What Every Engineer Should Know about Data-Driven Analytics 1st Edition by Satish Mahadevan Srinivasan 9781000859720 100085972X

What Every Engineer Should Know about Data-Driven Analytics 1st Edition Satish Mahadevan Srinivasan – Ebook Instant Download/Delivery ISBN(s): 9781000859720, 100085972X

Product details:

• ISBN 10: 100085972X
• ISBN 13:9781000859720
• Author: Satish Mahadevan Srinivasan 

What Every Engineer Should Know About Data-Driven Analytics

Table contents:

1 Data Collection and Cleaning
Data-Collection Strategies
Data Preprocessing Strategies
Programming with R
Data Types in R
Data Structures in R
Package Installation in R
Reading and Writing Data in R
Using the FOR Loop in R
Using the WHILE Loop in R
Using the IF-ELSE Statement in R
Programming with Python
Data Wrangling and Analytics in R and Python
Structuring and Cleaning Data
Missing Data
Strategies for Dealing with Missing Data
Data Deduplication
Summary
Exercise
Notes
References
2 Mathematical Background for Predictive Analytics
Basics of Linear Algebra
Vectors and Matrices
Determinant
Simple Linear Regression (SLR)
Principal Component Analysis (PCA)
Singular Value Decomposition (SVD)
Introduction to Neural Networks
Summary
Exercise
References
3 Introduction to Statistics, Probability, and Information Theory for Analytics
Normal Distribution and the Central Limit Theorem
Pearson Correlation Coefficient and Covariance
Basic Probability for Predictive Analytics
Conditional Probability
Bayes’ Theorem and Bayesian Classifiers
Information Theory for Predictive Modeling
Summary
Exercise
Notes
References
4 Introduction to Machine Learning
Statistical versus Machine Learning Models
Regression Techniques
Multiple Linear Regression (MLR) Model
Assumptions of MLR
Introduction to Multinomial Logistic Regression (MLogR)
Bias versus Variance Trade-off
Overfitting and Underfitting
Regularization
Ridge Regression
Lasso Regression
Summary
Exercise
Notes
References
5 Unsupervised Learning
K-means Clustering
Hierarchical Clustering
Association Rule Mining
K-Nearest Neighbors
Summary
Exercise
References
6 Supervised Learning
Introduction to Artificial Neural Networks
Forward and Backward Propagation Methods
Architectural Types in ANN
Hyperparameters for Tuning the ANN
An Example of ANN Classification
Introduction to Ensemble Learning Techniques
Random Forest Ensemble Learning
Introduction to AdaBoost Ensemble Learning
Introduction to Extreme Gradient Boosting (XGB)
Cross-Validation
Summary
Exercise
References
7 Natural Language Processing for Analyzing Unstructured Data
Terminology for NLP
Installing NLTK and Other Libraries
Tokenization
Stemming
Stopwords
Part of Speech Tagging
Bag-of-Words (BOW)
n-grams
Sentiment and Emotion Classification
Summary
Exercise
References
8 Predictive Analytics Using Deep Neural Networks
Introduction to Deep Learning
The Deep Neural Networks and Its Architectural Variants
Multilayer Perceptron (MLP)
Convolutional Neural Networks (CNN)
Recurrent Neural Networks (RNN)
AlexNet
VGGNet
Inception
ResNet and GoogLeNet
Hyperparameters of DNN and Strategies for Tuning Them
Activation Function
Regularization
Number of Hidden Layers
Number of Neurons Per Layer
Learning Rate
Optimizer
Batch Size
Epoch
Weight and Biases Initialization
Grid Search
Random Search
Deep Belief Networks (DBN)
Analyzing the Boston Housing Dataset Using DNN
Summary
Exercise
References
9 Convolutional Neural Networks (CNN) for Predictive Analytics
Convolution Layer
Padding and Strides
ReLU LAYER
Pooling Layer
Fully Connected Layer
Hyperparameters of CNNs
Image Classification Using a CNN Model Based on LeNet Architecture
Summary
Exercise
References
10 Recurrent Neural Networks (RNNs) for Predictive Analytics
Recurrent Neural Networks
Long Short-Term Memory
Forget Gate
Input Gate
Output Gate
More Details of the LSTM
Hyperparameters for RNNs
Summary
Exercise
References
11 Recommender Systems for Predictive Analytics
Content-Based Filtering
Cosine Similarity
Collaborative Filtering
User-Based Collaborative Filtering (UBCF)
Item-Based Collaborative Filtering (IBCF)
Hybrid Recommendation Systems
Examples of Using Hybrid Recommendation Systems
Summary
Exercise
References
12 Architecting Big Data Analytical Pipeline
Big Data Technology Landscape and Analytics Platform
Data Pipeline Architecture
Lambda Architecture
Twitter and Pinterest’s Data Pipeline Architecture
Design Strategies for Building Customized Big Data Pipeline
Design Patterns and Pattern Languages

People also search:

what every engineer should know about data-driven analytics

do data engineers need to know statistics

most important skills for data engineer

what is data driven analysis

what skills should a data engineer have