Three specialisations — each built on the neural network foundation from Topic 08. Real models running live in your browser. No cloud, no API key, no cost.
Upload any photo or use your webcam. Detect and count every object with bounding boxes. Classify images into 1000 ImageNet categories.
Four NLP tasks with one Transformer. Sentiment, zero-shot classification, named entity recognition, and semantic similarity on your own text.
Record your voice and transcribe it with Whisper, entirely in-browser. Or type any text and hear it spoken with full voice/pitch control.
No model download needed. Watch a Q-Learning agent learn to balance a CartPole, escape a grid maze, and play Catch — trained from scratch in your browser.
Q-Learning from scratch · Pure JS
Agent learns optimal path · ε-greedy
Convolutional layers detect local patterns: edges → textures → shapes → objects. Pooling reduces spatial size. Fully-connected layers classify.
Each token attends to every other token, weighted by relevance. This parallelisable design replaced RNNs and powers BERT, GPT, and all modern LLMs.
Agent observes state → takes action → receives reward → updates Q-table. The Bellman equation drives learning: Q(s,a) ← r + γ·max Q(s',a').
Audio is chunked into 30s windows → converted to log-Mel spectrogram → encoded by Transformer → decoded autoregressively into text tokens.
Detection Transformer uses a CNN backbone to extract features, then a Transformer encoder-decoder to simultaneously predict all bounding boxes and classes in one pass.
Replace Q-table with a neural network that takes state as input and outputs Q-values for all actions. Uses experience replay and target networks for stability.