Autoencoders
Linear Digressions
Autoencoders are neural nets that are optimized for creating outputs that... look like the inputs to the network. Turns out this is a not-too-shabby way to do unsupervised machine learning with neural nets.Next Episodes
When Private Data Isn't Private Anymore @ Linear Digressions
📆 2018-03-05 04:35 / ⌛ 00:26:20
What makes a machine learning algorithm "superhuman"? @ Linear Digressions
📆 2018-02-26 05:52 / ⌛ 00:34:48
Open Data and Open Science @ Linear Digressions
📆 2018-02-19 02:39 / ⌛ 00:16:54
Defining the quality of a machine learning production system @ Linear Digressions
📆 2018-02-12 03:00 / ⌛ 00:20:29
Auto-generating websites with deep learning @ Linear Digressions
📆 2018-02-05 00:02 / ⌛ 00:19:24