Artwork

Contenuto fornito da Wilf Nelson. Tutti i contenuti dei podcast, inclusi episodi, grafica e descrizioni dei podcast, vengono caricati e forniti direttamente da Wilf Nelson o dal partner della piattaforma podcast. Se ritieni che qualcuno stia utilizzando la tua opera protetta da copyright senza la tua autorizzazione, puoi seguire la procedura descritta qui https://it.player.fm/legal.
Player FM - App Podcast
Vai offline con l'app Player FM !

Think Fast S2, EP20 – How neuroscientists made deep fakes with Dr Michiel Spape

20:00
 
Condividi
 

Serie archiviate ("Feed non attivo" status)

When? This feed was archived on January 20, 2024 12:08 (2M ago). Last successful fetch was on August 08, 2022 20:46 (1+ y ago)

Why? Feed non attivo status. I nostri server non sono riusciti a recuperare un feed valido per un periodo prolungato.

What now? You might be able to find a more up-to-date version using the search function. This series will no longer be checked for updates. If you believe this to be in error, please check if the publisher's feed link below is valid and contact support to request the feed be restored or if you have any other concerns about this.

Manage episode 292928989 series 2646730
Contenuto fornito da Wilf Nelson. Tutti i contenuti dei podcast, inclusi episodi, grafica e descrizioni dei podcast, vengono caricati e forniti direttamente da Wilf Nelson o dal partner della piattaforma podcast. Se ritieni che qualcuno stia utilizzando la tua opera protetta da copyright senza la tua autorizzazione, puoi seguire la procedura descritta qui https://it.player.fm/legal.
In this episode, I am interviewing Dr Michael Spape on how his work into making AI that could recognise faces because of the different ways humans process faces lead to deep fakes. Michael walks us through how using EEG caps to process the brain's signals when seeing different types of faces generated data that humans cannot understand, but AI can. He tells us how he built and trained these intelligent programs to understand the neural signals behind faces and then what could be done with these completed but limited AI to start making new faces that haven't existed anywhere else. You will have undoubtedly heard about deep fakes, this episode shows you the labs and research that inspired them.
  continue reading

106 episodi

Artwork
iconCondividi
 

Serie archiviate ("Feed non attivo" status)

When? This feed was archived on January 20, 2024 12:08 (2M ago). Last successful fetch was on August 08, 2022 20:46 (1+ y ago)

Why? Feed non attivo status. I nostri server non sono riusciti a recuperare un feed valido per un periodo prolungato.

What now? You might be able to find a more up-to-date version using the search function. This series will no longer be checked for updates. If you believe this to be in error, please check if the publisher's feed link below is valid and contact support to request the feed be restored or if you have any other concerns about this.

Manage episode 292928989 series 2646730
Contenuto fornito da Wilf Nelson. Tutti i contenuti dei podcast, inclusi episodi, grafica e descrizioni dei podcast, vengono caricati e forniti direttamente da Wilf Nelson o dal partner della piattaforma podcast. Se ritieni che qualcuno stia utilizzando la tua opera protetta da copyright senza la tua autorizzazione, puoi seguire la procedura descritta qui https://it.player.fm/legal.
In this episode, I am interviewing Dr Michael Spape on how his work into making AI that could recognise faces because of the different ways humans process faces lead to deep fakes. Michael walks us through how using EEG caps to process the brain's signals when seeing different types of faces generated data that humans cannot understand, but AI can. He tells us how he built and trained these intelligent programs to understand the neural signals behind faces and then what could be done with these completed but limited AI to start making new faces that haven't existed anywhere else. You will have undoubtedly heard about deep fakes, this episode shows you the labs and research that inspired them.
  continue reading

106 episodi

Tutti gli episodi

×
 
Loading …

Benvenuto su Player FM!

Player FM ricerca sul web podcast di alta qualità che tu possa goderti adesso. È la migliore app di podcast e funziona su Android, iPhone e web. Registrati per sincronizzare le iscrizioni su tutti i tuoi dispositivi.

 

Guida rapida