1 |
Cross-Lingual Text-to-Speech Using Multi-Task Learning and Speaker Classifier Joint Training ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Global genetic differentiation of complex traits shaped by natural selection in humans.
|
|
|
|
In: Nature communications, vol. 9, no. 1, pp. 1865 (2018)
|
|
BASE
|
|
Show details
|
|
4 |
Using Network-Text Analysis to Characterise Learner Engagement in Active Video Watching
|
|
|
|
BASE
|
|
Show details
|
|
5 |
EEG oscillations during word processing predict MCI conversion to Alzheimer's disease
|
|
|
|
BASE
|
|
Show details
|
|
6 |
A hidden knowledge discovering approach for past tense and plural problems to language cognition
|
|
|
|
Abstract:
One purpose of using computational models in cognitive related researches is to use them as a tool to understand human's learning processes, especially focusing on understanding the processes of language development. Although connectionist computational models can simulate the learning process in a black-box way, understanding the inside rational relations is as important as the correlations between input and output. Therefore, this problem can be transferred to a machine learning problem: to discover the hidden knowledge(rules) for a non-classification problem domain. Unfortunately, most available rule extraction techniques are focusing on classification problems, few of them can solve non-classification problems. In this paper, we proposed a hidden knowledge exploration model for the Auto-encoder based computational models which implements the following two functions: (1) simulate the language learning process, (2) reveal the correlations between prior knowledge and the new knowledge through re-building the inherent rules. Experiments prove its efficiency by comparing its fidelity performances with the well performed black-box learning technique(Multi Layer Perceptron Artificial Neural Network).
|
|
URL: https://eprints.bbk.ac.uk/id/eprint/18293/ https://doi.org/10.1109/SKG.2016.015
|
|
BASE
|
|
Hide details
|
|
10 |
Childhood intelligence is heritable, highly polygenic and associated with FNBP1L
|
|
|
|
BASE
|
|
Show details
|
|
12 |
Childhood intelligence is heritable, highly polygenic and associated with FNBP1L
|
|
|
|
BASE
|
|
Show details
|
|
13 |
Childhood intelligence is heritable, highly polygenic and associated with FNBP1L.
|
|
|
|
In: Mol Psychiatry , 19 (2) 253 - 258. (2014) (2014)
|
|
BASE
|
|
Show details
|
|
14 |
Childhood intelligence is heritable, highly polygenic and associated with FNBP1L
|
|
|
|
BASE
|
|
Show details
|
|
15 |
Childhood intelligence is heritable, highly polygenic and associated with FNBP1L
|
|
|
|
BASE
|
|
Show details
|
|
16 |
Childhood intelligence is heritable, highly polygenic and associated with FNBP1L
|
|
|
|
BASE
|
|
Show details
|
|
17 |
DNA evidence for strong genome-wide pleiotropy of cognitive and learning abilities.
|
|
|
|
In: Behav Genet , 43 (4) 267 - 273. (2013) (2013)
|
|
BASE
|
|
Show details
|
|
19 |
Cardiorenal end points in a trial of aliskiren for type 2 diabetes.
|
|
|
|
In: New England Journal of Medicine, vol. 367, no. 23, pp. 2204-2213 (2012)
|
|
BASE
|
|
Show details
|
|
20 |
Children's perceptions of the impact of participation in an intercultural educational programme
|
|
|
|
BASE
|
|
Show details
|
|
|
|