Only Few Seats Left

Module

1

-Basics of Python Language

- Python objects with details of shell/numbers/variables etc.

- Python for Data cleaning and preprocessing using Pandas

- Python for Data visualization & Graphical plotting using libraries like Matplotlib & Seaborn

- Hands-on project to demonstrate the use of Python for Data Analytics, splitting Data into train & Test set, features scanning

Module

2

- Machine Learning Basics, introduction to supervised & unsupervised learning

-  Linear Regression for One and Multiple Variables, Cost Function & Gradient Function

- Ordinary Least Square, Dummy Variables, One Hot Encoding, Polynomial Regression

- Anscombe’s quartet, Performance Metrics like Mean Absolute Error, Root Mean Squared Error, - Regularization (Ridge & Lasso)

Module

3

- Logistic Regression, Sigmoid Function, Anscombe’s quartet

-Confusion Matrix, Interpreting parameters like F-1 score, Accuracy, Precision, Recall etc.

- Bias-variance trade off, Overfitting, Underfitting of Models

-K- nearest neighbors (KNN), Elbow Method

-Distance Metric in KNN

Module

4

- Understanding Support Vector Machines using Hyperplanes, Maximum Margin Classifier

- Higher Dimension Transformation and Projection, Kernels :: Polynomial, RBF etc.

- Decision Trees, Nodes: Root, Leaf, Parent, Children. Tree Pruning, Gini Impurity

- Random Forests, Ensemble Learners, Information Gain

- Hands-on Projects

Module

5

-Boosted Trees, Weak and Strong Learners, AdaBoost, Gradient Boosting, Stump Classification

-Naive Bayes classifier, Conditional Probability, Bayes Theorem

- Natural Language Processing (NLP), Count Vectorization, Extracting Features From Text Data, Term Frequency - Inverse Document Frequency (TF-IDF) , Document Term Matrix (DTM)

-Hands-on Projects

Module

6

-Unsupervised Learning Basics

- K-Means Clustering, Clustering of unlabeled data, Assigning new point to the cluster

-Hierarchical Clustering: Agglomerative and Divisive Approach, Dendrogram, Linkage Matrix, Similarity Metrics, Ward

- DBSCAN, epsilon distance, Core, Border and Outlier

-Principal Component Analysis (PCA), Dimension Reduction