🏠 Home
Benchmark Hub
📊 All Benchmarks 🦖 Dinosaur v1 🦖 Dinosaur v2 ✅ To-Do List Applications 🎨 Creative Free Pages 🎯 FSACB - Ultimate Showcase 🌍 Translation Benchmark
Models
🏆 Top 10 Models 🆓 Free Models 📋 All Models ⚙️ Kilo Code
Resources
💬 Prompts Library 📖 AI Glossary 🔗 Useful Links

AI Glossary

The complete dictionary of Artificial Intelligence

162
categories
2,032
subcategories
23,060
terms
📖
terms

Autoencoder

Unsupervised neural network composed of an encoder and a decoder that learns to efficiently compress and reconstruct input data.

📖
terms

Encoder

Part of the autoencoder responsible for compressing input data into a reduced-dimension representation in the latent space.

📖
terms

Decoder

Component of the autoencoder that reconstructs original data from their compressed representation in the latent space.

📖
terms

Latent space

Low-dimensional representation where compressed data by the encoder is stored, capturing essential features of input data.

📖
terms

Bottleneck

Minimal-dimension intermediate layer in an autoencoder that forces information compression and prevents direct copying.

📖
terms

Variational Autoencoder

Type of generative autoencoder that learns a probabilistic distribution in the latent space rather than a deterministic representation.

📖
terms

Denoising Autoencoder

Variant of autoencoder trained to reconstruct clean data from inputs corrupted by random noise.

📖
terms

Convolutional Autoencoder

Autoencoder using convolutional layers particularly effective for image and spatial data processing.

📖
terms

Sparse autoencoder

Autoencoder including a sparsity constraint to force the activation of only a few neurons in the hidden layer.

📖
terms

Contractive autoencoder

Autoencoder adding a penalty on the sensitivity of the representation to small variations in the input to improve robustness.

📖
terms

Reconstruction loss

Cost function measuring the difference between the original input data and their reconstruction by the autoencoder.

📖
terms

Deep autoencoder

Autoencoder architecture with multiple hidden layers allowing to learn hierarchies of complex features.

📖
terms

Memory autoencoder

Autoencoder integrating an external memory mechanism to store and retrieve learned representation prototypes.

📖
terms

Adversarial autoencoder

Combination of an autoencoder with a discriminator network to force the latent space to follow a specific distribution.

📖
terms

Reconstruction gap

Quantitative metric measuring the ability of an autoencoder to faithfully reconstruct the original input data.

📖
terms

Autoencoder overfitting

Phenomenon where the autoencoder memorizes the training data instead of learning generalizable representations.

📖
terms

Recursive Autoencoder

Autoencoder that processes hierarchical structures like syntactic trees by recursively applying encoding.

📖
terms

Hybrid Autoencoder

Architecture combining multiple types of autoencoders or integrating other deep learning models to improve performance.

📖
terms

Factor Disentanglement

Advanced objective of autoencoders aiming to separate independent factors of variation in the latent space.

📖
terms

Transformer Autoencoder

Autoencoder based on the transformer architecture using attention mechanisms to process sequential data.

🔍

No results found