Scribd
Upload
7 views1 page

AI&NLP

Uploaded by

Remya Anish
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
7 views1 page

AI&NLP

Uploaded by

Remya Anish
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 1

Syllabus-INTRODUCTION TO AI AND NLP

Module 1-INTRODUCTION TO ARTIFICIAL INTELLIGENCE:


Artificial Intelligence? History, AI on a conceptual level, Types of AI, Use Cases, importance and applications of AI, AI
algorithms, types of machine learning, types of problems solved in AI, advantages, and disadvantages of AI, AI In
Marketing, Banking, Finance, Agriculture, HealthCare, Gaming, Space Exploration., Autonomous Vehicles, Chatbots,
Artificial Creativity, AI Tools & Frameworks, AI vs Machine Learning vs Deep Learning, an overview of python for AI,
INTRODUCTION TO NLP: NLP in the Real World, NLP Tasks, Language? Its Building Blocks, Why Is NLP
Challenging? Machine Learning, Deep Learning, and NLP: An Overview, Approaches to NLP, Heuristics-Based NLP,
Machine Learning & Deep Learning for NLP, NLP Pipeline, Applications of NLP-Machine translation, Speech
recognition, Image Captioning, spam detection, text prediction- Introduction to Software Packages-Spacy, NLTK,
Gensim, PyTorch, Regular Expression-importance, properties, working and python package (re), case study: working of
Eliza chatbot.

Module 2- REGULAR EXPRESSION & TEXT PROCESSING:


Common regex function, Meta Characters- Big brackets, cap, Backslash, Squared Brackets, Special Sequences, Asterisk,
Plus, And Question mark, Curly Brackets Understanding Pattern Objects- Match Method Vs Search Method, Finditer
Method, Logical Or, Beginning And End Patterns, Parenthesis String Modification- split method, submethod, subn
method, Text Processing-Words, Tokens, Counting words, vocabulary, corpus, tokenization in spacy- Sentiment
Classification- (yelp) download a review dataset use data preparation using NumPy, pandas, counter, readd tokens to
vocabulary, build vocabulary from a data frame, from corpus, one hot encoding, encoding documents, train test splits,
feature computation, confusion matrix, analysis. Language Independent Tokenization: Types of tokenization — Word,
Character, and sub-word tokenization, problems with word tokenizer, drawbacks of a character-based tokenizer, problems
with sub-word tokenization, Byte Pair Encoding,String Matching and Spelling Correction-Minimum edit distance-
table filling, dynamic programming,

Module 3-WORD EMBEDDING & PROBABILISTIC MODELS:


Vector Models & Text Pre-processing: Vectors, Bag of Words, Count Vectorizer, Tokenization, Stopwords, Stemming,
and Lemmatization, Stemming, and Lemmatization, Count Vectorizer, Vector Similarity. TF-IDF, Word-to-Index
Mapping, Building TF-IDF, Neural Word Embeddings, Neural Word Embeddings. Vector Models Text Preprocessing
Summary, steps of NLP analysis, Probabilistic Models-Language Modelling: importance, types of language modeling,
the curse of dimensionality, Language Model Markov Assumption And N-Grams, Language Model Implementation –
Setup, Ngrams Function, Update Counts Function, Probability Model Function, Reading Corpus, Language Model
Implementation Sampling Text, Markov Models: Markov Property, Markov Model, Probability Smoothing and Log-
Probabilities, Building a Text Classifier, Article Spinning – Problem, N-Gram Approach, implementation, Cipher
Decryption with Language Modeling And Genetic Algorithm Ciphers, substitution cipher, bigrams, maximum
likelihood, and log-likelihood, Language models, Genetic Algorithms

Module 4- NLP USING MACHINE LEARNING MODELS


Spam Detection– Problem, Naive Bayes theorem, Intuition, spam detection using Naïve Bayes, class imbalance, ROC,
AUC, AND F1 SCORE, Implementing spam detection in python, Sentiment Analysis -Problem, Logistic Regression
Intuition, Multiclass Logistic Regression, Logistic Regression Training and Interpretation, sentiment analysis
implementation in python, Text Summarization-Using Vectors, Text Rank Intuition,Text Rank in Python, Text
Summarization in Python Topic Modeling-different topic modeling techniques, Latent Dirichlet Allocation (LDA) –
Essentials, Latent Dirichlet Allocation–Topic Modeling with Latent Dirichlet, Latent Symmatc Modelling(Indexing)-
LSA / LSI Introduction, Singular Value Decomposition Intuition, LSA / LSI: Applying SVD to NLP, Latent Semantic
Analysis / Latent Semantic Indexing in Python

Module 5- DEEP LEARNING


word embeddings, nonlinear neural networks, Neuron – Intro, Fitting a Line, Classification Code Preparation, Text
Classification in Tensorflow, The Neuron, How does a model learn?, Feed Forward Neural Networks- Ann-
introduction, The Geometrical Picture, Activation Functions, Multiclass Classification, Text Classification ANN in
Tensorflow, Text Preprocessing Code Preparation, Text Preprocessing in Tensorflow, Embeddings, CBOW(continuous
bag of words), CBOW in Tensorflow, Convolution Neural Networks- Convolution, pattern matching, weight sharing,
convolution in color images, CNN Architecture, CNN for Text, CNN for NLP in Tensorflow, Recurrent Neural
Networks- Simple RNN / Elman Unit, RNNs: Paying Attention to Shapes, GRU, and LSTM. RNN for Text
Classification in TensorFlow, Parts-of-Speech Tagging, and Named Entity Recognition in TensorFlow

You might also like