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)

Distributed Consensus

Computer Science research fellow of Cambridge University, Heidi Howard discusses Paxos, Raft, and distributed consensus in distributed systems alongside with her work "Paxos vs. Raft: Have we reached ...

30 Okt 202027min

ACID Compliance

Linhda joins Kyle today to talk through A.C.I.D. Compliance (atomicity, consistency, isolation, and durability). The presence of these four components can ensure that a database's transaction is compl...

23 Okt 202023min

National Popular Vote Interstate Compact

Patrick Rosenstiel joins us to discuss the The National Popular Vote.

16 Okt 202030min

Defending the p-value

Yudi Pawitan joins us to discuss his paper Defending the P-value.

12 Okt 202030min

Retraction Watch

Ivan Oransky joins us to discuss his work documenting the scientific peer-review process at retractionwatch.com.

5 Okt 202032min

Crowdsourced Expertise

Derek Lim joins us to discuss the paper Expertise and Dynamics within Crowdsourced Musical Knowledge Curation: A Case Study of the Genius Platform.

21 Sep 202027min

The Spread of Misinformation Online

Neil Johnson joins us to discuss the paper The online competition between pro- and anti-vaccination views.

14 Sep 202035min

Consensus Voting

Mashbat Suzuki joins us to discuss the paper How Many Freemasons Are There? The Consensus Voting Mechanism in Metric Spaces. Check out Mashbat's and many other great talks at the 13th Symposium on Alg...

7 Sep 202022min