DATA SCIENCE AND MACHINE LEARNING

– Core Data Structure of Python (Variable, List, Tuples, Dictionary, Set, Loop, Functions, Maps, Function Recursion)

– Python Core (List & Dictionary Comprehension, Exceptions & Exceptions Handling, File Handling, Object Oriented Programming & OOP concepts)

– List and Dictionary Comprehension

– Exceptions and Exception Handling

– File Handling

– Object Oriented Programming (OOP)

– Introduction to Classes

– Inheritance, Encapsulation, Polymorphism, Abstraction

– Method Overloading

– Building Custom Packages and Modules

– Introduction to Data Science, NumPy, Matplotlib,

– Matrix Operations with NumPy

– Probability, properties of Probability Distributions

– Mean, Median, Mode, Variance, Skewness, Kurtosis, Multivariate Normal Distribution, Co-Variance, Correlation

– Introduction to Scikit-Learn

– Dimensionality Reduction as Data Pre-Processing

– Principal Component Analysis (PCA), Linear Discriminant Analysis (LDA)

– Introduction to Reinforcement Learning

– Q-Learning with Python

– Introduction to Clustering

– K-Means Clustering

– Agglomerative Clustering

– Introduction to Supervised Learning

– Naive Bayes Classification

– Linear and Polynomial Regression, K-Nearest Neighbors, Decision Tree

– Balancing Bias vs Variance of ML Model, Ensemble Learning, Random Forest and Adaptive Boost

– Identifying Important Features of Data

– Time Series Analysis

– Introduction to Logistic Regression, Computation Graph and Gradient Descent

– Introduction to Artificial Neuron (Perceptron), Multi-Layer Perceptron

– Introduction to Artificial Neural Networks

– Designing Artificial Neural Networks with Keras

– Gradient Decent Variants, Classification and Regressionusing Neural Networks

– Introduction to Convolutional Neural Network (CNN)

– Object Classification with CNN, Standard CNN Architectures

– Introduction to Object Detection, Transfer Learning

– The YOLO Algorithm, Deep Reinforcement Learning

Natural Language Processing + Web Interface

– Introduction to NLTK, Text Pre-Processing

– POS Tagging and Named-Entity Recognition, Latent Semantic Analysis

– Introduction to Recurrent Neural Network, Word2Vec Algorithm for Text Vectorization

– Natural Language Processing with LST

– Giving Web Interface to ML Application using Flask/Django/Streamlit.

– Introduction to NLTK

– Text Pre-Processing

– POS Tagging and Named-Entity Recognition

– Latent Semantic Analysis

– Introduction to Recurrent Neural Network

– Word2Vec Algorithm for Text Vectorization

– Natural Language Processing with LST

– Giving Web Interface to ML Application using Flask/Django / Streamlit.

– Each student will have a project to complete in order to demonstrate their understanding both during and after the course.

– Lab assignments will focus on the practice and mastery of contents covered in the lectures; and introduce critical and fundamental problem-solving techniques to the students.