGAN, Janelle Shane
— Generating Videos with Scene Dynamics, Carl Vondrick, Hamed Pirsiavash, and Antonio Torralba
— Image-to-Image Translation with Conditional Adversarial Networks, Phillip Isola, Jun-Yan Zhu, Tinghui Zhou, and Alexei A. Efros
— Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks, Jun-Yan Zhu, Taesung Park, Phillip Isola, and Alexei A. Efros
— Deep Illumination, Manu Thomas and Angus Forbes
— Everybody Dance Now, Caroline Chan, Shiry Ginosar, Tinghui Zhou, and Alexei A. Efros
— Everybody Dance Now! Explained, Siraj Raval
— Why It Is So Hard to Train Generative Adversarial Networks!, Jonathan Hui
— SC-FEGAN : Face Editing Generative Adversarial Network with User’s Sketch and Color, Youngjoo Jo and Jongyoul Park

— Final Project, due 3/22 (with checkpoints and presentations along the way)

Readings / Videos / Code:

— Better Language Models and Their Implications, Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, and Ilya Sutskever
— Google DeepMind’s Deep Q-Learning & Superhuman Atari Gameplays, Two Minute Papers
— Human-level Control through Deep Reinforcement Learning, Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Andrei A. Rusu, Joel Veness, Marc G. Bellemare, Alex Graves, Martin Riedmiller, Andreas K. Fidjeland, Georg Ostrovski, Stig Petersen, Charles Beattie, Amir Sadik, Ioannis Antonoglou, Helen King, Dharshan Kumaran, Daan Wierstra, Shane Legg, and Demis Hassabis
— AlphaZero: Shedding New Light on the Grand Games of Chess, Shogi, and Go, DeepMind
— AlphaStar: Mastering the Real-Time Strategy Game StarCraft II and video, DeepMind
— tex.stackexchange.com
— Overleaf LaTeX Tutorials
— PlotNeuralNet LaTeX Figures, Haris Iqbal
— Interpretable Machine Learning, Christoph Molnar

— Homework 5, due 2/26 and 2/28 (and the night before you are presenting)

Events:

— Lise Getoor presents the 2019 UCSC Faculty Research Lecture on Responsible Data Science at the Music Recital Hall in the Performing Arts Complex on February 26 at 7pm.

Discussions:

— Deep Painterly Harmonization, Sarah Frost, Manu Thomas, and David Abramov
— Generating Mindfulness, Ferran Bertran, James Fey, and Bre Baltaxe-Admony
— Image-to-Image Translation with Memory Recall Drawings, Ella Dagan, and Ran Xu
— Interactive Style Transfer, Mahika Dubey and Jasmine Otto
— Generated Pokemon Cards, Rehaf Aljammaz, Beth Oliver, Mirek Stolee, and Devi Acharya
— Anime Style Transfer, Asiiah Song, Hadiseh Gooranorimi, Ishaan Paranjape, and Abdul Jawad
— Malicious Machines, Emily Hamedian

— Sherol Chen, Google Magenta

— Bill Gaver, Goldsmiths, University of London