# Course Structure

We have designed this course in order to provide extensive knowledge to the learner on how to kick start and enhance your career in the field of Data Science, Machine Learning and Deep Learning. On the basis of Deep Learning, our data scientist team will help you to understand the knowledge of computer vision using Deep Convolutional Network.

Basically, during the entire course, we will only focus on Python Programming. First, we will start with some Algorithm design problem-solving questions in order to familiarise learner on how we can develop various models of deep learning and let them do various tasks in less number of time. Next, we will focus on some important library of python which are the backbone of Data Science, Machine Learning and Deep Learning such as Pandas, Numpy, OpenCV, and StatsModel. While on the other side, this course will focus on Fundamental Mathematical concepts such as descriptive statistics, probability, Linear Algebra. Mathematics plays a very important in order to build a solid background for deep learning. Now, in the machine learning part, we aim to focus on theoretical concepts of some machine learning algorithms which are important to understanding deep learning and neural networks. Next, we jump to deep learning along with there implementation using SKlearn, Keras, Tensorflow. The best one will provide an opportunity to work with us as an intern/employee along with the understanding of deep learning in Computer Vision.

## Python Programming

Algorithm Design

Python Syntax

Introduction to Competitive Programming

Some practice problems.

Min-Max Algorithm

Backtracking

Dynamic Programming

Numpy, Pandas, OpenCV

## Statistics, Probability and Linear Algerbra

Maths behind M.L

Measures of central tendency

Z-Score

Interquartile Range

Collinearity and multicollinearity

Pearson's r

Probability Distributions

Baye's theorem

Central limit theorem

Hypothesis testing

Scalers, Vectors, Matrices, and Tensors

Linear Transformations.

Matrix inversion and determinants

Eigen Values, Eigen Vectors

Trace operator.

## Machine Learning

Now we start

Supervised Learning

Linear regression

Logistic regression

Overfitting, perfectly fit, underfitting

Hyperparameter Tuning

Bias and Variance

Gradient-Based optimization and stochastic gradient descent

Support Vector Machines

Agglomerative and K-means clustering

Decision Trees.

## Deep Learning

Here comes the monster

Learning the basics of neural networks

Backpropagation algorithm and forward propagation algorithm

Regularization for Deep learning

Optimization algorithm

Hyperparameter tuning and batch normalization

Convolutional Neural Networks

Object detection and face recognition theory