🏠 Home
Prestatietests
📊 Alle benchmarks 🦖 Dinosaur v1 🦖 Dinosaur v2 ✅ To-Do List applicaties 🎨 Creatieve vrije pagina's 🎯 FSACB - Ultieme showcase 🌍 Vertaalbenchmark
Modellen
🏆 Top 10 modellen 🆓 Gratis modellen 📋 Alle modellen ⚙️ Kilo Code
Bronnen
💬 Promptbibliotheek 📖 AI-woordenlijst 🔗 Nuttige links

AI-woordenlijst

Het complete woordenboek van kunstmatige intelligentie

162
categorieën
2.032
subcategorieën
23.060
termen
📖
termen

Multi-Head Self-Attention (MHSA)

Mechanism allowing the model to focus on different parts of the image simultaneously by computing multiple attention matrices in parallel, thus capturing various types of spatial relationships.

📖
termen

Layer Scale

Regularization technique introduced in deep ViTs where learnable weights are applied to residual outputs to stabilize the training of initial layers.

📖
termen

Windowed Attention

Attention mechanism restricted to local non-overlapping windows of the image, reducing computational complexity from O(n²) to O(n) where n is the number of patches.

📖
termen

Shifted Window Attention

Technique where attention windows are shifted between layers to enable cross-window connections, thereby improving the model's ability to model long-range relationships.

📖
termen

DeiT (Data-efficient Image Transformer)

Variant of ViT trainable with more modest amounts of data through a knowledge distillation strategy where a distillation token is added to learn from a CNN teacher.

📖
termen

Distillation Token

Additional token in DeiT that learns to mimic the predictions of a teacher model (often a CNN), facilitating knowledge transfer and improving performance with less data.

📖
termen

Masked Autoencoder (MAE)

Self-supervised approach for ViT where random patches of the image are masked (up to 75%) and the model learns to reconstruct them, revealing surprising learning capabilities.

📖
termen

Patch Merging

Operation in hierarchical transformers that combines groups of 2x2 adjacent patches to create lower-resolution tokens, thereby increasing depth and receptive field.

📖
termen

Relative Position Bias

Bias added to attention scores that depends on the relative positions of patches, improving the model's ability to understand spatial relationships without absolute position encoding.

📖
termen

Hybrid Architecture

Approach combining an initial convolutional network for feature extraction with a transformer for global processing, used in early ViT implementations to reduce data requirements.

📖
termen

Token Labeling

Training strategy where each patch receives a supervised label instead of a single label per image, forcing the model to learn richer and more localized representations.

🔍

Geen resultaten gevonden