# IMAGE PROCESSING SUMMER INTERNSHIP PROGRAM 2022

- IMAGE PROCESSING

COMPLETE TRAINING ON TECHNOLOGY | PROJECT DEVELOPEMENT

#### HYDERABAD

407, 4th Floor, Pavani Prestige (R.S Brothers)Building, Ameerpet, Hyderabad, India Opposite Image Hospital & Beside KLM Fashion Mall.

## About Image Processing

Machine learning is an application of artificial intelligence (AI) that provides systems the ability to automatically learn and improve from experience without being explicitly programmed. Machine learning focuses on the development of computer programs that can access data and use it to learn for themselves. The process of learning begins with observations of data, such as examples, direct experience, or instruction, in order to look for patterns in data and make better decisions in the future based on the examples that we provide. The primary aim is to allow the computers to learn automatically without human intervention or assistance and adjust actions accordingly.

## Registration Process

## Internship Tracks

## Machine Learning

##### Day - 1: Introduction to Machine Learning

2. How Machine Learning Useful in Daily Life

3. Machine Learning Goals and Deliverables.

4. Why Machine Learning

5. Machine Learning Tools.

##### Programming Essentials

##### Day - 2: Introduction to Python

2.Anaconda Installation and Introduction to Jupyter Notebook

##### Day - 3: Python Basics

##### Day - 4: Python Baiscs

##### Day - 5: Python Baiscs

##### Day - 6: Python for Data Science - Numpy

2. Operations in Numpy

##### Day - 7: Python for Data Science - Pandas

2. Operations in Pandas – Pandas Basics, Indexing and selecting Data,Merge and Append, Grouping and Summarizing, Lambda functions and Pivot tables

3. Introduction to Reading.

##### Day - 8: Python for Data Science - Matplotlub

2. Types of plots with ExamplesInheritence,Polymorphism,Encapsualtion,Abstraction

##### Day - 9: Introduction to SQL

2. Basics of SQL, Data Retrieval, sorting, compound functions and relational operators, pattern matching with wild cards.

3. Basics on Table creation, updating, modifying etc.

4. Overall Structure of data retrieval queries, Merging tables, User Defined Functions (UDF), Frames.

##### Statistics & Exploratory Data Analysis (EDA)

##### Day - 10: Introduction to Data Analytics

2. CRISP-DM Framework – Data Preparation, Modelling, Evaluation and Deployment

##### Day - 11: Data Visualization in Python

2. Introduction to various charts

3. Data visualization toolkit in Python (Libraries or modules available in Python)

4. Plotting Data in Python using matplotlib and seaborn – Univariate Distributions, Bi-variate Distributions

5. Plotting Time series data

##### Day - 12: Exploratory Data Analysis

2. Data Cleaning – Fixing rows and columns, Missing value Treatment, standardizing values, handling invalid values, Filtering data

##### Day - 13: Exploratory Data Analysis

2. Univariate Analysis, Bivariate Analysis, Segmented univariate Analysis

3. Derived Metrics and Feature Engineering

##### Day - 14: Exploratory Data Analysis

2. Identify Outliers

3. Outliers Handling using Imputation Techniques

##### Day - 15: Inferential Statistics

2. Discrete and Continuous Probability Distributions

3. Central Limit Theorem – Introduction and Industrial applications

##### Day - 16: Hypothesis Testing

2. Concepts of Hypothesis Testing – p value method, critical value method

3. Types of Errors, T Distribution, other types of tests

4. Industry Demonstration and A/B Testing

##### Day - 17: Case Study

2. GDP EDA Analysis

##### Machine Learning - I

##### Day - 18: Introduction to Machine Learning

##### Day - 19: Simple Linear Regression

2. Assumptions of Linear Regression (LINE)

3. Cost Functions, Strength of Linear relationship – OLS, coefficient of correlation, coefficient of Determination

4. Intuition to Gradient Descent for optimizing cost function

5. Hypothesis Testing in Linear Regression

6. Building a Linear Model – Reading Data, Cleaning Data, Libraries available – Sklearn, Statsmodel.api

7. Model Building using Sklearn and Training and Test Data, Model Development, Model validation using Residual Analysis, Evaluation against the test Data

##### Day - 20: Multiple Linear Regression

2. Introduction to overfitting, Multi-collinearity

3. Dealing with Categorical variables – OHE, Dummies, Label Encoding

4. Building the model using statesmodel.api and importance of p-values

5. Model Evaluation Metrics – Coefficient of Determination, Adjusted R2, RMSE, AIC, BIC and other model evaluation Metrics

6. Variable Selection – RFE, Step wise selection etc.

7. Gradient Descent and Normal Equation for Multiple Linear Regression

8. Industry Demonstration: Linear Regression Case Study

##### Day - 21: Logistic Regression

2. Binary classification using univariate logistic regression

3. Maximum Likelihood function, Sigmoid Curve and Best Fit

4. Intuition of odds and log-odds

5. Feature selection using RFE

6. Model evaluation – Confusion Matrix and Accuracy

7. Why Accuracy is not Enough and introduction to sensitivity, specificity, precision, recall, area under curve

8. Logistic Regression Case Study

##### Day - 22: Unsupervised Learning:Clustering

1. Understanding clustering with practical examples

2. KMeans Clustering – understanding the algorithm

3. Practical consideration for KMeans Clustering – Elbow curve, silhouette metric and hopkings test for clustering tendency of data, impact of outliers

##### Day - 23: Unsupervised Learning

1. Hierarchical clustering Algorithm

2. Interpreting the dendogram and Types of Linkages

3. Comparison of Kmeans clustering and Hierarchical clustering – advantages and disadvantages

##### Day - 24: Unsupervised Learning:Principal Component Analysis(PCA)

2. Variance as information and basis transformation of vectors

3. Singular Value Decomposition and Identifying optimum principal components using scree plots

4. Model building with PCA

5. Advantages of PCA and Limitations

##### Machine Learning - II

##### Day - 25: Support Vector Machine Algorithm

1. Introduction to SVM and How does it works.

2. Advantages and Disadvantages of SVM

3. Kernal Functions in used in SVM

4. Applications of SVM

5. Implementation of SVM using Python

##### Day - 26: K Nearest Neighbors Algorithm

1. Introduction to KNN and How does it works.

2. Advantages and Disadvantages of KNN

3. Applications of KNN

4. Implementation of KNN using Python

##### Day - 27: Naive Bayes Algorithm

1. Intoduction to Naive Bayes

2. Advantage and Disadvantage of Naive Bayes

3. Applications of Naive Bayes

4. Implementation of Naive Bayes using Python

##### Day - 28: Tree Models

1. Introduction to decision trees and Interpretation

2. Homogeneity measures for splitting a node 1. Gini Index 2. Entropy 3. R2

3. Understanding Hyper parameters – Truncation and Pruning

4. Advantages and Disadvantages

Random Forest:

1. Introduction to ensembling, bagging and intuition

2. Random Forest – Introduction and Hyperparamters

3. Building a model using Random Forest

4. Hyper-parameters impact on model and tuning them

5. Importance of predictors using Random Forrest

##### Day - 29: Boosting

2. Introduction to Boosting Algorithms : XGBoost, lightGBM, Catboost

3. Advantages of Boosting Algorithms

4.XGBoost Model Building and importance of various Hyper parameters

5. Hyper-parameter tuning for XGBoost

##### Day - 30: Case Study

##### Day - 31: Case Study

##### Day - 32: Time Series

2. Trend and seasonality

3. Decomposition

4. moothing (moving average)

5. SES, Holt & Holt-Winter Model

##### Day - 33: Time Series

2. IADF, Random walk and Auto Arima

##### Day - 34: Text Mining

2. Text cleaning, regular expressions, Stemming, Lemmatization

3. Word cloud, Principal Component Analysis, Bigrams & Trigrams

4. Text classification, Document vectors, Text classification using Doc2vec