athn-nik / cognitive_nlp Goto Github PK
View Code? Open in Web Editor NEWLicense: MIT License
License: MIT License
For every experiment's data extract the preprocessed data.Experiment for size store it and fix input pipeline for the new structure
Explore voxel selection implementation.
Current code:
Run and debug voxel selection from data. Parametrize normalization for the decoder to use
Currently we have Mitchell and Perreira Dataset.Ensmebling proposed --> Same voxel selection dimension
May reduce performance in case of Mitchell
Again weights are up.Do the text preprocessing i do for voc extraction.You know the rest or ask me
Methods in this paper
Implementation not currently available but easy
Ideas are:
Hard-coded brain parts for certain words
Text generation
Compositionality in brain
Use brain's advantage to learn from few examples
@georgepar follow below script to extract dataset and i will fix a function that given a word return the its embeddings.In weights folder you will find the trained weights for each of three experiments.The embeddings which will be used are glove42B.300d
import numpy as np
from sklearn.datasets.base import Bunch
from .utils import _get_as_pd
def fetch_MEN(which="all", form="natural"):
"""
Fetch MEN dataset for testing similarity and relatedness
----------
which : "all", "test" or "dev"
form : "lem" or "natural"
Returns
-------
data : sklearn.datasets.base.Bunch
dictionary-like object. Keys of interest:
'X': matrix of 2 words per column,
'y': vector with scores
Published at http://clic.cimec.unitn.it/~elia.bruni/MEN.html.
"""
if which == "dev":
data = _get_as_pd('https://www.dropbox.com/s/c0hm5dd95xapenf/EN-MEN-LEM-DEV.txt?dl=1',
'similarity', header=None, sep=" ")
elif which == "test":
data = _get_as_pd('https://www.dropbox.com/s/vdmqgvn65smm2ah/EN-MEN-LEM-TEST.txt?dl=1',
'similarity/EN-MEN-LEM-TEST', header=None, sep=" ")
elif which == "all":
data = _get_as_pd('https://www.dropbox.com/s/b9rv8s7l32ni274/EN-MEN-LEM.txt?dl=1',
'similarity', header=None, sep=" ")
else:
raise RuntimeError("Not recognized which parameter")
if form == "natural":
# Remove last two chars from first two columns
data = data.apply(lambda x: [y if isinstance(y, float) else y[0:-2] for y in x])
elif form != "lem":
raise RuntimeError("Not recognized form argument")
return Bunch(X=data.values[:, 0:2].astype("object"), y=data.values[:, 2:].astype(np.float) / 5.0)
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.