Jeff Hawkins suggests programming the neocortex for AI
Jeff Hawkins (Jeff Hawkins) is known as the founder of Palm Computing and the inventor of the Palm Pilot handheld computer. After his first startup, he founded Handspring and created the Treo device. Now this extraordinary mind is trying to prove another of its ideas: the possibility of creating artificial intelligence on the model of the neocortex of the human brain. To test the theory, Jeff Hawkins modeled the neocortex for machine intelligence. With this system, independent programmers can create new generation of self-learning computer programs.
For work in the field of artificial intelligence, Hawkins founded Numenta , and now she has finally released her first product: experimental software that implements Hierarchical Temporal Memory, HTM algorithms: this is analogous to the neocortex.
The HTM system is a software environment that is as close as possible to the human brain: it supports self-study principles for finding solutions to problems. The basic tools are the “sensors”, through which the initial information for analysis is fed into the system. The HTM design is a tree structure, in each node of which there is a basic function for learning and memorizing. The hierarchy of objects in the memory of the HTM models the structure of the world, which by its nature is hierarchical in time and space.
')
You can read more about the HTM system in the documentation ( PDF ), and also see Jeff Hawkins’s presentation at the cognitive computing congress ( video 152.9 MB ). Alternatively, you can read Hawkins book "On Intelligence" - there is a partial description of the HTM in the sixth chapter.
Additionally:
Discussion “On Intelligence” on the forum “Artificial Intelligence: Programming”
Deff Hawkins "On Intellect" (Russian; book in .DOC format)
For work in the field of artificial intelligence, Hawkins founded Numenta , and now she has finally released her first product: experimental software that implements Hierarchical Temporal Memory, HTM algorithms: this is analogous to the neocortex.
The HTM system is a software environment that is as close as possible to the human brain: it supports self-study principles for finding solutions to problems. The basic tools are the “sensors”, through which the initial information for analysis is fed into the system. The HTM design is a tree structure, in each node of which there is a basic function for learning and memorizing. The hierarchy of objects in the memory of the HTM models the structure of the world, which by its nature is hierarchical in time and space.
')
You can read more about the HTM system in the documentation ( PDF ), and also see Jeff Hawkins’s presentation at the cognitive computing congress ( video 152.9 MB ). Alternatively, you can read Hawkins book "On Intelligence" - there is a partial description of the HTM in the sixth chapter.
Additionally:
Discussion “On Intelligence” on the forum “Artificial Intelligence: Programming”
Deff Hawkins "On Intellect" (Russian; book in .DOC format)
Source: https://habr.com/ru/post/5923/
All Articles