Your Access to a bright

future

ARTIFICIAL INTELLIGENCE

ARTIFICIAL
INTELLIGENCE &
MACHINE LEARNING
PROGRAM

www.techaccess.co.in
 TECH ACCESS
LEARNING PVT LIMITED

|| ESSENTIAL OF ARTIFICIAL INNTELLIGENCE

• Introduction to python: Built foundation for • Data Analysis using SQL (OPTIONAL): Data in
the most in demand programming language companies is definitely not stored in excel
• Python for data science: Learn how to sheets learn the fundamentals of database
manipulate dataset in python using pandas, and extract information from RDBMS using
which is the most powerful for data the structured query language.
preparation and analysis • Data analysis in Excel: Thought by one of the
• Data Visualization in python: Humans are most renowned data scientists in the country
visual learns and hence no task related to data this module takes you from a beginner level
is complete without visualization learn to plot Excel user to an almost professional user.
and interpret various graph in python and • Analytics problem solving: This module
observe how they make data analysis and covers
drawing insights easier concepts of the framework for business
problem solving

|| STATISTICS AND EXPLORATORY DATA ANALYTICS

• Exploratory data analysis: learn how to find • Hypothesis testing: understand how to
and analysis the patterns in the data draw formulate and validate hypothesis for a
actionable insights. population to solve real life business.
• Inferential statistics :Understand how to • Lending club case study: Determine which
formulate and learn how to infer insights from customers are at risk default and what are
a huge population using a small sample their characteristics so as to avoid providing
loans to similar people in future
|| MACHINE LEARNING

• What is Machine learning: machine learning, • Naïve bayes: Understand the basic building
function Approximation ,Approaches for blocks of Naiave Bayes and learn how to build
prediction an SMS spam Ham Classifier using Naïve Bayes
technique.
• Linear regression : Build a model to
understand the factors car prices vary on the • Model Selection: Learn the pros and cons of
help a Chinese company enter the US car simple and complex model and the different
market methods for quantifying model complexity,
along with regularization and cross validation
• Logistic Regression: Learn your first binary
classification technique by determining • Support Vector Machine (Optional): Learn how
whether customers of a telecom operator are find a maximal marginal classifier using SVM
likely to churn to help the business retain and use them to delete spam emails recognize
customers. alphabets and more!
• Support Vector Machine : classification, • Classification: Case study, Logistic regression,
maximal margin classifier linear discriminates analysis.
• Boosting: Learn how weak learners can be • Decision Tree :Decision trees, Regression tree
‘boosted’ with the help of each other and classification tree ,Ensemble methods
become strong learns using different boosting
algorithms
 TECH ACCESS
LEARNING PVT LIMITED
|| MACHINE LEARNING

• Unsupervised Learning :Clustering Learn how

• Unsupervised learning: principal component
to group elements into different when you
analysis Understand important concepts
don’t have any pre-defined labels to segregate
related to dimensional reduction, the basic
them K-means clustering, hierarchical
idea and the learning algorithm of PCA, and
clustering, and more
its practical application on supervised and
unsupervised problems.

|| ARTIFICIAL INTELLIGENCE

• Introduction to Artificial Intelligence • History of machine learning

• What is artificial • Machine learning and statistics
• Artificial and natural intelligence • Artificial intelligence and machine learning
• AI Problems • Type of machine learning algorithms
• History of AI • Training machine learning system

|| DEEP LEARNING

 Introduction to TensorFlow  Implement Neural Network

• What are tensors • What is Neural Network
• Vector Data • Evaluate Deep Learning Models
• Timeseries and sequence data • Data preprocessing for neural networks
• Image and video data • Addressing Overfitting
• TensorFlow Estimator Benefits • Universal Workflow for Deep Learning
• Canned Estimators
 Convolutional Neural Network (CNN)
• Input Functions
• CNN Model
• Feature Columns
• Data Preprocessing
• Data Pipeline
• Autoencoders
 Neural Networks • Convolution Operation
• Deep Learning Introduction • ReLU layer
• Neuron and Perceptron • Pooling
• Artificial Neural Architecture(ANN) • Flattening
• Linear Perceptron • Full Connection
• Feed forward Neural Network • SoftMax & Cross-Entropy
• Activation Functions
 Recurrent Neural Network (RNN)
• Loss Functions
• Introduction
• Information Theory
• Text Generation
• Gradient Descent
• Long-Short Term Memory
• Backpropagation
• Time Series Forecasting
• Approaches to Gradient Descent
• Gated Recurrent Unit
• Gradient and saddle point
• Bidirectional RNN
• Optimizers
• Generating Images using GANs
 Introduction to Keras • Build data Pipeline
• Program • Plot the results
• MNIST dataset
 TECH ACCESS
|| Natural Language Processing LEARNING PVT LIMITED

• Introduction to NLP • Syntactic Processing: Learn the most interesting

• Lexical processing: Do you get annoyed by area in the field of NLP and understand different
the constant spams in your mail box/ techniques like word-embeddings, topic
Wouldn’t it be nice if we had program to modeling to build an application that extract
check your spellings? In this module learn opinion about socially relevant issues.
how to build a spell checker and spam • Case Study: Classifying customer complaint
detector using techniques like phonetic tickets in this case study you will create a
hashing, bag-of-words,TF-IDF, etc solution that will help in identifying the type of
complaints ticket raised by the customers if a
• Syntactical Processing: Learn how to multinational bank
analyze the syntax or the grammatical
structure of sentences using POS tagging
and Dependency parsing.

|| WORKING WITH OPEN CV

• Perform video operation using opencv
• Introduction opencv
• Image capture through webcam using opencv
• Installation opencv library
• Set resolution of webcam using opencv
• Loading and displaying images
• Live video processing using opencv
• Splitting and merging channels of images
• Live video recording using opencv
• Mat plot and color map
• Tracking faces
• Plotting image using matplotlib
• Face detection
• Blending and transitioning images
• Arithmetic operation on image

|| Advance Python for AI/ML

 Essential libraries  Introduction to statistics

• Anaconda • Statistics in real life
• Jupiter notebook • Variability in data
• Python language semantics • Uncertainty in data
• Duck typing • Observed variables
• Mutable and immutable objects • Casual association
• Scalar types • Lurking variables
• Type casting • Confounded variables
• Ternary expressions • Reasons for association
• Functions • Randomization
 TECH ACCESS
|| DATA STRUCTURE USING PYTHON LEARNING PVT LIMITED

• Introduction of data structure • Traversal a stack

• Implementation of stack using list • Implementation of queue as list
• Creating a stack • Create a queue using list
• Adding to a stack • Checking for empty queue
• Checking for empty stack • Inserting an element in a queue
• Pop operation • Traversal queue item
• Traversal a stack

|| ARRAY CONCEPT USING PYTHON

• Introduction of array using python • Search value and index of array

• How import array package • Update value from array
• Working on array method • Delete value from array
• Insert element in array • Sorting value of array
• Traverse value from array

|| GUI PROGRAMMING (TKINTER)

• Introduction of GUI using tkinter • Geometry Management

• How import tinker package • Difference between grid(),pack(),place() method
• Tkinter widgets (Button,Entry,Label) • Configure structure of windows
• Text,Frame, • Create menu and submenu using configuration
• Checkbutton,Radiobutton • Open dialog box using menu widgets
• OptionMenu,listbox,Spinbox
• Standard attribute

|| MY SQL DATABASE ACCESS

• Introduction of database • Categories of SQL(DDL,DML,DQL,TCL)

• What is database • Standard command and constrain command
• Advantage of database • Standard Join command
• What is SQL(Structure Query Language)

|| DATABASE CONNECTIVITY USING PYTHON

• Introduction of connectivity • Update operation

• Installation library pymysql • Delete operation
• Standard Connection method connect, • Commit operation
• Cursors, execute, rollback, close • Rollback operation
• Create database and establish connection • Search record from table
• Create database table • Disconnect Database
• Insert operation
• Read operation
 TECH ACCESS
LEARNING PVT LIMITED

|| INTRODUTION TO DATA ANALYTICS USING PYTHON

• What is analytics ? • Overview of analytics tools & their popularity
• Common Terms in Analytics • Analytics Methodology &problem solving
• Analytics vs. Data warehousing framework
• Relevance in industry and need of the hour • List of steps in Analytics projects
• Types of problems and business objectives • Identify the most appropriate solution design for
• How leading companies are harnessing the the given problem statement
power of analytics? • Why Python for data science?

|| DISTRIBUTIONS USED IN PYTHON FOR DATA ANALYTICS

• Numpy, scify, pandas, scikitlearn,nltk etc

• Pandas, Matplotlib, etc)
• Concept of Packages/Libraries – Important
• Installing & loading Packages & Name Spaces
• packages(NumPy, SciPy, scikit-learn)

|| IMPORTING AND EXPORTING DATA USING PYTHON

• Importing Data from various sources

• Exporting Data to various formats
• Csv, excel,txt
• Important python modules: Pandas
• Database Input (Connecting to database)
• Viewing Data objects - subsetting, methods

|| DATA MANIPULATION-USING PYHTON MODULES

• Cleansing Data with Python • Python User Defined Functions

• Data Manipulation steps(Sorting, filtering, • Stripping out extraneous information
duplicates, merging, appending, sub setting, • Formatting data
derived variables, sampling, Data type • Important Python modules for data
conversions, renaming, formatting etc) manipulation (Pandas, Numpy, re, math,
• Data manipulation tools(Operators, string, date time etc)
Functions, Packages, control structures,
Loops, arrays etc)
• Python Built-in Functions (Text, numeric,
date, utility functions)
 TECH ACCESS
LEARNING PVT LIMITED

|| INTRODUCTION TO STATISTICS

• Basic Statistics - Measures of Central • Statistical Methods - (mean(), median(),

Tendencies and Variance mode()), Correlations
• Building blocks - Probability Distributions – • Important modules for statistical methods:
Normal distribution - Central Limit Theorem Numpy, Scipy, Pandas

|| ISCIENTIFIC DATA GATHERING AND DATA PREPARATION

• Identify variables
• Percentiles
• Data collection
• Correlation
• Simple random sampling
• Correlation vs causality
• Stratified sample
• Linear regression
• Nonsampling errors in sample
• Regression coefficients
• Data description
• R-squared
• Measure Of central tendency
• Exploratory data analysis
• Measure of variability
• Data visualization
• Measure of association b/w 2 or more
• EDA prior for model selection
variables
• Bayesian statistics
 TECH ACCESS
LEARNING PVT LIMITED

Tech Access Learning Pvt Ltd

Authorized training Partner of IT-IteS SSC(nasscom)
TP ID:TPFB0000283

Corporate office:A-12, FIEE COMPLEX

OKHLA PHASE -2, NEW DELHI, 110020

Branch office:B-39,1st floor Guru nanak park

Laxmi nagar

www. techaccess.co.in
[email protected]

+91 9643320085 |9643320089|9310669272