You are on page 1of 4

AI - (Deep Learning/NLP)

OVERVIEW

The course aims to train engineers to become data scientist. It will contain lots of Practical, Theory and many end-
to-end Artificial Intelligence implementation.

PREREQUISITE
The participants are preferred to have some overview of Python language, ML basics and Applied Statistics.

DURATION
5 days

PROGRAM COROLLARY

An experienced instructor will share relevant theoretical and hands-on knowledge on developing Deep Learning and
NLP Models.

COURSE OUTLINE

<Day 1>

 Artificial Intelligence Introduction and Environment Setup

o Basics of AI, Deep Learning and NLP.


o Setting up Deep Learning Tensorflow Environment

 Introduction to Tensorflow and Keras

o Multi Layer Perceptron Model


o The Programming Model
o Tensor Board
o Introducing Feed Forward Neural Nets
o Softmax Classifier
o ReLU Classifier
o Dropout Optimization
o Deep Learning Applications
o Keras Overview
o Keras Deep Learning APIs

 Artificial Neural Network Modeling and Tuning

o Multi Layer Perceptron Model


o Cost Function Formation
o Back propagation and Gradient Descent Algorithm
o Industry Use Case using ANN Model
<Day 2>

 Convolutional Neural Networks


o CNN Architecture
o Convolution Function
o Pooling and Flattening
o Computer Vision
o Image Acquisition and manipulation
o Edge Detection, Corner Detection
o Image Scaling
o Use Case - Building a Convolution Neural Network for Image Classification.

 Recurrent Neural Networks


o RNN Architecture
o LSTM Networks
o The Vanishing Gradient Problem
o RNN Model Use Case

<Day 3>

 RBM(Restricted Boltzmann Machine) and Autoencoders


o RBM Concept
o Collaborative Filtering with RBM
o RBM Model Use Case
 Keras API for Deep Learning
o Keras Introduction for easy implementation of Deep learning Models
o Keras based Modeling steps
o TensorBoard with Keras
o Functional Composition
o Model Training Process using Keras
o CNN Use Case Implementation with Keras

<Day 4>

 Natural Language Programming ( NLP) Overview


o NLP Introduction
o NLP role in AI and related use cases overview
o NLP Packages NLTK, Spacy, Gensim etc.

 NLP Text Preprocessing and Cleaning


o Steps required to clean the text data
o Text Pre-processing and cleaning
o Tokenization
o Replacing and correcting words (Stemming and Lemmatization)
o Noise Entity Removal
o Removing Stop Words and Punctuations

 Text Feature Engineering


o Different steps of text feature engineering
o Syntactical Feature Analysis
o Part of Speech Tagging
o Semantic Analysis
o Statistical features (TF-IDF)
o word vector Analysis

<Day 5>

 Topic Modeling and Named Entity Recognition


o Entity Parsing
o Topic Modeling
o NER (Named Entity Recognition)
o NGram
o Phrase Detection

 Text Classification Use Case


o End-to-End implementation of Text Classification Use Case using NLP modeling in Python
o Text Preprocessing, Feature Engineering and NLP Model building and performance evaluation

 Text Similarity Use Case


o End-to-End implementation of Text Similarity Use Case using NLP modeling in Python

 Sentiment Analysis Use Case


o Sentiment Analysis Use Case Implementation

You might also like