Skip to content
sreejukomath edited this page Sep 18, 2019 · 13 revisions

Topics

NLTK

Genism

Spacy

pyLDAvis

MatplotLib

Keras

Tokenization

Frequency of tokens

UniGram

BiGram

Trigram

NGram

Stemmer

Lemaitazation

POS tagging

Name entity recognition

RegEx Matcher

bag-of-words

LSI Modeling

HDP Modeling

LDA Modeling

GaussianNB

SVM

TF-IDF

SVD

Normalizer

CoherenceModel

Bar Graph

LSTM

BiLSTM

Dense

Dropout

Input Layer

Hidden Layers

Output Layers

Loss function : categorical_crossentropy, softmax_cross_entropy_with_logits_v2

Optimizer: adam, RMSPropOptimizer

activation : softmax

Epoch

Batch size

weights

Bias

Iteration

Learning rate

Accuracy : tf.reduce_mean

Striding

Padding

Max Pooling

Back Propagation

Saving model

Loading a model

Sequential model

SGD Classifier

Logistic Regression

SVC Classifier

MultinomialNB

BernoulliNB

NaiveBayes Classifier

Random forest classifier

Linear Regression

Evaluation Matrix

Confusion Matrix: True Positive, True Negative, False Positive, False Negative

Precision / Recall

ROC(Receiver Operator Characteristic graph) / AUC (Area Under the Curve graph)

Word Embedding

OneHot vector

word2vec

doc2vec

para2vec

char2Vec

CBOW

skip gram

Sentiment Analysis

Predicting topics in a text

Predicting next word in sentence

Speaker identification

Chatbot

Clone this wiki locally