Data Science
Data science is a combination of statistics, data analysis, machine learning and many other methods to understand and analyse the data to get valuable insights. It uses techniques and ideas from various fields such as mathematics, information science, and computer science (Databases, machine learning etc). It is often used in business analytics to gather business intelligence and make informed business decisions. The Harvard Business Review called it “The Sexiest Job of the 20th Century” in their report in 2012 (report here) and it made a buzzword.
  • Next batch: 17 Nov, 2018
  • 80 hrs
  • 8 weekends (Sat & Sun)
About the Course
Introduction to Python • List | Strings | Tuples | Dictionary • Functions | Modules • Pandas • Numpy • Sklearn • Matplotlib
Conditional Probability • Bayes Theorem • Correlation and Covariance • Measure of central tendency • Standard Deviation and Variance • Central Limit Theorem • Binomial distribution • Multinomial distribution • Normal distribution • Vector and Matrix • Optimisation (Gradient Descent)
ML mathematical definition • Supervised, Unsupervised, Semi-supervised ML • Classification, Regression, Clustering • Training Data, Validation Data and Test Data • Underfitting and Overfitting • Bias and Variance trade-off • Accuracy, Precision, Recall, F-Measure, ROC curve
K- Nearest Neighbors ▪ Naïve Bayes- Discrete and Continuous ▪ Decision Trees ▪ Random Forest ▪ Support Vector Machines ▪ Bagging and Boasting ▪ Logistic Regression/Classifier
Linear Regression ▪ Lasso Regularization (L1) ▪ Ridge Regularization (L2) ▪ Elastic net Regularization
▪ K-means clustering ▪ K-medoids clustering ▪ Hierarchical Clustering - Agglomerative and Divisive ▪ Density-based clustering-DBSCAN
Introduction to Deep Learning • Artificial Neural Network • Forward propagation • Backword propagation • Activation functions • Gradient descent for Neural Nets • Regularization in Neural Nets • Common NLP tasks • Word Embeddings • TF-IDF • Continuous Bag of words • Skip-gram model • Text classification • Sentiment
Exploratory data analysis (EDA), Feature Engineering, Feature selection, training some predictive models, Validating and tuning hyper parameter
Trainer details
IIT Post-Graduate in Data Science I Experienced Data Scientist I Delivered trainings to 100+ professionals since 2016 l Published in International conferences like NLDB, SenEval and ICON.