Pinned Repositories
AlphaZero-Connect4
Deep RL algorithm based on AlphaZero algorithm for the game Connect4
custom-tilt5-localizer
Localization module for Tilt5 prokect
Image-Sematic-Labeling
Image Semantic Labeling with Convolutional Neural Networks based on the paper https://arxiv.org/abs/1611.01962.
inet
INET framework for the OMNeT++ discrete event simulator
keras-rl
Deep Reinforcement Learning for Keras.
NER
Named entity tagging system that requires minimal linguistic knowledge and can be applied to several target languages without substantial changes. The system is based on the ideas of the Brill’s tagger which makes it really simple. Using supervised machine learning, we construct a series of automatons (or transducers) in order to tag a given text. The final model is composed entirely of automatons and it requires a lineal time for tagging. It was tested with the Spanish data set provided in the CoNLL-2002 attaining an overall Fβ=1 measure of 60%. Also, we present an algorithm for the construction of the final transducer used to encode all the learned contextual rules.
NER-System
Name entity recognizer based on Brill Tagger with transducers
rubiks-cube-with-math
sampled-alpha-zero
Simulated-Medical-Data
dahuerfanov's Repositories
dahuerfanov/custom-tilt5-localizer
Localization module for Tilt5 prokect
dahuerfanov/AlphaZero-Connect4
Deep RL algorithm based on AlphaZero algorithm for the game Connect4
dahuerfanov/Image-Sematic-Labeling
Image Semantic Labeling with Convolutional Neural Networks based on the paper https://arxiv.org/abs/1611.01962.
dahuerfanov/inet
INET framework for the OMNeT++ discrete event simulator
dahuerfanov/keras-rl
Deep Reinforcement Learning for Keras.
dahuerfanov/NER
Named entity tagging system that requires minimal linguistic knowledge and can be applied to several target languages without substantial changes. The system is based on the ideas of the Brill’s tagger which makes it really simple. Using supervised machine learning, we construct a series of automatons (or transducers) in order to tag a given text. The final model is composed entirely of automatons and it requires a lineal time for tagging. It was tested with the Spanish data set provided in the CoNLL-2002 attaining an overall Fβ=1 measure of 60%. Also, we present an algorithm for the construction of the final transducer used to encode all the learned contextual rules.
dahuerfanov/NER-System
Name entity recognizer based on Brill Tagger with transducers
dahuerfanov/rubiks-cube-with-math
dahuerfanov/sampled-alpha-zero
dahuerfanov/Simulated-Medical-Data