### Course Information

Data Science Course Duration:  60 Hours

Data Science Training Timings:  Week days 1-2 Hours per day (or) Weekends: 2-3 Hours per day

Data Science Training Method:  Online/Classroom Training

Data Science Study Material:  Soft Copy

### Course Content

Data Science Learning and Implementation Program

Introduction to Data Science:

• What is Data Science
• Roll of Machine Learning and Deep Learning
• Use case of Data Science
• Tools used in Data Science
• Lifecycle of Data Science
• Importance of AI
• Opportunities in Data Science

Statistics:

• Inferential vs Descriptive Statistics
• Variable Measurements
• Central Tendency Measures
• Mean, Mode and Median
• The Story of Average
• Dispersion Measures
• Range, Variance and Standard Deviation
• Five Number Summary
• Data Distributions
• Central Limit Theorem
• Sampling Methods
• Hypothesis testing
• Confidence Level
• Degrees of freedom
• Correlation vs Regression

Python:

• Basic Syntax
• Variables
• Operators
• Numbers and Strings
• Lists, Tuples and Arrays
• Loops
• Functions
• Pandas
• Numpy
• Handling packages
• Data Visualization

Machine Learning:

1. Data Preparation

• Univariate Analysis
• Multivariate Analysis
• Outlier Deduction
• Z Score
• Inter Quartile Range
• Data Scaling
• Algorithm Evaluation
• Evaluation Metrics
• Baseline Models

2. Regression Algorithms

• Simple Linear Regression
• Multivariate Linear Regression
• Logistic Regression
• Confusion Matrix
• Perceptron

3. Nonlinear Algorithms

• Classification Trees
• Regression Trees
• Naive Bayes
• k-Nearest Neighbours
• Support Vector Machines

4. Ensemble Algorithms

• Bagging
• Random Forest

5. Unsupervised Learning

• K means Clustering

6. Natural Language processing

• NLKT
• Bag of Words
• Sentiment Analysis

7. Time series forecasting

• Auto regression
• Moving Averages
• ARIMA
• Autocorrelation

Three end-to-end Machine Learning projects as below:

1. Define Problem

2. Load Data from Different Data Sources

3. Analyze Data

• Understand Data With Descriptive Statistics
• Understand Data With Visualization

4. Prepare Data

• Pre-Process Data
• Feature Selection

5. Evaluate Algorithms

• Resampling Methods
• Algorithm Evaluation Metrics
• Compare Machine Learning Algorithms
• Model Selection

6. Algorithm Parameter Tuning (Improve Results)

7. Model Finalization (Present Results)

Deep Learning:

1. Artificial Neural Networks

• Neurons
• Networks of Neurons
• Training Networks
• Tensorflow
• Keras
• Build ANN with Tensorflow and Keras

2. Convolutional Neural Networks

• Convolutional Layers
• Pooling Layers
• Fully Connected Layers
• Convolutional Neural Networks Best Practices

3. Recurrent Neural Networks

• Long Short-Term Memory Networks
• LSTM Network For Regression
• LSTM Network For Classification

Three end-to-end Deep Learning Implementations:

1. Deep Learning for Natural Language Processing

• Bag-of-Words
• Word Embeddings
• Text Classification
• Sequences

2. Deep Learning for Time Series Forecasting

• Prepare Time Series Data for CNNs and LSTMs
• MLPs for Time Series Forecasting
• CNNs for Time Series Forecasting
• LSTMs for Time Series Forecasting

3. Deep Learning for Computer Vision

• Image Data Preparation
• Convolutions and Pooling
• Convolutional Neural Networks
• Image Classification
• Object Detection
• Face Recognition