Die Epoche läuft auf lernenden Maschinen, doch das Lernen selbst bleibt hinter einer API verborgen. Hier liegt es offen, jeder Schritt auf dem Bildschirm und vollständig in Ihrem Browser laufend: ein neuronales Netz, das in Echtzeit eine Entscheidungsgrenze herausarbeitet, ein Agent, der zufällig auf eine Belohnung stößt, Attention, die entscheidet, welches Wort sie betrachtet, Rauschen, das sich unter einem Diffusionsmodell zu Struktur klärt. Keine Cloud, keine Schlüssel — nur Gradienten, Strategien und Wahrscheinlichkeit, gezeichnet in dem Moment, in dem sie geschehen.
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.
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.
Watch temperature, top-k and nucleus top-p reshape a language model’s next-token distribution as text streams out token by token.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
Ein Kohonen-Gitter, das sich knittert, dehnt und über jede beliebige Datenverteilung legt — Topologieentdeckung, sichtbar gemacht.
Beobachten Sie, wie ein tabellarischer RL-Agent von Grund auf eine Navigationsstrategie aufbaut — durch Fallen stolpernd, Belohnung entdeckend und optimale Pfeile in jede Zelle des Gitters einätzend.
Beobachten Sie, wie das Rosenblatt-Neuron von 1958 eine Entscheidungslinie durch Ihre Daten zieht, eine Korrektur nach der anderen.
Beobachten Sie, wie ein selbstgebautes neuronales Netz seine Entscheidungsgrenze in Echtzeit biegt, während es per Backpropagation lernt, 2D-Punktwolken zu trennen.
Der Urahn von GPT — sagen Sie das nächste Token aus den letzten wenigen voraus und beobachten Sie, wie Kohärenz entsteht, je höher die Ordnung wird.
Beobachten Sie, wie Lloyds Algorithmus ein Streudiagramm in lebendige Voronoi-Gebiete zerschneidet, während die Zentroide in Echtzeit ihre Cluster aufspüren.
Beobachten Sie, wie ein verrauschtes oder halb gelöschtes Muster zu einer gespeicherten Erinnerung zurückschnappt, während ein Netz aus Neuronen bergab in einen Attraktor rollt.
Fünf gradientenbasierte Optimierer rasen gleichzeitig dieselbe Verlustlandschaft hinab und zeigen, warum Adam das schlichte SGD in Geschwindigkeit, Stabilität und der Flucht aus Sattelpunkten überflügelt.
Durchstreifen Sie einen handgefertigten semantischen Raum, in dem König − Mann + Frau exakt auf Königin einrastet und Bedeutungscluster in Neonfarben aufblühen.
Beobachten Sie, wie ein CART-Klassifikator Ihre 2-D-Daten in achsenparallele Regionen zerlegt — einen informationsmaximierenden Split nach dem anderen.
Sehen Sie zu, wie ε-greedy, UCB1 und Thompson Sampling um den besten Arm des Spielautomaten wetteifern — der kumulierte Regret live geplottet, während die Algorithmen erkunden und ausnutzen.
Beobachten Sie, wie ein Transformer entscheidet, worauf er blickt — softmax(QKᵀ/√d), greifbar gemacht durch Live-Heatmaps und bipartite Attention-Flüsse.