Machine Learning and Deep Learning

Date of commencement of Course
  • Shall be declared soon
  • Any graduate with background in Mathematics and interest in data science
  • Shall be declared soon
Expected Learning outcomes
  •  Participants will be able to write python programs

  • Understand statistics and inferences with applications

  • Machine learning and Deep Learning fundamentals and applications

Course Fees (in Rs.)
  • 12000/-
Topics covered
  • DS001: Python for Data Science (15 Hours)
  • Topics : Introduction to Google Colab, Basic Python Syntax, Operations in Python,  Decision and Control Structures, Python Lambdas, Python Functions, Recursion, Python Modules, Python Data Structures which include Lists, Tuples, Sets and Dictionaries, Python Install Packages (PIP), Introduction to Python Packages like Numpy, Pandas, datetime, Regular Expressions in Python
  • DS002: Descriptive and Inferential Statistics (15 Hours)
  • Topics: Descriptive Statistics which include Central Tendency, Dispersion, Skewness, Kurtosis, Correlation analysis which include Pearson, Spearman, Kendall correlation coe_ecient, Similarity and disimmilarity of attributes, Data Visualization using Matplotlib, Box plots, Introduction to Probability, Bayes Theorem, Probability Distributions: Binomial, Poisson , Normal, Central Limit Theory, Introduction to Inferential Statistics, Parameter Estimation, Concepts related to hypothesis testing, ANNOVA and related examples using Python
  • DS003 : Machine Learning (15 Hours)
  • Topics :Introduction to Machine Learning, Di_erent methods of Machine Learning, Data Preprocessing, Understanding data with Statistics and Visualization, Data Feature Selection, Performance Metrics,Machine Learning workows, Formuation and discussion of Machine Learning Algorithms which include Linear Regression, Naive Bayes Classification, K-Means Clustering, Logistic Regression and Time Series Analysis (ARIMA) with suitable case studies
  • DS004: Deep Learning (15 Hours)
  • Topics :Introduction to Deep Learning, Neural Network Basics, Artificial Neural networks and its layers, Activation functions, weights and weights sharing, loss functions and partial ordering, Working with Tensor flow, Keras and Pytorch, Backpropogation in Feed forward networks, Feed forwards in Classification and Regression, Regularization, Optimization for Training deep learning models, Hyperparameter tuning, Introduction to Convolutional Neural networks, Understanding
Faculty/Experts/Resource person
  • Prof. Hrishikesh Khaladkar, Dr. Tushar Deshmukh
Program Coordinator


Association With: