🏠 Home
Benchmark
📊 Tutti i benchmark 🦖 Dinosauro v1 🦖 Dinosauro v2 ✅ App To-Do List 🎨 Pagine libere creative 🎯 FSACB - Ultimate Showcase 🌍 Benchmark traduzione
Modelli
🏆 Top 10 modelli 🆓 Modelli gratuiti 📋 Tutti i modelli ⚙️ Kilo Code
Risorse
💬 Libreria di prompt 📖 Glossario IA 🔗 Link utili

Glossario IA

Il dizionario completo dell'Intelligenza Artificiale

162
categorie
2.032
sottocategorie
23.060
termini
📂
sottocategorie

Transformer Architecture

Neural structure based on attention mechanisms that enables parallel processing of text sequences

5 termini
📂
sottocategorie

Tokenization

Process of segmenting text into discrete units (tokens) for processing by models

13 termini
📂
sottocategorie

Fine-tuning

Specialized adaptation of a pre-trained model on specific data for targeted tasks

6 termini
📂
sottocategorie

Prompt Engineering

Design optimization of instructions to effectively guide language model responses

14 termini
📂
sottocategorie

Attention Mechanism

System allowing the model to weight the importance of different parts of the text during processing

2 termini
📂
sottocategorie

Language Embeddings

Dense vector representations that capture the semantic meaning of words and phrases

8 termini
📂
sottocategorie

Transfer Learning

Reusing knowledge acquired from a large corpus for specific tasks with limited data

4 termini
📂
sottocategorie

Scaling Laws

Mathematical principles describing performance improvement with increasing model size

20 termini
📂
sottocategorie

Zero-shot Learning

Ability of models to perform tasks never seen during training without examples

8 termini
📂
sottocategorie

Multimodal Models

LLM integrating text, image, audio, and other modalities within a unified framework

18 termini
📂
sottocategorie

Quantization

Reducing the numerical precision of model weights to optimize inference and storage

20 termini
📂
sottocategorie

RAG (Retrieval-Augmented Generation)

Combination of external information retrieval with generation to improve answer accuracy

6 termini
📂
sottocategorie

Alignment and Safety

Techniques to ensure that models respect human values and avoid harmful behaviors

16 termini
📂
sottocategorie

Autoregressive Models

Generative architecture predicting the next token based on all previous tokens

15 termini
📂
sottocategorie

LoRA (Low-Rank Adaptation)

Memory-efficient fine-tuning method using low-rank matrices

11 termini
🔍

Nessun risultato trovato