Linear Digressions

Neural Nets (Part 2)

Linear Digressions

In the last episode, we zipped through neural nets and got a quick idea of how they work and why they can be so powerful. Here’s the real payoff of that work: In this episode, we’ll talk about a brand-new pair of results, one from Stanford and one from Google, that use neural nets to perform automated picture captioning. One neural net does the object and relationship recognition of the image, a second neural net handles the natural language processing required to express that in an English sentence, and when you put them together you get an automated captioning tool. Two heads are better than one indeed...

Next Episodes

Linear Digressions

Neural Nets (Part 1) @ Linear Digressions

πŸ“† 2015-05-01 20:59 / βŒ› 00:09:00


Linear Digressions

Inferring Authorship (Part 2) @ Linear Digressions

πŸ“† 2015-04-28 18:56 / βŒ› 00:14:04


Linear Digressions

Inferring Authorship (Part 1) @ Linear Digressions

πŸ“† 2015-04-16 19:25 / βŒ› 00:08:51


Linear Digressions

Statistical Mistakes and the Challenger Disaster @ Linear Digressions

πŸ“† 2015-04-06 21:36 / βŒ› 00:13:09


Linear Digressions

Genetics and Um Detection (HMM Part 2) @ Linear Digressions

πŸ“† 2015-03-25 18:29 / βŒ› 00:14:49