Difference between revisions of "(Tree) Recursive Neural (Tensor) Network (RNTN)"
m (BPeat moved page (Tree) Recursive Neural (Tensor) Networks (RNTN) to (Tree) Recursive Neural (Tensor) Network (RNTN) without leaving a redirect) |
|||
| Line 5: | Line 5: | ||
Certain patterns are innately hierarchical, like the underlying parse tree of a natural language sentence. A Recursive Neural Tensor Network (RNTN) is a powerful tool for deciphering and labelling these types of patterns. Structurally, an RNTN is a binary tree with three nodes: a root and two leaves. The root and leaf nodes are not neurons, but instead they are groups of neurons – the more complicated the input data the more neurons are required. As expected, the root group connects to each leaf group, but the leaf groups do not share a connection with each other. Despite the simple structure of the net, an RNTN is capable of extracting deep, complex patterns out of a set of data. An RNTN detects patterns through a recursive process. In a sentence-parsing application where the objective is to identify the grammatical elements in a sentence (like a noun phrase or a verb phrase, for example), the first and second words are initially converted into an ordered set of numbers known as a vector. | Certain patterns are innately hierarchical, like the underlying parse tree of a natural language sentence. A Recursive Neural Tensor Network (RNTN) is a powerful tool for deciphering and labelling these types of patterns. Structurally, an RNTN is a binary tree with three nodes: a root and two leaves. The root and leaf nodes are not neurons, but instead they are groups of neurons – the more complicated the input data the more neurons are required. As expected, the root group connects to each leaf group, but the leaf groups do not share a connection with each other. Despite the simple structure of the net, an RNTN is capable of extracting deep, complex patterns out of a set of data. An RNTN detects patterns through a recursive process. In a sentence-parsing application where the objective is to identify the grammatical elements in a sentence (like a noun phrase or a verb phrase, for example), the first and second words are initially converted into an ordered set of numbers known as a vector. | ||
| + | <youtube>Io0VfObzntA<</youtube> | ||
<youtube>Z56jojdmDV0</youtube> | <youtube>Z56jojdmDV0</youtube> | ||
<youtube>wp1bgd8reDk</youtube> | <youtube>wp1bgd8reDk</youtube> | ||
<youtube>mVfPGu8rrXM</youtube> | <youtube>mVfPGu8rrXM</youtube> | ||
<youtube>RfwgqPkWZ1w</youtube> | <youtube>RfwgqPkWZ1w</youtube> | ||
Revision as of 21:50, 24 June 2018
Certain patterns are innately hierarchical, like the underlying parse tree of a natural language sentence. A Recursive Neural Tensor Network (RNTN) is a powerful tool for deciphering and labelling these types of patterns. Structurally, an RNTN is a binary tree with three nodes: a root and two leaves. The root and leaf nodes are not neurons, but instead they are groups of neurons – the more complicated the input data the more neurons are required. As expected, the root group connects to each leaf group, but the leaf groups do not share a connection with each other. Despite the simple structure of the net, an RNTN is capable of extracting deep, complex patterns out of a set of data. An RNTN detects patterns through a recursive process. In a sentence-parsing application where the objective is to identify the grammatical elements in a sentence (like a noun phrase or a verb phrase, for example), the first and second words are initially converted into an ordered set of numbers known as a vector.
