🏠 Strona Główna
Benchmarki
📊 Wszystkie benchmarki 🦖 Dinozaur v1 🦖 Dinozaur v2 ✅ Aplikacje To-Do List 🎨 Kreatywne wolne strony 🎯 FSACB - Ostateczny pokaz 🌍 Benchmark tłumaczeń
Modele
🏆 Top 10 modeli 🆓 Darmowe modele 📋 Wszystkie modele ⚙️ Kilo Code
Zasoby
💬 Biblioteka promptów 📖 Słownik AI 🔗 Przydatne linki

Słownik AI

Kompletny słownik sztucznej inteligencji

162
kategorie
2 032
podkategorie
23 060
pojęcia
📖
pojęcia

Parameter Initialization

Crucial process in MAML that involves finding optimal starting weights that minimize the adaptation distance needed to achieve good performance on a new task.

📖
pojęcia

Support Tasks

Subset of data from a meta-training task used to compute adaptation gradients and temporarily update the model parameters.

📖
pojęcia

Query Tasks

Validation samples in each task used to evaluate performance after adaptation and compute meta-gradients for updating initialization parameters.

📖
pojęcia

Meta-learning Step

External learning rate used in the meta-optimization loop to update initialization parameters by minimizing loss on query sets.

📖
pojęcia

Task Adaptation Step

Internal learning rate applied during rapid adaptation to a new specific task in MAML's internal optimization loop.

📖
pojęcia

Meta-gradients

Gradients calculated through task adaptation steps, allowing performance information to propagate to initialization parameters.

📖
pojęcia

First-Order MAML (FOMAML)

Computationally efficient variant of MAML that ignores second derivatives in meta-gradients, reducing complexity while maintaining good performance.

📖
pojęcia

Inner Loop

Internal optimization loop in MAML that performs rapid adaptation of parameters to a specific task using support data.

📖
pojęcia

Outer loop

Outer optimization loop in MAML that updates initialization parameters by aggregating performance information across all tasks.

📖
pojęcia

Task distribution

Underlying set of tasks from which MAML samples during training to learn robust and generalizable representations.

📖
pojęcia

Reptile

Simplified meta-learning algorithm that performs interpolation between initialized weights and weights after adaptation, without requiring nested gradients.

📖
pojęcia

Cross-task generalization

Fundamental objective of MAML consisting of learning representations that effectively transfer knowledge between different related tasks.

📖
pojęcia

Task uncertainty quantification

Extension of MAML incorporating Bayesian methods to quantify uncertainty in predictions when adapting to new tasks.

🔍

Nie znaleziono wyników