AI Dictionary › Fondamenti AI

Convolutional Neural Network (CNN)

Rete neurale convoluzionale (CNN)

A convolutional neural network, or CNN, is an architecture specialized in processing grid-structured data, especially images. Instead of looking at each pixel in isolation, it applies small filters that slide across the image searching for local patterns like edges, corners, and textures. It's like examining a photo with a magnifying glass moved systematically over every area: layer by layer, the network combines simple patterns into increasingly complex concepts, from outlines to shapes, up to recognizing eyes, faces, or whole objects. Sharing filters across the whole image makes CNNs efficient and able to recognize an object wherever it appears.

Definition

CNNs revolutionized computer vision, powering facial recognition, medical image diagnosis, autonomous driving, and photo filters. Though now joined by transformers even in vision, they remain a practical, efficient pillar, often preferred when speed matters or data is limited.

Related terms

• Recurrent Neural Network (RNN)
• Computer Vision
• Deep Learning
• Neural Network
• Transformer

More in Fondamenti AI

• LLM (Large Language Model)
• Token
• Context Window
• Temperature
• AI Hallucination
• Fine-tuning
• RAG (Retrieval Augmented Generation)
• Embedding

Put it into practice

• Real scenario: apply this concept with an instant AI verdict.
• Daily gym: short drills to train dictionary concepts.
• Playoff game: challenge other players, elimination-style.

📱 Download the Android app (beta) iOS coming soon

Say what you mean. Get what you need.

Grace Certified, the AI coach that trains and certifies your prompt engineering, by Agora Intelligence.