• 목록
• 답변
• 글쓰기
• 게시판 리스트 옵션
  • 수정
  • 삭제

Hierarchical temporal memory (HTM) is a biologically constrained machine intelligence technology developed by Numenta. Originally described within the 2004 e-book On Intelligence by Jeff Hawkins with Sandra Blakeslee, HTM is primarily used right this moment for anomaly detection in streaming information. The technology relies on neuroscience and the physiology and interaction of pyramidal neurons within the neocortex of the mammalian (in particular, human) brain. At the core of HTM are studying algorithms that can store, be taught, infer, and recall excessive-order sequences. Not like most different machine studying strategies, Memory Wave HTM consistently learns (in an unsupervised process) time-primarily based patterns in unlabeled data. HTM is robust to noise, and has excessive capacity (it might be taught multiple patterns concurrently). A typical HTM network is a tree-formed hierarchy of ranges (to not be confused with the "layers" of the neocortex, as described below). These ranges are composed of smaller components referred to as regions (or nodes). A single stage in the hierarchy probably comprises several areas. Increased hierarchy levels typically have fewer regions.

Greater hierarchy ranges can reuse patterns discovered at the lower ranges by combining them to memorize extra advanced patterns. Each HTM region has the identical basic operate. In studying and inference modes, sensory knowledge (e.g. information from the eyes) comes into bottom-degree areas. In era mode, the underside level regions output the generated sample of a given class. When set in inference mode, a area (in every level) interprets info developing from its "baby" areas as probabilities of the classes it has in Memory Wave memory booster. Each HTM region learns by identifying and memorizing spatial patterns-mixtures of enter bits that often occur at the same time. It then identifies temporal sequences of spatial patterns which can be more likely to occur one after another. HTM is the algorithmic element to Jeff Hawkins’ Thousand Brains Principle of Intelligence. So new findings on the neocortex are progressively incorporated into the HTM model, Memory Wave which changes over time in response. The brand new findings do not essentially invalidate the earlier components of the mannequin, so ideas from one technology are not essentially excluded in its successive one.

During coaching, a node (or area) receives a temporal sequence of spatial patterns as its enter. 1. The spatial pooling identifies (in the input) ceaselessly noticed patterns and memorise them as "coincidences". Patterns which can be considerably related to one another are treated as the same coincidence. Numerous potential input patterns are reduced to a manageable number of known coincidences. 2. The temporal pooling partitions coincidences that are likely to observe each other in the training sequence into temporal teams. Every group of patterns represents a "trigger" of the enter pattern (or "identify" in On Intelligence). The concepts of spatial pooling and temporal pooling are still quite important in the current HTM algorithms. Temporal pooling will not be yet nicely understood, and its that means has changed over time (as the HTM algorithms advanced). Throughout inference, the node calculates the set of probabilities that a sample belongs to every known coincidence. Then it calculates the probabilities that the input represents every temporal group.

The set of probabilities assigned to the teams known as a node's "perception" concerning the input pattern. This perception is the results of the inference that is passed to a number of "guardian" nodes in the subsequent increased level of the hierarchy. If sequences of patterns are just like the coaching sequences, then the assigned probabilities to the teams won't change as typically as patterns are received. In a more normal scheme, Memory Wave memory booster the node's belief will be despatched to the enter of any node(s) at any level(s), however the connections between the nodes are still fixed. The upper-level node combines this output with the output from different baby nodes thus forming its own input pattern. Since resolution in area and time is misplaced in each node as described above, beliefs formed by larger-degree nodes symbolize an excellent larger vary of house and time. This is supposed to replicate the organisation of the physical world as it is perceived by the human mind.