This tool was created for CEE 4803 (Art & Generative AI) at the Georgia Institute of Technology.
It pairs with our Libre textbook, AI Fundamentals.
Kenneth (Alex) Jenkins - TA for CEE 4803
Interactive demonstrations of AI and machine learning architectures
The foundational building block of neural networks - a simple linear classifier
Multi-layer neural network with hidden layers for complex decision boundaries
Statistical physics model showing spin interactions and phase transitions
Associative memory network that stores and retrieves patterns
Compress and reconstruct data through a bottleneck latent representation
A generative network with bidirectional energy flow between visible and hidden layers
Probabilistic encoder-decoder that learns continuous latent distributions
Invertible transformations that map simple to complex distributions
Bidirectional convolutional network for image processing tasks
Modern architecture using attention mechanisms to process sequences
State-of-the-art architecture replacing Transformers with linear-time complexity for ultra-long sequences
GPU parallel computing concepts: threads, blocks, and memory hierarchy
Transformer-based architecture that generates original melodies using self-attention mechanisms and sequential pattern learning
A perceptron is like a simple decision-maker with a checklist. Imagine a bouncer at a party who decides if you can come in based on a few things: Are you on the guest list? Are you wearing nice shoes? Do you have an invitation? The bouncer gives each rule a different importance (weight), adds up the scores, and makes a final yes/no decision. When the bouncer makes mistakes, they learn by adjusting how important each rule is!
The Perceptron: A Probabilistic Model for Information Storage and Organization in the Brain
Psychological Review, 65(6), 386-408
An RBM is like a box full of light switches that can turn on or off. Some switches are on the front (visible units - things we can see) and some are hidden inside (hidden units - patterns we discover). The cool part? The switches talk to each other! If you flip the visible switches in a certain pattern (like showing it a picture of a cat), the hidden switches learn to recognize "cat-ness". Then you can flip the hidden switches and the visible ones will show you a new cat picture!
Restricted Boltzmann Machines for Collaborative Filtering
Proceedings of the 24th International Conference on Machine Learning (ICML)
An autoencoder is like a really clever note-taker in class. Instead of writing down everything the teacher says word-for-word, they write short notes with just the most important ideas (encoding). Later, when studying for the test, they can expand those short notes back into full explanations (decoding). If the notes are good, you can recreate almost the whole lecture! The autoencoder learns what's "important enough" to write down to recreate the original information.
Reducing the Dimensionality of Data with Neural Networks
Science, 313(5786), 504-507
The Ising Model is like a checkerboard where each square is a tiny magnet that wants to point either up or down. Here's the cool part: each magnet wants to match its neighbors - if your neighbor points up, you want to point up too! Temperature is like how much the magnets "wiggle around". When it's cold, all the magnets line up the same way (like everyone wearing the same team jersey). When it's hot, they point randomly (like a messy crowd). This shows how simple rules create complex group behavior!
Beitrag zur Theorie des Ferromagnetismus (Contribution to the Theory of Ferromagnetism)
Zeitschrift für Physik, 31(1), 253-258
A Hopfield Network is like a magic photo restoration machine. Imagine you have a damaged old photograph with parts missing or blurry. You show it to the network, and it "remembers" complete photos it saw before and fixes your damaged one! It's like when you see half a face and your brain fills in the rest. The network stores memories as patterns, and when you give it a partial or noisy pattern, it rolls downhill into the closest complete memory - like a ball rolling into a valley!
Neural Networks and Physical Systems with Emergent Collective Computational Abilities
Proceedings of the National Academy of Sciences, 79(8), 2554-2558
In practice, a Transformer takes the tokens you've typed and outputs a probability distribution over the next token. This demo uses a trigram/bigram language model that looks at the last 1-2 words to predict what comes next, with intelligent fallbacks for unseen phrases. Real transformers use self-attention to consider ALL previous tokens with different weights, making them vastly more powerful. The model has learned patterns from diverse example sentences about food, animals, machine learning, and everyday conversations. Try typing phrases like "i like pizza that" or "machine learning is" to see contextually relevant predictions!
Attention Is All You Need
Advances in Neural Information Processing Systems 30 (NeurIPS 2017)
A Deep Perceptron (MLP) is like a tower of smart committees, each one making decisions based on what the committee below figured out! The first committee looks at raw information (like pixels in a photo). The second committee looks at patterns the first one found (like "edges"). The third committee spots bigger patterns (like "circles" or "corners"). Each committee learns what's important and passes it up. By the time you reach the top, the network can recognize really complex things like "this is a cat" or "this email is spam!" It's like playing telephone, but each person in line makes the message smarter instead of more confusing.
Learning Representations by Back-Propagating Errors
Nature, 323(6088), 533-536
A Normalizing Flow is like a Play-Doh factory that can make ANY shape you want! You start with a simple ball of Play-Doh (easy to make). Then you push it through a series of special molds - twist here, stretch there, bend this way. Each mold transforms it step-by-step. The cool part? You can write down EXACTLY what each mold does, so you can reverse the whole process perfectly! If you want another copy, just start with a ball and push through the same molds. This is how AI can create realistic faces, voices, or artwork - it learns what "molds" (transformations) turn random noise into the real thing.
NICE: Non-linear Independent Components Estimation
International Conference on Learning Representations (ICLR 2015)
A VAE is like an artist who doesn't trace drawings exactly - they learn the STYLE! Imagine showing an artist 1000 cat photos. Instead of memorizing each cat, they learn "cats usually have pointy ears, whiskers, and round eyes - but every cat is slightly different." Now when you ask them to draw a new cat, they don't copy an old photo; they create a unique cat using what they learned about "cat-ness." The magic is they also learn WHERE in "cat space" each feature lives (fluffy vs. short-hair, big vs. small), so you can even say "draw me a cat that's halfway between these two!" This is how AI generates new faces, art, or music that look real but never existed before.
Auto-Encoding Variational Bayes
International Conference on Learning Representations (ICLR 2014)
Imagine you're looking at a photo through a magnifying glass that first makes everything blurry and simple (like squinting your eyes), then gradually brings back all the details. The CNN Encoder-Decoder is like a smart camera that first simplifies an image by focusing on the most important shapes and patterns, then rebuilds it with all the details restored - like taking a puzzle apart and putting it back together, but now you understand every piece!
U-Net: Convolutional Networks for Biomedical Image Segmentation
Medical Image Computing and Computer-Assisted Intervention (MICCAI 2015)
Think of Transformers as a student who needs to compare every word in a book with every other word to understand it - this gets impossibly slow with long books! Mamba2 is like a speed-reader with a smart notebook: as it reads, it instantly decides "This is important, write it down" or "This is background info, skip it." The notebook stays small and organized, so even with massive texts, Mamba2 reads at lightning speed. This breakthrough is why Mamba2 is rapidly replacing Transformers in applications that need to understand really long sequences - from analyzing entire research papers to processing hours of conversation history. Selective State Spaces let Mamba2 focus on the most relevant information without getting bogged down, making it perfect for the next generation of AI models that need to handle vast amounts of data efficiently.
Mamba: Linear-Time Sequence Modeling with Selective State Spaces
arXiv preprint arXiv:2312.00752
Imagine you have a big homework assignment with 1000 math problems. Your regular CPU is like having ONE really smart student who solves each problem one at a time - fast, but it takes a while. A GPU with CUDA is like having a classroom with THOUSANDS of students who each solve one problem at the same time! Even though each student might be a bit slower than the super-smart one, when they all work together, they finish the whole assignment way faster. That's why GPUs are perfect for training AI!
