Results 1 -
3 of
3
Very efficient learning of structured classes of subsequential functions from positive data
"... In this paper, we present a new algorithm that can identify in polynomial time and data using positive examples any class of subsequential functions that share a particular finite-state structure. While this structure is given to the learner a priori, it allows for the exact learning of partial func ..."
Abstract
-
Cited by 1 (1 self)
- Add to MetaCart
In this paper, we present a new algorithm that can identify in polynomial time and data using positive examples any class of subsequential functions that share a particular finite-state structure. While this structure is given to the learner a priori, it allows for the exact learning of partial functions, and both the time and data complexity of the algorithm are linear. We demonstrate the algorithm on examples from natural language phonology and morphology in which the needed structure has been argued to be plausibly known in advance. A procedure for making any subsequential transducer onward without changing its structure is also presented.
Predicting Sequential Data with LSTMs Augmented with Strictly 2-Piecewise Input Vectors
, 2016
"... Abstract Recurrent neural networks such as Long-Short Term Memory (LSTM) are often used to learn from various kinds of time-series data, especially those that involved long-distance dependencies. We introduce a vector representation for the Strictly 2-Piecewise (SP-2) formal languages, which encode ..."
Abstract
- Add to MetaCart
(Show Context)
Abstract Recurrent neural networks such as Long-Short Term Memory (LSTM) are often used to learn from various kinds of time-series data, especially those that involved long-distance dependencies. We introduce a vector representation for the Strictly 2-Piecewise (SP-2) formal languages, which encode certain kinds of long-distance dependencies using subsequences. These vectors are added to the LSTM architecture as an additional input. Through experiments with the problems in the SPiCe dataset
Longest Common Prefix
, 2014
"... Very efficient learning of structured classes of subsequential functions from ..."
Abstract
- Add to MetaCart
Very efficient learning of structured classes of subsequential functions from
