DIGISIM.OBSERVATORY · category 22 — mind
0 live · 0 planned build 0.2 — : —
English
category 22 · mind

Watch a machine learn.

The era runs on learning machines, yet the learning itself stays hidden behind an API. Here it is in the open, every step on screen and running entirely in your browser: a neural net carving a decision boundary in real time, an agent stumbling into a reward, attention deciding which word to look at, noise resolving into structure under a diffusion model. No cloud, no keys — just gradients, policies and probability, drawn as they happen.

apps live 0
in design 0
opened 05·31
MIND-001 · BUILT ready
featured
Neuron Lab

A real fully-connected neural network learning to read digits, drawn in 3D — every ball a neuron, every wire a weight. Press Train and watch backpropagation flow; open any neuron to read its exact weighted sum.

neural-networkbackpropagationmlpdeep-learningmnisttraining
2026-06-16 /mind/neuron-lab
in this section · 36 apps
MIND-002 ready
Universal Approximator

Draw any curve y=f(x) and watch a tiny MLP learn to fit it live by backpropagation — add neurons to chase wigglier targets and see the universal approximation theorem unfold as a sum of basis bumps.

mind /mind/universal-approximator
MIND-003 ready
Temperature & Sampling

Watch temperature, top-k and nucleus top-p reshape a language model’s next-token distribution as text streams out token by token.

mind /mind/temperature-sampling
MIND-004 ready
Next-Token Predictor

Drive a real language model by hand: a word-level interpolated trigram trained on public-domain prose shows its top next-token candidates with live probabilities — click one to append it and watch the distribution shift.

mind /mind/next-token-predictor
MIND-005 ready
Neuroevolution

A population of little cars, each driven by its own tiny neural network, evolves to race a procedural track — raycast sensors feed an MLP that learns to steer, and a genetic algorithm breeds the survivors generation after generation.

mind /mind/neuroevolution
MIND-006 ready
MNIST Live

Draw a digit and a classifier trained in your browser on the real MNIST dataset recognises it live — per-class confidence bars and the top pick update on every stroke.

mind /mind/mnist-live
MIND-007 ready
t-SNE Unfolding

Watch real t-SNE run live: a random fog of high-dimensional points pulls itself apart frame by frame, gradient-descending the KL divergence until clean, separated clusters bloom — Gaussian blobs, interlocking rings, baked digits, concentric shells.

mind /mind/tsne
MIND-008 ready
Tokenizer Playground

Train a real Byte-Pair Encoding live, then watch your text shatter into colored tokens — and finally see why "strawberry" trips up an LLM trying to count its r’s.

tokenizer /mind/tokenizer
MIND-009 ready
Reservoir Computing

Watch an Echo State Network learn a chaotic signal the lazy, brilliant way: a big FIXED random recurrent reservoir is driven by the input, and only a single linear readout is trained — by ridge regression, no backprop — yet it learns to predict the series, then runs autonomously off its own output, continuing the signal until chaos finally pulls it apart.

mind /mind/reservoir-computing
MIND-010 ready
PCA Projector

Watch real Principal Component Analysis fold a high-dimensional cloud — a tilted 3D Gaussian, the classic Iris flowers, a Swiss-roll, clustered digits — onto its principal axes, points sliding into place while the explained-variance bars fill.

mind /mind/pca
MIND-011 ready
Naive Bayes

Train a real multinomial Naive Bayes spam filter in your browser, then type a message and watch each word tug the verdict toward spam or ham — with the log-odds math drawn live, word by word.

mind /mind/naive-bayes
MIND-012 ready
Markov Decision Process

Solve a stochastic gridworld with value iteration — watch value flood out from the goal and the optimal policy re-point as discount, living reward, and action noise reshape the safest path.

reinforcement-learning /mind/mdp
MIND-013 ready
Manifold Hypothesis

High-dimensional data lives on a curved low-dimensional sheet — so "learning" is unrolling it. Watch a Swiss roll, S-curve, or severed sphere flatten in 3D, then see real Isomap and LLE recover the true 2D layout while linear PCA fails to unroll and folds the colours back on themselves.

mind /mind/manifold
MIND-014 ready
kNN Explorer

Classify every pixel of a 2D plane by the majority vote of its k nearest training points — slide k from a jagged k=1 island map to a smooth large-k wash and watch overfitting melt into underfitting in real time.

mind /mind/knn
MIND-015 ready
Genetic Algorithm

Watch a population of genomes evolve over generations — selection, crossover and mutation — as a recognizable image rises from noise, rockets thread an obstacle, a phrase assembles itself, or a swarm climbs a rugged fitness landscape.

mind /mind/genetic-algorithm
MIND-016 ready
GAN Arena

Watch a generative adversarial network duel in your browser: a tiny generator maps random noise into 2-D points trying to mimic a real target distribution while a discriminator fights to tell real from fake — the fakes migrate to cover the target, the discriminator surface flattens toward a coin-flip as the generator wins, the two loss curves duel, and on a grid of modes you can trigger the classic mode collapse on cue.

mind /mind/gan-arena
MIND-017 ready
Diffusion Denoiser

The tech behind image generators, made tractable in 2D — add Gaussian noise to a point cloud until a shape dissolves, then watch a tiny denoiser network you train in your browser flow pure noise back into the shape, guided by a learned score field.

mind /mind/diffusion-denoiser
MIND-018 ready
Gradient Descent Landscape

Watch a real optimizer descend a 3D loss surface — switch between SGD, Momentum, RMSProp and Adam, then crank the learning rate until it visibly diverges.

mind /mind/descent-landscape
MIND-019 ready
Decision Boundary

Drop labelled points on a plane and watch four real classifiers — k-NN, logistic regression, a live-trained neural net, and an RBF kernel — carve the space into coloured decision regions before your eyes.

mind /mind/decision-boundary
MIND-020 ready
Confusion Matrix

Drag a decision threshold across two overlapping score distributions and watch the confusion matrix, ROC and PR curves, and every metric recompute live — then crank the class imbalance to expose why accuracy lies.

mind /mind/confusion-matrix
MIND-021 ready
CNN Filters

Slide a 3×3 convolution kernel across a procedurally drawn image and watch the feature map light up — switch between blur, sharpen, Sobel edges, emboss and a Laplacian, or hand-craft your own kernel and chain a second layer.

mind /mind/cnn-filters
MIND-022 ready
CartPole RL

Watch a reinforcement-learning agent teach itself to balance an inverted pendulum on a cart — from flailing in the first second to holding the pole upright for a full episode, with the reward curve climbing live as it learns.

mind /mind/cartpole
MIND-023 ready
Bias–Variance

Fit a model to many noisy training sets at once and watch the curve family swing from rigid-and-biased to wild-and-overfit — with the classic U-shaped test error and its sweet spot decomposed live into bias² + variance + noise.

mind /mind/bias-variance
MIND-024 ready
Bayesian Optimization

Hunt the maximum of an expensive, hidden function in as few samples as possible — a Gaussian-process surrogate fits the points so far, draws its mean and a ±2σ uncertainty band, and an acquisition function picks the next, smartest place to look.

mind /mind/bayes-opt
MIND-025 ready
Autoencoder

Train a real neural autoencoder live: tiny glyphs are squeezed through a 2-D bottleneck and rebuilt by a decoder, the reconstructions sharpening epoch by epoch while a latent map blooms into class clusters — then click anywhere in that latent plane to watch the decoder dream a new glyph into being.

mind /mind/autoencoder
MIND-026 ready
Self-Organizing Map

A Kohonen lattice that crumples, stretches, and drapes itself over any data distribution — topology discovery made visible.

som /mind/self-organizing-map
MIND-027 ready
Q-Learning

Watch a tabular RL agent bootstrap a navigation policy from scratch — stumbling through traps, discovering reward, and etching optimal arrows into every cell of the grid.

reinforcement-learning /mind/q-learning
MIND-028 ready
Perceptron

Watch the 1958 Rosenblatt neuron carve a decision line through your data, one correction at a time.

perceptron /mind/perceptron
MIND-029 ready
Neural Playground

Watch a hand-rolled neural network bend its decision boundary in real time as it learns to separate 2D point clouds through backpropagation.

neural-network /mind/neural-playground
MIND-030 ready
Markov Babble

The ancestor of GPT — predict the next token from the last few and watch coherence emerge as order grows.

markov /mind/markov-text
MIND-031 ready
K-Means

Watch Lloyd's algorithm carve a scatterplot into living Voronoi territories as centroids hunt down their clusters in real time.

clustering /mind/k-means
MIND-032 ready
Hopfield Memory

Watch a noisy or half-erased pattern snap back to a stored memory as a network of neurons rolls downhill into an attractor.

hopfield /mind/hopfield
MIND-033 ready
Optimizer Race

Five gradient-based optimizers race down the same loss landscape simultaneously, revealing why Adam dominates vanilla SGD in speed, stability, and saddle-point escape.

gradient-descent /mind/gradient-descent
MIND-034 ready
Word Embeddings

Roam a hand-crafted semantic space where king − man + woman snaps exactly to queen, and clusters of meaning bloom in neon colour.

embeddings /mind/embeddings
MIND-035 ready
Decision Tree

Watch a CART classifier carve your 2-D data into axis-aligned regions — one information-maximising split at a time.

decision-tree /mind/decision-tree
MIND-036 ready
Multi-Armed Bandit

Watch ε-greedy, UCB1, and Thompson Sampling race to find the best slot machine arm — live cumulative regret plotted as the algorithms explore and exploit.

bandit /mind/bandit
MIND-037 ready
Attention

Watch a transformer decide what to look at — softmax(QKᵀ/√d) made visceral through live heatmaps and bipartite attention flows.

transformer /mind/attention
mind · category 22 ← back to observatory