Dual Space Training for GANs: A Pathway to Efficient and Creative Generative Models
Fuente:
arXiv
Salvato in:
| Autore principale: | |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929557933654016 |
|---|---|
| author | Modrekiladze, Beka |
| author_facet | Modrekiladze, Beka |
| contents | Generative Adversarial Networks (GANs) have demonstrated remarkable advancements in generative modeling; however, their training is often resource-intensive, requiring extensive computational time and hundreds of thousands of epochs. This paper proposes a novel optimization approach that transforms the training process by operating within a dual space of the initial data using invertible mappings, specifically autoencoders. By training GANs on the encoded representations in the dual space, which encapsulate the most salient features of the data, the generative process becomes significantly more efficient and potentially reveals underlying patterns beyond human recognition. This approach not only enhances training speed and resource usage but also explores the philosophical question of whether models can generate insights that transcend the human intelligence while being limited by the human-generated data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_19009 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Dual Space Training for GANs: A Pathway to Efficient and Creative Generative Models Modrekiladze, Beka Machine Learning Artificial Intelligence Generative Adversarial Networks (GANs) have demonstrated remarkable advancements in generative modeling; however, their training is often resource-intensive, requiring extensive computational time and hundreds of thousands of epochs. This paper proposes a novel optimization approach that transforms the training process by operating within a dual space of the initial data using invertible mappings, specifically autoencoders. By training GANs on the encoded representations in the dual space, which encapsulate the most salient features of the data, the generative process becomes significantly more efficient and potentially reveals underlying patterns beyond human recognition. This approach not only enhances training speed and resource usage but also explores the philosophical question of whether models can generate insights that transcend the human intelligence while being limited by the human-generated data. |
| title | Dual Space Training for GANs: A Pathway to Efficient and Creative Generative Models |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2410.19009 |