Practical Notes for the AI and ML Enthusiast: A practical guide with working examples for AI and ML practitioners to deliver larger impact

What is in this book?

This book is a large collection of notes and research the author has put together to create a landscape of some of the key areas of Machine Learning and Artificial Intelligence topics that you should know.

Who should get this book?

PERFECT FOR MANAGERS, PROJECT LEADS, MID TO SENIOR AND STAFF DATA SCIENTISTS AND SWEs LOOKING TO JUMP INTO ML/AI.

Each chapter explains an algorithm and provides context on some application areas, shows a few snippets of code, and provides an overall understanding of the topic.

This is not a textbook!!

This is not a book filled with pages and pages of code!!

Machine Learning and Artificial Intelligence require practitioners to learn a large variety of topics. Many of these topics can span multiple academic departments in a post-graduate university not to mention cross-disciplinary disciplines are often interwoven in the full understanding of AI.

This book does a survey of many topics across a large number of references and material from authoritative sources online. You are getting research and information that should give you excellent resources to continue your learning journey.

Power-packed 30 chapters

1 Simple Linear Regression – Square Feet vs Price

2 Non-Linear Regression – China’s GDP

3 K-Nearest Neighbors – Diabetes Dataset

4 Decision Trees – Fruit Classification

5 Support Vector Machines – Fruit Classification

6 Naïve Bayes Classifier – Santander Customer Transaction Prediction

7 K-Means Clustering – Clustering hand-written digits

8 DBSCAN – Women Love Shopping

9 Random Forest – Fifa Best Player

10 Gradient Boosting – Income Prediction

11 Partial Least Squares Regression - Near-infrared Spectroscopy

12 Manifold learning – Breast Cancer Wisconsin

13 Isolation Forest – Detecting Anomalies

14 Hierarchical Clustering – Wholesale Customer Segmentation

15 Affinity Propagation Clustering – Feature-based Customer Segmentation

16 LSTM – LSTM in Trading

17 CNN – MNIST Image Classification

18 GAN – CIFAR -10 

19 RNN – Passengers of International Airline

20 Dimensionality Reduction Algorithms - Surface Electromyography

21 Markov Chain – Customer Identification

22 GRU - Multivariate Analysis - Oil Price Prediction Using LSTM & GRU

23 Deconvolutional NN – DNN in Keras

24 Hopfield - Hopfield Networks is All You Need

25 Boltzmann machines (BM) – Restricted Boltzmann Machines

26 Resnet – Facebook AI Research

27 Neural Turing Machines - Tensorflow implementation of a Neural Turing Machine

28 Kohonen Network - Data Mining Using Self-Organizing Kohonen Maps

29 Deep Belief Network – Credit Card Fraud Detection

30 Echo State Network - Reservoir Computing and Generalized Learning

About the Author

Superpowers today are the ability to wrangle cloud resources, AutoML, transfer learning, Notebooks with magics, serverless SQL, window functions, spreadsheets, JavaScript, Python, BigQuery, Colab, Docker, SparkSQL, Hive UDFs, Sparklyr, Plotly.

Harsh Singhal has created Market Mix Optimization (which ad property gets most of your dollars, Mu Sigma), Interaction Optimization & Customer Success Modeling (match agents to specific training programs based on chat text, 24/7), Bot Detection, and Credit Card Fraud (protect LinkedIn from fraudsters and content scrapers, LinkedIn), Game Anomaly Detection (protect real gamers from lazy botmasters, MZ) and Ad Optimization (ensure advertisers show ads to people and not to scripts running in data centers, C1X).