You are on page 1of 20

ACADGILD

Learn. Do. Earn.

DATA SCIENCE
WITH PYTHON
COURSE DETAILS
01

Brief About this Course


Deep learning is an application of Machine Learning using Artificial Neural
Network (ANN). Inspired from the functioning of the brain, Deep Learning
emulates the learning approach of human in computers and machines. Used
for some of the most revolutionary developments in AI, it is gradually
transforming the machine-intelligence landscape worldwide.

AcadGild’s Data Science - Deep Learning with TensorFlow training is an


intensive course to help you acquire advanced knowledge of all the key
concepts of Deep Learning.
02

Who should take this Course


This course exposes you to the real-world applications of Deep Learning.
Learn and explore Deep Learning skill sets by implementing an intuitive
approach to build complex models that enable the machines to solve real
-time problems with AcadGild’s Deep Learning with TensorFlow training
program.
03

Why Learn
Deep Learning, a rising and promising extension to traditional Machine
Learning is creating a huge stride with Google’s Brain project and its
acquisition of Deepmind, a London-based Deep Learning start-up

Google’s TensorFlow is expected to be a Game Changer in Artificial


Intelligence era by empowering everyone an opportunity to learn
and understand.

The average salary of a Data Scientist with Machine Learning skills is $91,
422 per year.
04

Data Science with


Python course
05

Session 2 Hours
01

Python Basics ,Conditional &Loops


• Installation of Python and Ipython Notebook
• Python Objects • Number & Booleans • Strings • Container objects
• Mutability of objects • Operators - Arithmetic
• Bitwise,comparision and Assignment operators
• Operators Precedence and associativity • Conditions(If else,if-elif-else)
• Loops(While ,for) • Break and Continue statements • Range functions

Session 2 Hours
02

String Objects and List objects


• String object basics • String methods • Splitting and Joining Strings
• String format functions • list object basics • list methods
• List as stack and Queues • List comprehensions

Session 2 Hours
03

Tuples, Set, Dictionaries & Functions


• Tuples • Sets • Dictionary Object basics • Dictionary Object methods
• Dictionary View Objects • Functions basics • Parameter passing
• Iterators • Generator functions • Lambda functions • Map • Reduce
• Filter functions
06

Session 2 Hours
04

OOPS concepts & Working with Files


• OOPS basic concepts • Creating classes and Objects • Inheritance
• Multiple Inheritance • Working with files • Reading and writing files
• Buffered read and write • Other File methods

Session 2 Hours
05

Modules , Exception Handling and


Database Programming
• Using Standard Module • Creating new modules • Creating
• Exceptions Handling with Try-except • Inserting and retrieving Table
• Updating and deleting the data

Session 2 Hours
06

Statistics I
• Descriptive Statistics • Sample vs Population statistics
• Expected value
07

Session 2 Hours
07

Statistics II
• Binomial Distribution • Normal Disrtributions • z-score
• Central limit Theoram

Session 2 Hours
08

Statistics III
• Hypothesis testing • Z-Stats vs T-stats • Type 1 type 2 error
• confidence interval

Session 2 Hours
09

Statistics IV
• Chi Square test • ANOVA test • F-stats

Session 2 Hours
10

Data Ananlysis I
• Numpy variable • Scipy • Pandas intro
08

Session 2 Hours
11

Data Ananlysis II
• Descriptive analysis • Pandas Input-output • Pandas groupby
• Pandas manipulation

Session 2 Hours
12

Data Ananlysis III


• Matplotlib intro • Bar charts histogram • Scatter plot
• Stack charts • Legend title Style

Session 2 Hours
13

Data Ananlysis IV
• Combining multiple datasets to get a single and clean dataset
• Data Cleaning walkthrough
09

Session 2 Hours
14

Machine Learning I
• Introduction • Supervised • Unsupervised • PSemi-supervised
• Reinforcement • Train • Tes • Validation Split • Performance
• Overfitting • Underfitting

Session 2 Hours
15

Machine Learning II
• Linear Regression • Assumptions • R square adjusted R square
• Intro to Scikit learn • Training methodology
• Hands on linear regression

Session 2 Hours
16

Machine Learning III


• Logistics regression • Precision Recall
• ROC curve • F-Score
10

Session 2 Hours
17

Machine Learning IV
• Decision Tree • Cross Validation
• Bias vs Variance

Session 2 Hours
18

Machine Learning V
• Ensemble approach • Bagging Boosting
• Randon Forest • Variable Importance

Session 2 Hours
19

Machine Learning VI
• XGBoost
• Hands on XgBoost

Session 2 Hours
20

Machine Learning VII


• K Nearest Neighbour • Lazy learners
• Curse of Dimensionality • KNN Issues
11

Session 2 Hours
21

Machine Learning VIII


• Text Ananlytics • Tokenizing • Chunking • TFIDF
• Document term Matrix • Sentiment analysis hands on

Session 2 Hours
22

Machine Learning IX
• Hierarchical clustering • K-Means
• Performance measurement

Session 2 Hours
23

Machine Learning X
• Principal Component analysis
• Dimesionality reduction • Factor Analysis

Session 2 Hours
24

Machine Learning XI
• Time Series Forecasting
• Moving Average • ARIMA model
12

Session 2 Hours
25

Deep Learning I
• Basic of Neural Network • Type of NN • Cost Function
• Gradient descent • Linear Algebra basics

Session 2 Hours
26

Deep Learning II
• Linear Algebra Refresher

Session 2 Hours
27

Deep Learning III


• Vanilla implementation of Neural Network in python

Session 2 Hours
28

Machine Learning IV
• Tensorflow basics
• Hands on Simple NN with Tensorflow
13

Session 2 Hours
29

Deep Learning V
• Multilayer model with tensorflow • Save and restore trained model
• Make tensorflow graph • Dropout

Session 2 Hours
30

Deep Learning VI
• Word Embedding • CBOW • Skip-gram
• Word Relations • Hands on word2vec

Session 2 Hours
31

Deep Learning VII


• Convolutional Neural Network • Maxpool
• Window padding • Hands On

Session 2 Hours
32

Machine Learning VIII


Image classification using Convolutional Neural Network
14

Session 2 Hours
33

Deep Learning IX
• Recurrent Neural Network
• Long Short Term Memory (LSTM) architecture
• Building Story writer using character level RNN

Session 2 Hours
34

Deep Learning X
• Sentiment Analysis Hands on
• Hands on embedding + RNN

Session 2 Hours
35

Deep Learning XI
• Seq-to-Seq model
• Hands on translation
15

Session 2 Hours
36

Deep Learning XII


• Encoder Decoder
• Hands on cleaning images

Session 2 Hours
37

Deep Learning XIII


• GAN
• Generative Model Using GAN

Session 2 Hours
38

Deep Learning XIV


• Semi-supervised learning using GAN
16

Session 2 Hours
39

Projects I
• Case Study: Spam Detection

Session 2 Hours
40

Projects II
• Case Study: Generating scripts for TV Serials

Session 2 Hours
41

Projects III
• Case Study: Translation model for languages
17

Session 2 Hours
42

Handling Big Data With Spark I


• Spark Installation And Jupyter Notebook Integration

Session 2 Hours
43

Handling Big Data With Spark II


• RDD's in Spark

Session 2 Hours
44

Handling Big Data With Spark III


• Introduction to Data Frames & Spark SQL

Session 2 Hours
45

Handling Big Data With Spark III


• Spark Streaming
18

Session 2 Hours
46

Handling Big Data With Spark IV


• MLib & GraphX

Session 2 Hours
47

Handling Big Data With Spark V


• Deplyoing a Spark Application

Session 2 Hours
48

Handling Big Data With Spark VI


• Implementing Case Study on Spark Ecosystem
support@acadgild.com | www.acadgild.com | 8880025025

You might also like