Različite arhitekture neuronskih mreža pogađaju različitim podacima i zadacima — CNN-ovi za slike, RNN-ovi za sekvence, i transformatori za jezik (i sve više za sve ostalo). Razumijevanje glavnih tipova pojašnjava kako AI rješava različite probleme.
Glavne arhitekture
CNN (Convolutional Neural Network) → for IMAGES/spatial data:
→ uses convolutions to detect local features (edges, shapes) hierarchically
→ for: image classification, object detection, computer vision
RNN (Recurrent Neural Network) → for SEQUENCES/time-series:
→ processes sequences step by step, maintaining a 'memory' of previous inputs
→ for: text, time-series, speech (older approach; LSTM/GRU variants)
⚠️ struggles with long sequences; largely SUPERSEDED by transformers for language
TRANSFORMER → for SEQUENCES (language) and increasingly everything:
→ attention mechanism; parallel; the dominant modern architecture (LLMs)
→ for: language (LLMs), and now vision, audio, multimodal
