Berbagai arsitektur jaringan saraf cocok untuk data dan tugas yang berbeda — CNNs untuk gambar, RNNs untuk urutan, dan transformers untuk bahasa (dan semakin banyak hal lainnya). Memahami tipe utama memperjelas bagaimana AI menangani masalah yang berbeda.
Arsitektur utama
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⚠️ struggles with long sequences; largely SUPERSEDED by transformers for language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
