With Deep Learning, Ng says, you just give the system a lot of data “so it can discover by itself what some of the concepts in the world are.” Last year, one of his algorithms taught itself torecognize cats after scanning millions of images on the internet. The algorithm didn’t know the word “cat” — Ng had to supply that — but over time, it learned to identify the furry creatures we know as cats, all on its own.
This approach is inspired by how scientists believe that humans learn. As babies, we watch our environments and start to understand the structure of objects we encounter, but until a parent tells us what it is, we can’t put a name to it.
From TopicMinder alerts: Tech Trends
- Relational Modeling? Not as we know it! This topic deserves a post of its own. I have been reading up a bunch of stuff on flexible database design, using semantic technologies to ease schema evolution and a bunch of other interesting ideas.
- 1CThe distributed social web 1D
- Semantic Microblogging
- A lightweight ontology for annotating offerings on the Web
- A Scalable, Transactional Data Store for Web 2.0 Services
- Speaking the Language of the Brain (Video – Building a scientific base for the human mind)