The Neural Aesthetic @ ITP-NYU, Fall 2018
Lectures Syllabus Student projects
Description
- Course goals, logistics, and resources
- Introduction to AI, machine learning, and deep learning
- The whole class "in 60 minutes"
Practical
Supplementary / links
Description
- How convolutional neural networks work (forward pass)
- Transfer learning
- Demos and applications of transfer learning
Supplementary / links
Description
- How neural nets are trained (backward pass)
- Overfitting, regularization, optimization
- ml4a-ofx demos: ConvnetPredictor, AudioClassifier, DoodleClassifier
Practical
Supplementary / links
- How neural nets are trained
- Numpy for ninjas: linear algebra [planned]
Description
- Feature extraction
- Reverse image search and X degrees
- t-SNE of images/sounds & visualization
- Transfer learning
Supplementary / links
Description
- Visualizing convnet features
- Pixel-optimization, Deepdream, neural-synth
- Style transfer and textur synthesis
Practical
Supplementary / links
Description
- Basic terminal navigation
- Python shell and bash scripting
- Connecting to remote VM
Practical
Supplementary / links
Description
- Autoencoders & Generative adversarial networks
- Compiling, scraping, and processing datasets
- Training DCGANs
Practical
Supplementary / links
- Garbage in, treasure out: a field guide to compiling datasets on a messy internet [planned]
- From PCA to Puppyslugs
Description
- Image-to-image translation (pix2pix/CycleGAN)
- Scraping and preparing parallel datasets
- YOLO & dense captioning
Supplementary / links
Description
- Recurrent networks & LSTMs
- Sequence-to-sequence applications
- im2txt, Sketch-RNN, char-rnn tutorials
Practical
Supplementary / links
Description
- GLOW and reversible generative models
- BigGAN tutorial
- Music information retrieval
Practical
Supplementary / links
Description
- Natural language processing
- Agent-environment systems & games
- AlphaGo and AlphaZero
Supplementary / links
Description
- Cryptography, peer-to-peer networks, DAOs
- Curation markets and cryptoeconomics
- Decentralizing machine learning
Practical
Supplementary / links
11 Dec 2018
Final presentations
Description
Practical
Supplementary / links