#GenerativeAdversarialNetwork

MathiasTCK.bsky.social

@mathiastck.bsky.social

2 months ago

We make a #generator and a #discriminator fight. A lot.

"
In a #GAN, two #NeuralNetworks compete with each other in the form of a #ZeroSumGame, where one agent's gain is another agent's loss
"

#GenerativeAdversarialNetwork

MathiasTCK.bsky.social

@mathiastck.bsky.social

2 months ago

Generative adversarial network - Wikipedia

For awhile I would clarify I am not talking about a #LargeLanguageModel , I am talking about a #GenerativeAdversarialNetwork

en.wikipedia.org/wiki/Generat...

But honestly, but that's just because I'm a game theory aficionado who thinks Generative Adversarial Network is a cool term.

#LLM
#GAN

MathiasTCK.bsky.social

@mathiastck.bsky.social

3 months ago

#AbominableIntelligence
#Heretechnica
#Hereteknica
#GrimDark
#Replicant

#MachineLearning #LargeLanguageModel
#GenerativeAdversarialNetwork

#AIDoesNotUnderstand
#DoesNotThink
#NotConscious

#replicate
#simulate
#probabilistically

bsky.app/profile/math...

MathiasTCK.bsky.social

@mathiastck.bsky.social

3 months ago

When appropriate I try to use the right term:

#MachineLearning #LargeLanguageModel
#GenerativeAdversarialNetwork

I find myself putting "AI" in quotes when I type it. It does not understand, it does not think, it is not conscious, its job is to #replicate to #simulate to guess, probabilistically

@tag-bot.bsky.social

8 months ago

#superfake #deepfake #syntheticmedia #ai-generatedimage #ai-generatedvideo #contentcreation #digitalforgery #visualforgery #fakeimage #fakevideo #facerecognition #generativeadversarialnetwork #gans #industrytrend #costrange #mediaengineering #visualart #digitalart #mediaindustry #journalism

JMIR Publications

@jmirpub.bsky.social

8 months ago

Enhancing Ultrasound Image Quality Across Disease Domains: Application of Cycle-Consistent Generative Adversarial Network and Perceptual Loss Background: Numerous studies have explored image processing techniques aimed at enhancing ultrasound images to narrow the performance gap between low-quality portable devices and high-end ultrasound equipment. These investigations often use registered image pairs created by modifying the same image through methods like down sampling or adding noise, rather than using separate images from different machines. Additionally, they rely on organ-specific features, limiting the models’ generalizability across various imaging conditions and devices. The challenge remains to develop a universal framework capable of improving image quality across different devices and conditions, independent of registration or specific organ characteristics. Objective: This study aims to develop a robust framework that enhances the quality of ultrasound images, particularly those captured with compact, portable devices, which are often constrained by low quality due to hardware limitations. The framework is designed to effectively process nonregistered ultrasound image pairs, a common challenge in medical imaging, across various clinical settings and device types. By addressing these challenges, the research seeks to provide a more generalized and adaptable solution that can be widely applied across diverse medical scenarios, improving the accessibility and quality of diagnostic imaging. Methods: A retrospective analysis was conducted by using a cycle-consistent generative adversarial network (CycleGAN) framework enhanced with perceptual loss to improve the quality of ultrasound images, focusing on nonregistered image pairs from various organ systems. The perceptual loss was integrated to preserve anatomical integrity by comparing deep features extracted from pretrained neural networks. The model’s performance was evaluated against corresponding high-resolution images, ensuring that the enhanced outputs closely mimic those from high-end ultrasound devices. The model was trained and validated using a publicly available, diverse dataset to ensure robustness and generalizability across different imaging scenarios. Results: The advanced CycleGAN framework, enhanced with perceptual loss, significantly outperformed the previous state-of-the-art, stable CycleGAN, in multiple evaluation metrics. Specifically, our method achieved a structural similarity index of 0.2889 versus 0.2502 (P

New JMIR BioMedEng: Enhancing Ultrasound Image Quality Across Disease Domains: Application of Cycle-Consistent Generative Adversarial Network and Perceptual Loss #Ultrasound #ImageProcessing #MachineLearning #GenerativeAdversarialNetwork #MedicalImaging

MathiasTCK.bsky.social

@mathiastck.bsky.social

9 months ago

So not your recommended tools for making things better, but what about all the people seeking to make things worse? Would a #LargeLanguageModel / #LLM be right for them?

Or perhaps a #GenerativeAdversarialNetwork / #GAN, could one of those help someone make things worse, faster?

Christoph

@trendspotter.bsky.social

1 year ago

New framework may solve mode collapse in generative adversarial network Generative adversarial networks (GANs) are widely used to synthesize intricate and realistic data by learning the distribution of authentic real samples. However, a significant challenge that GANs fac...

New framework solves mode collapse in #GenerativeAdversarialNetwork, #GAN #AI

A significant challenge that Generative Adversarial Network faces is mode collapse. Researchers proposed a new framework, Dynamic GAN (DynGAN), to resolve mode collapse in GAN.

techxplore.com/news/2024-04...

MathiasTCK.bsky.social

@mathiastck.bsky.social

1 year ago

#LargeLanguageModel #GenerativeAdversarialNetwork seem to be the 2 main types I am encountering. Using either term is a lot more illustrative of what is happening then #ArtificialIntelligence

MathiasTCK.bsky.social

@mathiastck.bsky.social

1 year ago

Generative adversarial network - Wikipedia

Yeah I hesitate everytime I type "AI", I'll use chatBot, or image generator. I like the phrase #GenerativeAdversarialNetwork because it spells out what happened:

en.wikipedia.org/wiki/Generat...