Machine Learning detailed syllabus for Cloud Computing & Big Data (CC) for 2021 revision curriculum has been taken from the SITTTRs official website and presented for the Cloud Computing & Big Data students. For course code, course name, number of credits for a course and other scheme related information, do visit full semester subjects post given below.
For Cloud Computing & Big Data 5th Sem scheme and its subjects, do visit Cloud Computing & Big Data (CC) 5th Sem 2021 revision scheme. The detailed syllabus of machine learning is as follows.
Course Objectives:
For the complete syllabus, results, class timetable, and many other features kindly download the iStudy App
It is a lightweight, easy to use, no images, and no pdfs platform to make students’s lives easier.
.
Course Outcomes:
On completion of the course, the student will be able to:
- Describe Concept, Types and Challenges of Machine Learning Systems
- Elaborate Prediction and Clustering Techniques
- Discuss Classification Techniques
- Summarize Artificial Neural Network
Module 1:
Introduction to Machine Learning, Machine Learning Types- Supervised, Semisupervised, Unsupervised and Reinforcement Learning, Online Vs Batch learning, Instance based vs model based. Machine Learning – Tasks- Prediction, Classification and Clustering- Applications of each. Training data, Test data, K-fold cross validation. Model parameters, Hyperparameters. Performance Evaluation Metrics – Confusion matrix, Accuracy, Precision, Recall, Specificity, AUC, F-Measure Prepare the Data for Machine Learning Algorithms- Data preprocessing- Data Cleaning, Feature Scaling-Standardization, Normalization. Dimensionality reductionPrincipal Component Analysis(PCA). Machine Learning Challenges- Small dataset, nonrepresentative data, Poor quality of data, Irrelevant Features, Overfitting, Underfitting, Testing and Validation, Hyperparameter Tuning and Model Selection
Module 2:
For the complete syllabus, results, class timetable, and many other features kindly download the iStudy App
It is a lightweight, easy to use, no images, and no pdfs platform to make students’s lives easier..
Module 3:
Classification- Binary and Multiclass, Logistic Regression- Training and Cost function, Decision boundaries, Softmax Regression, Cross Entropy, Hyperparameters of Logistic Regression model, Advantages and disadvantages of Logistic Regression. Decision Tree- Training and Visualizing Decision Tree, Splitting Criteria, Information gain, Gini Index, Stopping Criteria, Pruning methods, Advantages and disadvantages of Decision tree. RDF- ensemble methods, hyperparameters of RDF- advantages and disadvantages of RDF Support Vector Machine (SVM) – Concept of support vectors, hyper line, and hyperplane, Soft margin and hard margin, Linear and Nonlinear SVM Classification, Outliers, Polynomial- RBF kernel, Similarity Features, Hyperparameters of SVM model, Advantages and disadvantages of SVM classifier.
Module 4:
From Biological to Artificial Neurons, Logical computations with neurons, The Perceptron, Multilayer perceptron(MLP), Backpropagation, Regression and classification MLPs, Fine-tuning Neural network hyperparameters Deep Learning Concepts, Convolutional Neural Network (CNN), Filters, Convolution and Pooling operation, Vanishing/exploding gradient problems, activation function, Applications of CNN Transfer Learning Concepts- Introduction to Pretrained CNN architectures- LeNet-5, AlexNet, GoogleNet, VGG, ResNet or Xception
Text Books:
For the complete syllabus, results, class timetable, and many other features kindly download the iStudy App
It is a lightweight, easy to use, no images, and no pdfs platform to make students’s lives easier..
Reference Books:
- Pratap Dangeti, “Statistics for Machine Learning”, Packt
- Jiawei Han, Micheline Kamber, Jian Pei, ” Data Mining Concepts and Techniques” Third Edition, (MK)Morgan Kaufmann – Elsevier
- Josh Hugh Learning, “Python Machine Learning”
Online Resources
For the complete syllabus, results, class timetable, and many other features kindly download the iStudy App
It is a lightweight, easy to use, no images, and no pdfs platform to make students’s lives easier..
For detailed syllabus of all other subjects of Cloud Computing & Big Data (CC), 2021 revision curriculum do visit Cloud Computing & Big Data 5th Sem subject syllabuses for 2021 revision.
To see the syllabus of all other branches of diploma 2021 revision curriculum do visit SITTTR diploma all branches syllabus..
To see the results of Cloud Computing & Big Data (CC) of diploma 2021 revision curriculum do visit SITTTR diploma Cloud Computing & Big Data (CC) results..
For all Cloud Computing & Big Data academic calendars, visit Cloud Computing & Big Data all semesters academic calendar direct link.