Data Mining Skill, MDS Program 1, MDS Program 2
Machine Learning and Deep Learning using Python , TensorFlow and Keras
0( 0 REVIEWS )
0 STUDENTS
Instructors
You must be logged in to take this course → LOGIN | REGISTER NOW
Machine Learning and Deep Learning using Python , TensorFlow and Keras
0 STUDENTS ENROLLED
Course Curriculum
| Session - 1 Data Preparation & Regression Analysis | |||
| Introduction to Machine Learning | 00:00:00 | ||
| <ul> <li>Introduction to Machine Learning tools</li> <li>Introduction to Python</li> <li>Tools comparison</li> <li>The learning paths</li> </ul> | |||
| Data Exploration, Validation and Sanitization | 00:00:00 | ||
| <ul> <li>Raw Data - issues</li> <li>Data Exploration for continuous variables</li> <li>Data Exploration for categorical variables</li> <li>Data Validation</li> <li>Data sanitization techniques</li> <li>Missing value treatment</li> <li>Outlier treatment</li> <li>Loans data case study and data cleaning</li> </ul> | |||
| Regression Analysis | 00:00:00 | ||
| <ul> <li>Correlation Simple</li> <li>Regression models</li> <li>R-Square</li> <li>Multiple regression</li> <li>Multicollinearity</li> <li>Individual Variable Impact</li> <li>Air passenger’s data case study</li> <li>SAT score data case study</li> </ul> | |||
| Session - 2 Classification using Logistic Regression and Trees | |||
| Logistic Regression deep learning | 00:00:00 | ||
| <ul> <li>Need of logistic Regression</li> <li>Logistic regression models</li> <li>Validation of logistic regression models</li> <li>Multicollinearity in logistic regression</li> <li>Individual Impact of variables</li> <li>Confusion Matrix</li> <li>Service Provider Attrition data case study</li> </ul> | |||
| Decision Trees | 00:00:00 | ||
| <ul> <li>Segmentation</li> <li>Entropy</li> <li>Information gain</li> <li>Building Decision Trees</li> <li>Validation of Trees</li> <li>Pruning the trees</li> <li>Fine tuning the trees</li> <li>Prediction using Trees</li> <li>Customer retention case study</li> </ul> | |||
| Session - 3 Model Validation Techniques and Neural Networks | |||
| Model Selection and Cross validation | 00:00:00 | ||
| <ul> <li>How to validate a model?</li> <li>What is a best model?</li> <li>Types of data</li> <li>Types of errors</li> <li>The problem of over fitting</li> <li>The problem of under fitting</li> <li>Bias Variance Trade-off</li> <li>Cross validation</li> <li>Boot strapping</li> <li>Attrition data case study</li> </ul> | |||
| Neural Networks | 00:00:00 | ||
| <ul> <li>Neural network Intuition</li> <li>Neural network and vocabulary</li> <li>Neural network algorithm</li> <li>Math behind neural network algorithm</li> <li>Building the neural networks</li> <li>Validating the neural network model</li> <li>Neural network applications</li> <li>Image recognition using neural networks</li> </ul> | |||
| Session - 4 Random Forest, Boosting and NLP | |||
| Random Forest and Boosting | 00:00:00 | ||
| <ul> <li>Introduction</li> <li>Ensemble Learning</li> <li>How ensemble learning works</li> <li>Bagging Building models using</li> <li>Bagging Random Forest algorithm</li> <li>Random Forest model building</li> <li>Finetuning parameters and model selection</li> <li>Boosting Introduction</li> <li>Boosting algorithm</li> <li>GBM Model building and Validating in python</li> </ul> | |||
| Text Mining and NLP | 00:00:00 | ||
| <ul> <li>What is text mining</li> <li>The NLTK package</li> <li>Preparing text for analysis</li> <li>Step by step guide to prepare text data</li> <li>Text summarisation</li> <li>Sentiment analysis</li> <li>Naïve bayes technique for sentiment analysis</li> <li>Movie review sentiment analysis</li> </ul> | |||
| Session - 5 Introduction to TensorFlow and CNN | |||
| Deep Learning tool – Tensor Flow and Keras (Wrapper on Tensor Flow) | 00:00:00 | ||
| <ul> <li>Deep Learning tool TensorFlow</li> <li>Comparison with python libraries</li> <li>Introduction to TensorFlow</li> <li>TensorFlow made easy with Keras</li> <li>Setting up Keras</li> <li>Keras on TensorFlow</li> <li>Keras Basic Commands</li> </ul> | |||
| CNN | 00:00:00 | ||
| <ul> <li>CNN Introduction</li> <li>Issues with Standard ANN</li> <li>Kernel filter</li> <li>Convolution layer</li> <li>Pooling layer Fully connected dense layer</li> <li>Weights and number of parameters</li> <li>Back propagation</li> <li>CNN Model building</li> <li>CNN Hyperparameters</li> <li>CNN tips and tricks</li> </ul> | |||
| Case Studies | |||
| List of Case Studies used in the MLP course | 00:00:00 | ||
| <ol> <li> Bank loans data cleaning – Data exploration and cleaning</li> <li>Air passenger prediction and driver analysis -Regression</li> <li>SAT score prediction and driver analysis -Regression</li> <li>E-com Website sales prediction case study -Regression</li> <li>Product sales analysis – Logistic Regression</li> <li>Customer attrition analysis -Logistic Regression</li> <li>Customer Survey Segmentation and Drivers – Decision Trees</li> <li>Internet service provider customer segmentation – Decision Trees</li> <li>Customer attrition analysis – Model selection and cross validation</li> <li>Productivity data -Neural networks</li> <li>Image recognition -Neural networks</li> <li>Car Sensor IOT data -Random forest</li> <li>E-com product classification - Boosting</li> <li>Movie review data – Sentiment Analysis - NLP</li> <li>Restaurants review data analysis – NLP</li> <li>News group review text classification – NLP</li> <li>Object Recognition problems – CNN</li> <li>Digit recognizer – CNN</li> </ol> | |||
