Activity for Attila Kertesz-Farkas
-
Attila Kertesz-Farkas committed [d468a3]
minor update in text
-
removed DSE ID
-
minor adjustments
-
minor fixes
-
finished
-
finalized the sentiment experiments, reduced page numbe
-
typo fixed
-
Merge branch 'master' of ssh://git.code.sf.net/p/machine-reasoning/code
-
revised
-
fixed some typo
-
minor type fixed
-
Merge branch 'master' of ssh://git.code.sf.net/p/machine-reasoning/code
-
Merge branch 'master' of ssh://git.code.sf.net/p/machine-reasoning/code
-
type fix
-
Merge branch 'master' of ssh://git.code.sf.net/p/machine-reasoning/code
-
minor update
-
Merge branch 'master' of ssh://git.code.sf.net/p/machine-reasoning/code
-
typo fix
-
typo fix|
-
paper draft 0 done
-
Merge branch 'master' of ssh://git.code.sf.net/p/machine-reasoning/code
-
minor update on text
-
hypernym probes
-
Merge branch 'master' of ssh://git.code.sf.net/p/machine-reasoning/code
-
updated paper draft
-
main.pdf removed
-
MS updated
-
compositionality paper updated
-
Compositionality manuscript added
-
final ConvNet architecture
-
conflict resolved
-
typos fixed
-
supervisors review
-
Merge branch 'master' of ssh://git.code.sf.net/p/phd-thesis-pavel/code
-
added some comments
-
minor update
-
response to reviewers added
-
Merge branch 'master' of ssh://git.code.sf.net/p/phd-thesis-pavel/code
-
author contribution updated
-
comments added
-
added updates
-
conflict resolved
-
finished mass spec section
-
intro is finished, but needs actions from Pavel
-
Finished chapters 3,4,5
-
original articles are added
-
conflict resolved
-
comments
-
revised db search, few minor comments
-
comments on fdr
-
comments about validation}
-
comments for baikal model test
-
revision request
-
comments added
-
added recent interesting articles
-
added finished method section
-
intorduction finished
-
implement bidaf with tensorflow.
-
compare their performance with respect to Tensorflow_vs_pytorch_for_neural_NLP.ipynb
-
prepare a very nice, comprehensive and beautiful labbook about the results which summarizes our findings. Use nice language, easy to understand.
-
read articles on BERT, QAnet, BAG, capsNets and dynamic routing.
-
train or download a model for sentence entailment. (i.e. to predict if the meaning of two sentences are the same)
-
decide which word embedding should be used.
-
model with capsule nets.
-
summer practice projects
-
model with capsule nets.
-
Check BERT if it is useful for us.
-
decide which word embedding should be used.
-
train or download a model for sentence entailment. (i.e. to predict if the meaning of two sentences are the same)
-
read articles on BERT, QAnet, BAG, capsNets and dynamic routing.
-
prepare a very nice, comprehensive and beautiful labbook about the results which summarizes our findings. Use nice language, easy to understand.
-
compare their performance with respect to Tensorflow_vs_pytorch_for_neural_NLP.ipynb
-
implement bidaf with tensorflow.
-
check that the weight update is correct in own implementation.
-
bibliography updated
-
conflict resolved
-
conflict resolved
-
conflict resolved
1 >
Gen AI apps are built with MongoDB Atlas
Atlas offers built-in vector search and global availability across 125+ regions. Start building AI apps faster, all in one place.
Try Free →