NATURAL LANGUAGE PROCESSING

PROFESSIONAL PROGRAM

1) Learning Methodology
• Instructor-Led Classroom Training (ILT).

2) Prerequisites:
• Basic skills with at least one programming language are desirable

3) Training Program Description:

• In this program, you’ll learn and put in practice the concepts behind natural
language processing and speech recognition, including machine translation, part
of speech tagging, and sentiment analysis. This program will cover the latest in
deep learning architectures, which, combined with the more classical probabilistic
methods used in a variety of applications, will give you a repertory of techniques
widely used in the industry. With the practical skills you gain in this program,
you’ll be able to build your own models which will extract information from text or
voice data, and enable you to solve real-world challenges.

• This program will enhance your existing machine learning and deep learning
skills with the addition of natural language processing and speech recognition
techniques. These skills can be used in various applications such as part of
speech tagging and machine translation, among others. You’ll develop the skills
you need to start applying natural language processing techniques to real-world
challenges and applications.

• Length of Program : 200 Hrs.

1
4) Projects

This program is comprised of many career-oriented projects. Each project you build will
be an opportunity to demonstrate what you’ve learned in the lessons. Your completed
projects will become part of a career portfolio that will demonstrate to potential
employers that you have skills in data analysis and feature engineering, machine
learning algorithms, and training and evaluating models.

One of our main goals at ETI is to help you create a job-ready portfolio of completed
projects. Building a project is one of the best ways to test the skills you’ve acquired and
to demonstrate your newfound abilities to future employers or colleagues. Throughout
this program, you’ll have the opportunity to prove your skills by building the following
projects

Building a project is one of the best ways both to test the skills you've acquired and to
demonstrate your newfound abilities to future employers. Throughout this program,
you'll have the opportunity to prove your skills by building the following projects:

o Project 1: Exploring the Titanic Survival Data

o Project 2: Predicting Housing Prices
o Project 3: Finding Donors for Charity
o Project 4: Creating Customer Segments Deep learning
o project 5: Dog Breed Recognition
o Project 6: Teach a Quad copter to Fly
o Project 7: Your First Neural Network
o Project 8: Generate Faces
o Project 9: Part of Speech Tagging
o Project 10: Machine Translation
o Project 11: Speech to Text

Capstone projects in many fields:

1- Self-driving cars
2- Business
3- Trading
4- Computer vision

2
5) Training Program Curriculum:

I- Python 3 Topics

• Introduction
o syntax
o data types and operations
o I/O
o Operators and bitwise
o Lists
o Tuples
o If statements
o For – while loops
• Object-Oriented Programming (OOP)
o Special Functions
o Strings
o Classes
o Inheritance
o Regular expressions
o Working with files
o Python generators
o Python Decorators
o Exceptions
o Regular expressions
o Multithreading and multiprocessing Sockets and APIs
• Introduction to Gui
o Gui grid
o Gui events
o Gui styles
• Intro to data science

3
 o Database with SQLite
o Numpy and matrix operations
o Pandas
o Matplotlib
o Building your own server
o Data visualization
o Git command line and GUI based
o Web Scraping for data collecting

II- Machine Learning Topics

• Linear algebra
• Calculus
• Statistics
• Introduction to ML and Business cases
o The difference between ML, Big data, Data analysis and
Deep Learning
o Linear Algebra and Statistics for ML
o Data preprocessing

• Data preprocessing
o Importing libraries
o Data acquisition
o Data cleaning
o Handling missing data
o Categorical data
o Data splitting
o Feature scaling
• Regression problem

4
 o Linear Regression
o Multi-linear regression
o Polynomial regression
o K-nearest neighbour regression
o Decision tree regression
o Regression Evaluation Metrics
• Classification problem
o Logistic Regression
o Naive Bayes
o K-nearest neighbour classifier
o Support vector machine (SVM)
o Decision tree classifier
o Ensemble learning
o Classification Evaluation Metrics
• Clustering Problems
o Dimensionality reduction
o K-means
o DBSCAN
o hierarchical clustering
o Association Rules

• Reinforcement learning
o Upper confidence bond
o Thompson sampling
• Model Selection and evaluation
o Loss functions
o Gradient descent
o Bias-variance tradeoff
o Cross-validation

5
 o Hyperparameter tuning
• Result communication and report

III- Data Structures & Algorithms Topics

• Introduction
o How to Solve Problems
o Big O Notation
• Data Structures
o Collection data structures (lists, arrays, linked lists, queues,
stack)
o Recursion
o Trees
o Maps and Hashing
• Basic Algorithms
o Binary Search
o Sorting Algorithms
o Divide & Conquer Algorithms
o Maps and Hashing
o Practice Problems: Randomized Binary Search, K-smallest
elements using Heaps, Build Red-Black Tree, bubble sort,
merge sort, quick sort, sorting strings, Linear-time median
finding
• Advanced Algorithms
o Greedy Algorithms
o Graph Algorithms
o Dynamic Programming
o Linear Programming

6
 o Practice Problems: Graph Traversals, Diijkstra's Algorithm,
Shortest Hops, A* Search, Longest Palindromic
subsequence, web crawler

IV- Deep Learning Topics

• Neural Networks
o INTRODUCTION TO NEURAL NETWORKS
o IMPLEMENTING GRADIENT DESCENT
o TRAINING NEURAL NETWORKS
o SENTIMENT ANALYSIS
o DEEP LEARNING WITH PYTORCH

• Convolutional Neural Networks

o INVARIANCE, STABILITY
o CLOUD COMPUTING
o CONVOLUTIONAL NEURAL NETWORK
o CNNS IN PYTORCH
o PROPERTIES OF CNN REPRESENTATIONS: INVERTIBILITY,
STABILITY, INVARIANCE.
o WEIGHT INITIALIZATION
o AUTOENCODERS
o VARIATIONAL AUTOENCODERS
o TRANSFER LEARNING IN PYTORCH
o DEEP LEARNING FOR CANCER DETECTION
o VARIABILITY MODELS (DEFORMATION MODEL, STOCHASTIC
MODEL).
o SCATTERING NETWORKS
o GROUP FORMALISM
o SUPERVISED LEARNING: CLASSIFICATION.

7
 o COVARIANCE/INVARIANCE: CAPSULES AND RELATED
MODELS.
o CONNECTIONS WITH OTHER MODELS: DICTIONARY
LEARNING, LISTA.
o OTHER TASKS: LOCALIZATION, REGRESSION.
o EMBEDDINGS (DRLIM), INVERSE PROBLEMS
o EXTENSIONS TO NON-EUCLIDEAN DOMAINS
o DYNAMICAL SYSTEMS: RNNS.

• Recurrent Neural Networks

o RECURRENT NEURAL NETWORKS
o LONG SHORT-TERM MEMORY NETWORK
o IMPLEMENTATION OF RNN & LSTM
o HYPERPARAMETERS
o EMBEDDINGS & WORD2VEC
o SENTIMENT PREDICTION RNN

• Generative Adversarial Networks

o GENERATIVE ADVERSARIAL NETWORK
o MAXIMUM ENTROPY DISTRIBUTIONS
o DEEP CONVOLUTIONAL GANs
o PIX2PIX & CYCLEGAN

• Model Deployment
o INTRODUCTION TO DEPLOYMENT
o DEPLOY A MODEL
o CUSTOM MODELS & WEBHOSTING
o MODEL MONITORING
o UPDATING A MODEL

8
 • MISCELLANEOUS TOPICS
o NON-CONVEX OPTIMIZATION FOR DEEP NETWORKS
o STOCHASTIC OPTIMIZATION
o ATTENTION AND MEMORY MODELS
o OPEN PROBLEMS

V- Natural Language Processing Topics

• Introduction to Natural Language Processing

o INTRO TO NLP
o TEXT PROCESSING
o PART OF SPEECH TAGGING WITH HIDDEN MARKOV
MODELS

• Computing with Natural Language

o FEATURE EXTRACTION AND EMBEDDINGS
o MODELING
o DEEP LEARNING ATTENTION
o INFORMATION SYSTEMS

• Communicating with Natural Language

o INTRO TO VOICE USER INTERFACES
o ALEXA HISTORY SKILL
o INTRODUCTION TO SPEECH RECOGNITION

9
FOR MORE INFORMATION:
To get more details
regarding special discount for
Website: https://epsiloneg.com groups.
E-mail: info@epsiloneg.com
Mobile: +2 01122885566 / +2 01011933233 / +20 2 22749985
Address: Elserag Shopping Mall, Residential Building 1,
Entrance 1, Floor 11 Makram Ebeid, Nasr City, cairo, Egypt

10
CERTIFICATE
• Participants will be granted a completion certificate from Epsilon Training
Institute, Delaware, USA if they attend a minimum of 80 percent of the direct
contact hours of the Program and after fulfilling program requirements (passing
both Final Exam and Project to obtain the Certificate)

REGISTRATION PROCEDURES
• Confirmation of registration is based on receipt of a Purchase Order or
Registration Form.
• Training Program registrations will not be confirmed until registration is complete
and billing information is received in full

PAYMENT TERMS AND METHODS

• Payment must be made prior to course commencement at Epsilon Training
Center, Nasr City HQ

• In-Person
o In Cash to our address: Elserag shopping mall,
Residential Building 1, Entrance 1, Floor 11
o By cheque - Payable to: Epsilon Training center

• Bank transfer to our ACC in:

QNB ALAHLI Acc /20318280579-69 EGP Branch code / 00078

• Vodafone Cash to 01011933233

11
REFUND
• Any cancellation must be done three (3) weeks prior to course commencement in
order to receive a full refund of paid registration fees
• A 50% Cancellation Fees will be imposed for any course cancellation received
within two (2) weeks or on the date of course commencement.
o Refund Prior 3 weeks of the training program start date, 100% Refund
o Refund Prior 2 weeks of the training program start date, 50% Refund of
training program fees
o Refund Prior 1 week of the training program start date, No Refund
• Any refund request should be requested by a documented email or in writing.

RECAP
• Recap is available for only 1 session with the available dates
• If you need to recap a session you attended already it will be paid for 200 LE per
session with the available dates

POSTPONING
• Postponing only could be before the start of the training program with minimum
10 days

12