shashankg7

import numpy as np
import theano
from theano import tensor as T


rng = np.random


class Autoencoder(object):
    def __init__(self, maxnum, reduced_dims, learnrate=0.4):

shashankg7

- character2vec http://arxiv.org/pdf/1508.02096v2.pdf
- word2vec https://arxiv.org/abs/1310.4546
- sentenc2vec, paragraph2vec, doc2vec https://cs.stanford.edu/~quocle/paragraph_vector.pdf
- tweet2vec http://arxiv.org/abs/1605.03481
- tweet2vec http://socialmachines.media.mit.edu/wp-content/uploads/sites/27/2016/05/tweet2vec_vvr.pdf
- author2vec http://dl.acm.org/citation.cfm?id=2889382
- item2vec http://arxiv.org/abs/1603.04259
- lda2vec https://arxiv.org/abs/1605.02019
- illustration2vec http://dl.acm.org/citation.cfm?id=2820907
- tag2vec http://ktsaurabh.weebly.com/uploads/3/1/7/8/31783965/distributed_representations_for_content-based_and_personalized_tag_recommendation.pdf

shashankg7

"""Information Retrieval metrics

Useful Resources:
http://www.cs.utexas.edu/~mooney/ir-course/slides/Evaluation.ppt
http://www.nii.ac.jp/TechReports/05-014E.pdf
http://www.stanford.edu/class/cs276/handouts/EvaluationNew-handout-6-per.pdf
http://hal.archives-ouvertes.fr/docs/00/72/67/60/PDF/07-busa-fekete.pdf
Learning to Rank for Information Retrieval (Tie-Yan Liu)
"""
import numpy as np

shashankg7

from keras.models import Graph
from keras.layers import containers
from keras.layers.core import Dense, Dropout, Activation, Reshape, Flatten
from keras.layers.embeddings import Embedding
from keras.layers.convolutional import Convolution2D, MaxPooling2D

def ngram_cnn(n_vocab, max_length, embedding_size, ngram_filters=[2, 3, 4, 5], n_feature_maps=100, dropout=0.5, n_hidden=15):
    """A single-layer convolutional network using different n-gram filters.

    Parameters

shashankg7

"""
preprocess-twitter.py

python preprocess-twitter.py "Some random text with #hashtags, @mentions and http://t.co/kdjfkdjf (links). :)"

Script for preprocessing tweets by Romain Paulus
with small modifications by Jeffrey Pennington
with translation to Python by Motoki Wu

Translation of Ruby script to create features for GloVe vectors for Twitter data.

shashankg7

These links no longer work. Springer have pulled the free plug.

Graduate texts in mathematics

duplicates = multiple editions

A Classical Introduction to Modern Number Theory, Kenneth Ireland Michael Rosen

A Classical Introduction to Modern Number Theory, Kenneth Ireland Michael Rosen

shashankg7

"""
Code to parse sklearn classification_report
"""
##
import sys
import collections
##
def parse_classification_report(clfreport):
    """
    Parse a sklearn classification report into a dict keyed by class name

shashankg7

import numpy as np

def symdirichlet(alpha, n):
    v = np.zeros(n)+alpha
    return np.random.dirichlet(v)


def exp_digamma(x):
    if x < 0.1:
        return x/100

shashankg7

Extentions of Topic Models

There are a lot of Topic Models. 18/02/23 # of TM is 24

A

• ATM(author topic model)
  • The Author-Topic Model for Authors and Documents (UAI'04)

shashankg7

#!/bin/bash
#
# script to extract ImageNet dataset
# ILSVRC2012_img_train.tar (about 138 GB)
# ILSVRC2012_img_val.tar (about 6.3 GB)
# make sure ILSVRC2012_img_train.tar & ILSVRC2012_img_val.tar in your current directory
#
#  https://github.com/facebook/fb.resnet.torch/blob/master/INSTALL.md
# 
#  train/