Self Governing Neural Networks (SGNN): the Projection Layer

Related tags

Deep Learning SGNN-Self-Governing-Neural-Networks-Projection-Layer
Overview

Self Governing Neural Networks (SGNN): the Projection Layer

A SGNN's word projections preprocessing pipeline in scikit-learn

In this notebook, we'll use T=80 random hashing projection functions, each of dimensionnality d=14, for a total of 1120 features per projected word in the projection function P.

Next, we'll need feedforward neural network (dense) layers on top of that (as in the paper) to re-encode the projection into something better. This is not done in the current notebook and is left to you to implement in your own neural network to train the dense layers jointly with a learning objective. The SGNN projection created hereby is therefore only a preprocessing on the text to project words into the hashing space, which becomes spase 1120-dimensional word features created dynamically hereby. Only the CountVectorizer needs to be fitted, as it is a char n-gram term frequency prior to the hasher. This one could be computed dynamically too without any fit, as it would be possible to use the power set of the possible n-grams as sparse indices computed on the fly as (indices, count_value) tuples, too.

import sklearn
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.pipeline import Pipeline, FeatureUnion
from sklearn.random_projection import SparseRandomProjection
from sklearn.base import BaseEstimator, TransformerMixin
from sklearn.metrics.pairwise import cosine_similarity

from collections import Counter
from pprint import pprint

Preparing dummy data for demonstration:

SentenceTokenizer.MAXIMUM_SENTENCE_LENGTH: # clip too long sentences. sub_phrase = phrase[:SentenceTokenizer.MAXIMUM_SENTENCE_LENGTH].lstrip() splitted_string.append(sub_phrase) phrase = phrase[SentenceTokenizer.MAXIMUM_SENTENCE_LENGTH:].rstrip() if len(phrase) >= SentenceTokenizer.MINIMUM_SENTENCE_LENGTH: splitted_string.append(phrase) return splitted_string with open("./data/How-to-Grow-Neat-Software-Architecture-out-of-Jupyter-Notebooks.md") as f: raw_data = f.read() test_str_tokenized = SentenceTokenizer().fit_transform(raw_data) # Print text example: print(len(test_str_tokenized)) pprint(test_str_tokenized[3:9])"> 
class SentenceTokenizer(BaseEstimator, TransformerMixin):
    # char lengths:
    MINIMUM_SENTENCE_LENGTH = 10
    MAXIMUM_SENTENCE_LENGTH = 200
    
    def fit(self, X, y=None):
        return self
    
    def transform(self, X):
        return self._split(X)
    
    def _split(self, string_):
        splitted_string = []
        
        sep = chr(29)  # special separator character to split sentences or phrases.
        string_ = string_.strip().replace(".", "." + sep).replace("?", "?" + sep).replace("!", "!" + sep).replace(";", ";" + sep).replace("\n", "\n" + sep)
        for phrase in string_.split(sep):
            phrase = phrase.strip()
            
            while len(phrase) > SentenceTokenizer.MAXIMUM_SENTENCE_LENGTH:
                # clip too long sentences.
                sub_phrase = phrase[:SentenceTokenizer.MAXIMUM_SENTENCE_LENGTH].lstrip()
                splitted_string.append(sub_phrase)
                phrase = phrase[SentenceTokenizer.MAXIMUM_SENTENCE_LENGTH:].rstrip()
            
            if len(phrase) >= SentenceTokenizer.MINIMUM_SENTENCE_LENGTH:
                splitted_string.append(phrase)

        return splitted_string


with open("./data/How-to-Grow-Neat-Software-Architecture-out-of-Jupyter-Notebooks.md") as f:
    raw_data = f.read()

test_str_tokenized = SentenceTokenizer().fit_transform(raw_data)

# Print text example:
print(len(test_str_tokenized))
pprint(test_str_tokenized[3:9])
168
["Have you ever been in the situation where you've got Jupyter notebooks "
 '(iPython notebooks) so huge that you were feeling stuck in your code?',
 'Or even worse: have you ever found yourself duplicating your notebook to do '
 'changes, and then ending up with lots of badly named notebooks?',
 "Well, we've all been here if using notebooks long enough.",
 'So how should we code with notebooks?',
 "First, let's see why we need to be careful with notebooks.",
 "Then, let's see how to do TDD inside notebook cells and how to grow a neat "
 'software architecture out of your notebooks.']

Creating a SGNN preprocessing pipeline's classes

<" end_of_word = ">" out = [ [ begin_of_word + word + end_of_word for word in sentence.replace("//", " /").replace("/", " /").replace("-", " -").replace(" ", " ").split(" ") if not len(word) == 0 ] for sentence in X ] return out "> 
class WordTokenizer(BaseEstimator, TransformerMixin):
    
    def fit(self, X, y=None):
        return self
    
    def transform(self, X):
        begin_of_word = "<"
        end_of_word = ">"
        out = [
            [
                begin_of_word + word + end_of_word
                for word in sentence.replace("//", " /").replace("/", " /").replace("-", " -").replace("  ", " ").split(" ")
                if not len(word) == 0
            ]
            for sentence in X
        ]
        return out
char_ngram_range = (1, 4)

char_term_frequency_params = {
    'char_term_frequency__analyzer': 'char',
    'char_term_frequency__lowercase': False,
    'char_term_frequency__ngram_range': char_ngram_range,
    'char_term_frequency__strip_accents': None,
    'char_term_frequency__min_df': 2,
    'char_term_frequency__max_df': 0.99,
    'char_term_frequency__max_features': int(1e7),
}

class CountVectorizer3D(CountVectorizer):

    def fit(self, X, y=None):
        X_flattened_2D = sum(X.copy(), [])
        super(CountVectorizer3D, self).fit_transform(X_flattened_2D, y)  # can't simply call "fit"
        return self

    def transform(self, X):
        return [
            super(CountVectorizer3D, self).transform(x_2D)
            for x_2D in X
        ]
    
    def fit_transform(self, X, y=None):
        return self.fit(X, y).transform(X)
import scipy.sparse as sp

T = 80
d = 14

hashing_feature_union_params = {
    # T=80 projections for each of dimension d=14: 80 * 14 = 1120-dimensionnal word projections.
    **{'union__sparse_random_projection_hasher_{}__n_components'.format(t): d
       for t in range(T)
    },
    **{'union__sparse_random_projection_hasher_{}__dense_output'.format(t): False  # only AFTER hashing.
       for t in range(T)
    }
}

class FeatureUnion3D(FeatureUnion):
    
    def fit(self, X, y=None):
        X_flattened_2D = sp.vstack(X, format='csr')
        super(FeatureUnion3D, self).fit(X_flattened_2D, y)
        return self
    
    def transform(self, X): 
        return [
            super(FeatureUnion3D, self).transform(x_2D)
            for x_2D in X
        ]
    
    def fit_transform(self, X, y=None):
        return self.fit(X, y).transform(X)

Fitting the pipeline

Note: at fit time, the only thing done is to discard some unused char n-grams and to instanciate the random hash, the whole thing could be independent of the data, but here because of discarding the n-grams, we need to "fit" the data. Therefore, fitting could be avoided all along, but we fit here for simplicity of implementation using scikit-learn.

params = dict()
params.update(char_term_frequency_params)
params.update(hashing_feature_union_params)

pipeline = Pipeline([
    ("word_tokenizer", WordTokenizer()),
    ("char_term_frequency", CountVectorizer3D()),
    ('union', FeatureUnion3D([
        ('sparse_random_projection_hasher_{}'.format(t), SparseRandomProjection())
        for t in range(T)
    ]))
])
pipeline.set_params(**params)

result = pipeline.fit_transform(test_str_tokenized)

print(len(result), len(test_str_tokenized))
print(result[0].shape)
168 168
(12, 1120)

Let's see the output and its form.

print(result[0].toarray().shape)
print(result[0].toarray()[0].tolist())
print("")

# The whole thing is quite discrete:
print(set(result[0].toarray()[0].tolist()))

# We see that we could optimize by using integers here instead of floats by counting the occurence of every entry.
print(Counter(result[0].toarray()[0].tolist()))
(12, 1120)
[0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 2.005715251142432, 0.0, -2.005715251142432, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 2.005715251142432, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, -2.005715251142432, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, -2.005715251142432, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 2.005715251142432, -2.005715251142432, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, -2.005715251142432, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 2.005715251142432, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, -2.005715251142432, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 2.005715251142432, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, -2.005715251142432, 0.0, -2.005715251142432, 0.0, 0.0, 0.0, 0.0, 2.005715251142432, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 2.005715251142432, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 2.005715251142432, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, -2.005715251142432, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, -2.005715251142432, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 2.005715251142432, 0.0, 0.0, 0.0, -2.005715251142432, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, -2.005715251142432, 0.0, 0.0, 0.0, 0.0, -2.005715251142432, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 2.005715251142432, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, -2.005715251142432, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 2.005715251142432, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, -2.005715251142432, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, -2.005715251142432, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, -2.005715251142432, 0.0, 0.0, 0.0, 0.0, 0.0, -2.005715251142432, 0.0, 0.0, 0.0, 0.0, 0.0, -2.005715251142432, 2.005715251142432, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 2.005715251142432, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 2.005715251142432, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 2.005715251142432, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 2.005715251142432, 0.0, 0.0, 2.005715251142432, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, -2.005715251142432, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, -2.005715251142432, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 2.005715251142432, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, -2.005715251142432, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, -2.005715251142432, 0.0, 0.0, 2.005715251142432, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, -2.005715251142432, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 2.005715251142432, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 2.005715251142432, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 2.005715251142432, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, -2.005715251142432, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, -2.005715251142432, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, -2.005715251142432, 0.0, 2.005715251142432, 0.0, 0.0, 2.005715251142432, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0]

{0.0, 2.005715251142432, -2.005715251142432}
Counter({0.0: 1069, -2.005715251142432: 27, 2.005715251142432: 24})

Checking that the cosine similarity before and after word projection is kept

Note that this is a yet low-quality test, as the neural network layers above the projection are absent, so the similary is not yet semantic, it only looks at characters.

0.5 else "no") print("\t - similarity after :", cos_sim_after , "\t Are words similar?", "yes" if cos_sim_after > 0.5 else "no") print("")"> 
word_pairs_to_check_against_each_other = [
    # Similar:
    ["start", "started"],
    ["prioritize", "priority"],
    ["twitter", "tweet"],
    ["Great", "great"],
    # Dissimilar:
    ["boat", "cow"],
    ["orange", "chewbacca"],
    ["twitter", "coffee"],
    ["ab", "ae"],
]

before = pipeline.named_steps["char_term_frequency"].transform(word_pairs_to_check_against_each_other)
after = pipeline.named_steps["union"].transform(before)

for i, word_pair in enumerate(word_pairs_to_check_against_each_other):
    cos_sim_before = cosine_similarity(before[i][0], before[i][1])[0,0]
    cos_sim_after  = cosine_similarity( after[i][0],  after[i][1])[0,0]
    print("Word pair tested:", word_pair)
    print("\t - similarity before:", cos_sim_before, 
          "\t Are words similar?", "yes" if cos_sim_before > 0.5 else "no")
    print("\t - similarity after :", cos_sim_after , 
          "\t Are words similar?", "yes" if cos_sim_after  > 0.5 else "no")
    print("")
Word pair tested: ['start', 'started']
	 - similarity before: 0.8728715609439697 	 Are words similar? yes
	 - similarity after : 0.8542062410985866 	 Are words similar? yes

Word pair tested: ['prioritize', 'priority']
	 - similarity before: 0.8458888522202895 	 Are words similar? yes
	 - similarity after : 0.8495862181305898 	 Are words similar? yes

Word pair tested: ['twitter', 'tweet']
	 - similarity before: 0.5439282932204212 	 Are words similar? yes
	 - similarity after : 0.4826046482460216 	 Are words similar? no

Word pair tested: ['Great', 'great']
	 - similarity before: 0.8006407690254358 	 Are words similar? yes
	 - similarity after : 0.8175049752615363 	 Are words similar? yes

Word pair tested: ['boat', 'cow']
	 - similarity before: 0.1690308509457033 	 Are words similar? no
	 - similarity after : 0.10236537810666581 	 Are words similar? no

Word pair tested: ['orange', 'chewbacca']
	 - similarity before: 0.14907119849998599 	 Are words similar? no
	 - similarity after : 0.2019908169580899 	 Are words similar? no

Word pair tested: ['twitter', 'coffee']
	 - similarity before: 0.09513029883089882 	 Are words similar? no
	 - similarity after : 0.1016460166230715 	 Are words similar? no

Word pair tested: ['ab', 'ae']
	 - similarity before: 0.408248290463863 	 Are words similar? no
	 - similarity after : 0.42850530886130067 	 Are words similar? no

Next up

So we have created the sentence preprocessing pipeline and the sparse projection (random hashing) function. We now need a few feedforward layers on top of that.

Also, a few things could be optimized, such as using the power set of the possible n-gram values with a predefined character set instead of fitting it, and the Hashing's fit function could be avoided as well by passing the random seed earlier, because the Hasher doesn't even look at the data and it only needs to be created at some point. This would yield a truly embedding-free approach. Free to you to implement this. I wanted to have something that worked first, leaving optimization for later.

License

BSD 3-Clause License

Copyright (c) 2018, Guillaume Chevalier

All rights reserved.

Extra links

Connect with me

Liked this piece of code? Did it help you? Leave a star, fork and share the love!

You might also like...
This repository contains notebook implementations of the following Neural Process variants: Conditional Neural Processes (CNPs), Neural Processes (NPs), Attentive Neural Processes (ANPs).

The Neural Process Family This repository contains notebook implementations of the following Neural Process variants: Conditional Neural Processes (CN

DeepMind 892 Dec 28, 2022
S2-BNN: Bridging the Gap Between Self-Supervised Real and 1-bit Neural Networks via Guided Distribution Calibration (CVPR 2021)
S2-BNN: Bridging the Gap Between Self-Supervised Real and 1-bit Neural Networks via Guided Distribution Calibration (CVPR 2021)

S2-BNN (Self-supervised Binary Neural Networks Using Distillation Loss) This is the official pytorch implementation of our paper: "S2-BNN: Bridging th

Zhiqiang Shen 52 Dec 24, 2022
This is the paddle code for SeBoW(Self-Born wiring for neural trees), a kind of neural tree born form a large search space
This is the paddle code for SeBoW(Self-Born wiring for neural trees), a kind of neural tree born form a large search space

SeBoW: Self-Born Wiring for neural trees(PaddlePaddle version) This is the paddle code for SeBoW(Self-Born wiring for neural trees), a kind of neural

HollyLee 13 Dec 8, 2022
A framework that constructs deep neural networks, autoencoders, logistic regressors, and linear networks

A framework that constructs deep neural networks, autoencoders, logistic regressors, and linear networks without the use of any outside machine learning libraries - all from scratch.

Kordel K. France 2 Nov 14, 2022
Predictive AI layer for existing databases.
Predictive AI layer for existing databases.

MindsDB is an open-source AI layer for existing databases that allows you to effortlessly develop, train and deploy state-of-the-art machine learning

MindsDB Inc 12.2k Jan 3, 2023
Implementation of the Point Transformer layer, in Pytorch
Implementation of the Point Transformer layer, in Pytorch

Point Transformer - Pytorch Implementation of the Point Transformer self-attention layer, in Pytorch. The simple circuit above seemed to have allowed

Phil Wang 501 Jan 3, 2023
Predictive AI layer for existing databases.
Predictive AI layer for existing databases.

MindsDB is an open-source AI layer for existing databases that allows you to effortlessly develop, train and deploy state-of-the-art machine learning

MindsDB Inc 3.2k Feb 12, 2021
An abstraction layer for mathematical optimization solvers.
An abstraction layer for mathematical optimization solvers.

MathOptInterface Documentation Build Status Social An abstraction layer for mathematical optimization solvers. Replaces MathProgBase. Citing MathOptIn

JuMP-dev 284 Jan 4, 2023
Understanding and Improving Encoder Layer Fusion in Sequence-to-Sequence Learning (ICLR 2021)

Understanding and Improving Encoder Layer Fusion in Sequence-to-Sequence Learning (ICLR 2021) Citation Please cite as: @inproceedings{liu2020understan

Sunbow Liu 22 Nov 25, 2022
Comments
  • Implementation details

    Implementation details

    Hi Guillaume,

    I'm also pretty exciting of this paper and approached suggested. I've went through your implementation as well as your questions on Stackoverflow: https://stackoverflow.com/questions/53876974/how-is-hashing-implemented-in-sgnn-self-governing-neural-networks

    Sorry, I don't have enough points to comment your Stackoverflow question and I don't have right answers, I just want to discuss it.

    1. ... on words' characters to obtain a featurized representation of words in a text ...

    For me it seems like they used the whole text on character-lvl, not word-lvl. So for each example it is one vector of features that then is passed to projections. Although, you implementation is quite interesting as well because it still allows to use RNN/CNNs and keeps skip/ngrams ordering.

    1. ... it doesn't seem to yield a binary output ...

    If I understand correctly paper, binary output comes from sign of dot product of feature (F) vector and generated projection (P) vector of feature in F. Assuming, that both vectors are normalized (unit length and they pointed that LSH produces unit vectors), dot product would be in range of {-1, 1} (cosine similarity) and sign of it would give us binary output.

    What do you think about it? Does my understanding make sense?

    I'm still not quite sure how those P vectors are obtained via LSH though.

    opened by thinline72 15
  • speech act classifier?

    speech act classifier?

    Thanks for your work Guillaume. Did you implement the speech act classifier as in the SGNN paper? If you did, I wonder what scores did you get, as I am trying to do it myself and I am inspired by your implementation.

    opened by glicerico 1
  • Use only 1 hasher

    Use only 1 hasher

    Instead of using a FeatureUnion over T=80 random hashers of d=14 dimensions (80*14=1120 word features), use only one hasher (1x1120), which results in a dramatic speedup.

    You can see the fix here: https://github.com/guillaume-chevalier/NLP-TP3

    opened by guillaume-chevalier 5
Owner
Guillaume Chevalier
e^(πi) + 1 = 0
Guillaume Chevalier
GitHub https://github.com/guillaume-chevalier/NLP-TP3
Curved Projection Reformation

Description Assuming that we already know the image of the centerline, we want the lumen to be displayed on a plane, which requires curved projection

夜听残荷 5 Sep 11, 2022
ImVoxelNet: Image to Voxels Projection for Monocular and Multi-View General-Purpose 3D Object Detection

ImVoxelNet: Image to Voxels Projection for Monocular and Multi-View General-Purpose 3D Object Detection This repository contains implementation of the

Visual Understanding Lab @ Samsung AI Center Moscow 190 Dec 30, 2022
Hierarchical Uniform Manifold Approximation and Projection

HUMAP Hierarchical Manifold Approximation and Projection (HUMAP) is a technique based on UMAP for hierarchical non-linear dimensionality reduction. HU

Wilson Estécio Marcílio Júnior 160 Jan 6, 2023
Implementation of "Bidirectional Projection Network for Cross Dimension Scene Understanding" CVPR 2021 (Oral)

Bidirectional Projection Network for Cross Dimension Scene Understanding CVPR 2021 (Oral) [ Project Webpage ] [ arXiv ] [ Video ] Existing segmentatio

Hu Wenbo 135 Dec 26, 2022
my graduation project is about live human face augmentation by projection mapping by using CNN

Live-human-face-expression-augmentation-by-projection my graduation project is about live human face augmentation by projection mapping by using CNN o

null 1 Mar 8, 2022
Using NumPy to solve the equations of fluid mechanics together with Finite Differences, explicit time stepping and Chorin's Projection methods

Computational Fluid Dynamics in Python Using NumPy to solve the equations of fluid mechanics ?? ?? ?? together with Finite Differences, explicit time

Felix Köhler 4 Nov 12, 2022
Implementation of the 😇 Attention layer from the paper, Scaling Local Self-Attention For Parameter Efficient Visual Backbones

HaloNet - Pytorch Implementation of the Attention layer from the paper, Scaling Local Self-Attention For Parameter Efficient Visual Backbones. This re

Phil Wang 189 Nov 22, 2022
In this project we use both Resnet and Self-attention layer for cat, dog and flower classification.

cdf_att_classification classes = {0: 'cat', 1: 'dog', 2: 'flower'} In this project we use both Resnet and Self-attention layer for cdf-Classification.

null 3 Nov 23, 2022
A PyTorch implementation of Radio Transformer Networks from the paper "An Introduction to Deep Learning for the Physical Layer".

An Introduction to Deep Learning for the Physical Layer An usable PyTorch implementation of the noisy autoencoder infrastructure in the paper "An Intr

Gram.AI 120 Nov 21, 2022
Complex-Valued Neural Networks (CVNN)Complex-Valued Neural Networks (CVNN)

Complex-Valued Neural Networks (CVNN) Done by @NEGU93 - J. Agustin Barrachina Using this library, the only difference with a Tensorflow code is that y

youceF 1 Nov 12, 2021