Sequenzmodelle & generative Modelle

103 Methoden in dieser Familie.

Ausgewählt

Attention MechanismThe attention mechanism, introduced by Bahdanau, Cho and Bengio in 2015 and refined by Luong, Pham and Manning the same year, lets a sequence decoder dynamically learn which of the AutoencoderAn autoencoder is an encoder-decoder neural network, popularised by Hinton and Salakhutdinov in 2006, that compresses data into a low-dimensional latent code and then reconstructs Bidirectional RNNA Bidirectional RNN, introduced by Schuster and Paliwal in 1997, processes a sequence in both forward and backward directions so that every position has access to its full surround CrossformerCrossformer is a Transformer-based architecture for multivariate time series forecasting, introduced by Yunhao Zhang and Junchi Yan at ICLR 2023. Unlike earlier Transformer variant CycleGANCycleGAN, introduced by Zhu et al. at ICCV 2017, learns to translate images between two visual domains without requiring paired training examples. It trains two generators and two DeepARDeepAR is Amazon's industrial forecasting model, introduced by Salinas, Flunkert and Gasthaus (2017; published 2020), that uses an autoregressive recurrent neural network to estima

Reading path

This topic's most-referenced foundational methods, in the order they were developed — a place to start if you're new here.

Rekurrentes neuronales Netz1986–1990by Rumelhart, D. E.; Elman, J. L.
Long Short-Term Memory (LSTM)1997by Hochreiter, S. & Schmidhuber, J.
Gated Recurrent Unit (GRU)2014by Cho, K., van Merrienboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y.
Generative Adversarial Network2014by Goodfellow, I. et al.
Variationaler Autoencoder2014by Kingma, D. P. & Welling, M.
Fine-Tuned Transformer2017–2019by Vaswani et al. (architecture); fine-tuning paradigm popularised by Howard & Ruder, Devlin et al.
Multimodaler Transformer2019–2021by Lu et al. (ViLBERT); Radford et al. (CLIP)
Vision Transformer2021by Dosovitskiy, A. et al.

all methods on this shelf ↓

Alle Methoden 103

Attention Mechanism Autoencoder Bidirectional RNN Crossformer CycleGAN DeepAR Diffusion Model Domänenadaptives Diffusionsmodell Domänen-adaptiver GAN Domain-Adaptive GRU Domänenadaptiver rekurrenter neuronaler Netz Domänenadaptive Satz-Einbettungen Domain-Adaptive Transformer Domain-Adaptiver Variational Autoencoder Domain-Adaptive Vision Transformer Erklärbares Diffusionsmodell Erklärbare GANs Erklärbare GRU Erklärbare LSTM Erklärbares Rekurrentes Neuronales Netz Erklärbarer Transformer Erklärbarer Variational Autoencoder FEDformer: Frequency Enhanced Decomposed Transformer Feinabgestimmtes Diffusionsmodell Fine-Tuned Generative Adversarial Network Feinabgestimmte GRU Fine-Tuned LSTM Feinabgestimmtes rekurrierendes neuronales Netz Feinabgestimmte Textzusammenfassung Fine-Tuned Transformer Feinabgestimmter Variational Autoencoder Feinabgestimmter Vision Transformer Gated Recurrent Unit (GRU)Generative Adversarial Network Graph Attention Network Gated Recurrent Unit (GRU)Informer iTransformer: Inverted Transformer für multivariate Zeitreihenprognosen Latent Diffusion Models Long Short-Term Memory (LSTM)Longformer / BigBird LSTM Masked Autoencoders Moirai: Universeller Transformer für Zeitreihenprognosen Multilingual Diffusion Model Multilingual GAN Mehrsprachige GRU Mehrsprachiges LSTM Rekurrente Neuronale Netze für Mehrsprachigkeit Mehrsprachige Textzusammenfassung Multilingual Variational Autoencoder Mehrsprachiger Vision Transformer Multimodales Diffusionsmodell Multimodale GANs Multimodales GRU Multimodal LSTM Multimodales Rekurrentes Neuronales Netz Multimodaler Transformer Multimodaler Variational Autoencoder Multimodal Vision Transformer Non-stationary Transformer PatchTST Pyraformer: Pyramidal Attention Transformer für Langzeit-Zeitreihenprognosen Rekurrentes neuronales Netz Reformer: Der effiziente Transformer für lange Sequenzen Score-basiertes generatives Modell SegRNN: Segment Recurrent Neural Network für langfristige Zeitreihenprognosen Multi-Head Self-Attention Selbstüberwachtes Diffusionsmodell Selbst-überwachtes GAN Selbstüberwachtes GRU Selbstüberwachter Transformer Self-supervised Variational Autoencoder Selbstüberwachtes Vision Transformer Halbüberwachtes Diffusionsmodell Semi-supervised GAN Semi-supervised GRU Halbüberwachte LSTM Semisupervidierter Transformer Semi-supervised Variational Autoencoder Semi-supervised Vision Transformer Sequence-to-Sequence Model Swin Transformer T5 (Text-to-Text Transfer Transformer)Temporal Fusion Transformer Time-MoE: Ein Foundation Model für Zeitreihen basierend auf Mixture-of-Experts TiRex: Zero-Shot-Zeitreihenprognose mit xLSTM Transfer Learning GAN Transfer Learning mit Variational Autoencoder Transfer Learning mit Diffusionsmodellen Transfer Learning mit LSTM Transfer Learning mit rekurrierenden neuronalen Netzen Variationaler Autoencoder Vision Transformer Wasserstein GAN (WGAN)Schwaches überwachtes Diffusionsmodell Schwach überwachter GAN Schwach überwachtes GRU Schwache überwachte LSTM Schwache rekurrente neuronale Netze Schwach überwachter Transformer Schwacher überwachter Variationsautoencoder Schwach überwachter Vision Transformer (WS-ViT)

Mehr in Deep Learning

Architekturen & Training 124