Python Programming (Oplan CSE-14) (23 Sep to 27 Sep 2019)

Contents

Introduction to Python Programming and Applications
Anaconda Distribution, Jupyter setup and Python Programming
Data Structures, Functions, Modules and Control Statements
Statistics, Linear Algebra, and Probability
File and Data Handling
Data Preprocessing, Cleaning, Mangling and Association Analysis
Object oriented Programming, Error and Exception Handling
Supervised Techniques Implementation , Model Evaluation and Hands-On
Geospatial Data Analysis and Real Time Streaming Apps
Computer Vision and Image Processing using OpenCV with Practice Session
Block Chain Implementation using Python
Unsupervised Techniques Implementation, Model Evaluation and Hands-On
Advance Data Visualization and Plotting using Matplotlib
Social Data Analysis using Python
Programming Paradigm and Future Research Prospects

Machine Learning and Deep Learning using Open Source (Oplan CSE-12) (16 Sep 2019 to 27 Sep 2019)

Setup and Installation of Python and Jupyter Notebook

Essential of statistics for Machine Learning

Advance Statistics

Data Structure, Data Types, Control Statements in Python

Functions, Arrays and Essentials of Python
Machine Learning Algorithms and Libraries

Implementation of Decision Trees

Naïve Bayes Classifiers
k‐nearest Neighbours, Ensembles of Decision Trees
Clustering, K‐means, Agglomerative and Hierarchical Clustering

File and Data Handling For Machine Learning

Data Preprocessing and ETL Tools for Machine Learning
Random Forest, Ensemble Learning and Regression Algorithms
Advance Clustering Algorithms and Implementation
OpenCV for Machine Learning in Computer Vision Applications

Machine Learning for Social Network Analysis

Introduction to Deep Learning and Applications
Deep Learning Chains

Tensor flow Installation and Programming

Keras Framework and Programming

Essential Mathematics for Deep Learning
Principles of Deep Learning Techniques

Building Neural Networks from scratch: Path towards deep networks

Techniques for Optimizing Deep Neural Networks
Parallel Architectures, GPUs and Hardware for Deep Learning
Training deep networks from Scratch, Classical Architectures and Transfer Learning
Sequence Models

Working with NLP: intro spacy, embeddings and text generation