Introduction to Machine Learning:

Machine learning enables computers the ability to automatically learn and improve from experience without being explicitly programmed. Machine Learning accesses data for real time business problems and solves with improved decision making. A machine learning algorithm enables to identify hidden patterns inside a data, build models and offer solutions for complex business problems.

In this course, we provide you with both conceptual and practical approach on solving multiple real-life Business Data Problems. By the end of the course, you will have a solid understanding of Machine Learning, Machine Learning Algorithms, Feature Engineering, Machine Learning Components and Model Building, Model tuning, Model Optimization, Decision Making, Data Visualization, Data Interpretation, Advanced Data Analysis and Deep Learning.

Curriculum for this course:

Data Science and Data Analytics

  • What is Data Analytics
  • Skills required to become a data analyst
  • What is Data Science?
  • Skills required to become a data scientist

Machine Learning

  • What is Machine Learning
  • Supervised Learning
  • Unsupervised Learning
  • Reinforcement Learning

ML Model Deployment

  • Gathering the data
  • Data Preprocessing
  • Feature Engineering
  • Model building

ML Components

  • Representation
  • Evaluation
  • Optimization

Linear Regression

  • Simple, Multiple and Multivariate Linear Regression
  • Assumptions and Tests
  • Gradient Descent
  • Regularization

Logistic Regression

  • Multinomial and Ordinal Logistic Regression
  • Converting linear function to logistic function
  • Characteristics and Assumptions
  • Evaluation metrics
  • Goodness fit tests
  • Gradient descent

Decision Tree

  • Structure of tree models
  • Tree splitting (Gini index, Chi-square, entropy, variance)
  • Tree model parameters
  • Tree pruning (pre-pruning and post-pruning)

Random Forest

  • Ensemble Learning
  • Misconception: How Random forest is different from bagging
  • Parameter tuning
  • Variable Importance and Feature selection tool

Naïve Bayes’

  • Bayes’ theorem
  • Naïve assumption
  • Working with unstructured data
  • Zero frequency; Smoothing and Laplace transformation.

K means Clustering

  • What is Clustering and types
  • Connectivity, centroid, Distribution and Density models
  • Euclidean, Manhattan, Chebychev and MInkowsky distance
  • Total withiness
  • Elbow, Silhouette and Gap Statistic methods

K Nearest Neighbor

  • KNN intuition
  • Effective K
  • KNN for regression and Weighted KNN
  • Voronoi diagram
  • Kd-tree based on KNN
  • Locality sensitive hashing

Use Cases

  • Predicting House Value Price
  • Diabetic Classification
  • Predicting mail spam
  • Loan Predictions
  • US Arrests clusters

Have any additional questions?