[MINI] Generative Adversarial Networks
Data Skeptic5 Mai 2017

[MINI] Generative Adversarial Networks

GANs are an unsupervised learning method involving two neural networks iteratively competing. The discriminator is a typical learning system. It attempts to develop the ability to recognize members of a certain class, such as all photos which have birds in them. The generator attempts to create false examples which the discriminator incorrectly classifies. In successive training rounds, the networks examine each and play a mini-max game of trying to harm the performance of the other.

In addition to being a useful way of training networks in the absence of a large body of labeled data, there are additional benefits. The discriminator may end up learning more about edge cases than it otherwise would be given typical examples. Also, the generator's false images can be novel and interesting on their own.

The concept was first introduced in the paper Generative Adversarial Networks.

Denne episoden er hentet fra en åpen RSS-feed og er ikke publisert av Podme. Den kan derfor inneholde annonser.

Episoder(601)

Privacy Preference Signals

Privacy Preference Signals

Have you ever wondered what goes on under the hood when you accept a website's cookies? Today, Maximilian Hils, a PhD student in Computer Science, at the University of Innsbruck, Austria, dissects the...

4 Jul 202233min

Neural Architecture Search for CTR Prediction

Neural Architecture Search for CTR Prediction

Ravi Krishna joins us today to talk about his recent work on a differentiable NAS framework for ads CTR prediction. He discussed what CTR prediction is about and why his NAS framework helps in buildin...

27 Jun 202228min

Algorithmic PPC Management

Algorithmic PPC Management

Effectively managing a large budget of pay per click advertising demands software solutions. When spending multi-million dollar budgets on hundreds of thousands of keywords, an effective algorithmic s...

21 Jun 202243min

Data Skeptic: Ad Tech

Data Skeptic: Ad Tech

Increasingly, people get most if not all of the information they consume online. Alongside the web sites, videos, apps, and other destinations, we're consistently served advertisements alongside the o...

18 Jun 202242min

The Reliability of Mobile Phone Data

The Reliability of Mobile Phone Data

Our mobile phones generate an incredible amount of data inbound and outbound. In today's episode, Nishant Kishore, a PhD graduate of Harvard University in Infectious Disease Epidemiology, explains how...

13 Jun 202249min

Haywire Algorithms

Haywire Algorithms

The pandemic changed how we lived. And this had a ripple effect on the performance of machine learning models. Ravi Parikh joins us today to discuss how the pandemic has affected the performance of ma...

6 Jun 202233min

School Reopening Analysis

School Reopening Analysis

Carly Lupton-Smith joins us today to speak about her research which investigated the consistency between household and county measures of school reopening. Carly is a doctoral researcher in Biostatist...

30 Mai 202233min

Modern Data Stacks

Modern Data Stacks

Today, we are joined by Alexander Thor, a Product Manager at Vizlib, makers of Astrato. Astrato is a data analytics and business intelligence tool built on the cloud and for the cloud. Alexander discu...

26 Mai 202234min

Populært innen Vitenskap

fastlegen
tingenes-tilstand
jss
rss-zahid-ali-hjelper-deg
rekommandert
sinnsyn
rss-paradigmepodden
liberal-halvtime
vett-og-vitenskap-med-gaute-einevoll
forskningno
rss-overskuddsliv
villmarksliv
kvinnehelsepodden
nordnorsk-historie
grunnstoffene
tidlose-historier
rss-inn-til-kjernen-med-sunniva-rose
nevropodden
dekodet-2
rss-rekommandert