Machine learning is covered in the field of computer science under the practices of artificial intelligence. It generally uses statistical techniques by providing the ability to learn and executive the data without being programmed explicitly.

Course Curriculum

No curriculum found !

INTRODUCTION

Machine learning is systematic learning approach to give ability to the computer programs to ‘learn’ with Data. There are many methods and ways to learn machine learning. Learning ‘ML’ require us to understand Python, R and other tools such TensorFlow. We would use an incremental way to learn ML. The classes are designed in accordance to the latest industry standards and are backed by lab practicals.

Course Description

ML course is designed in keeping the needs of the industry and classes will be taken by industry experts. Machine Learning is engine behind the facial recognition to fraud detection and driverless car. This course will help the student to learn the key concepts of Machine learning such as, automatic analyzation of large data set. Data preprocessing, Basic statistics, Regression and Classification. We would be offering free Python course with this course.
After the completion of the course you would possess skill to create supervised and unsupervised machine learning models. Gain practical knowledge and hands on. Gain deeper understanding about vector machines, kernel SVM, naive bayes, decision tree classifier, random forest classifier, logistic regression, K-nearest neighbors, K-means clustering and more.
You would understand about Machine Learning and apply machine learning techniques in day to day life. You would be able to grasp better theoretical concepts, and would be able to model and develop models, using a wide variety of machine learning algorithms like deep learning.

Key Features

CURRICULUM

1. What is Machine Learning?
2. Supervised Learning
3. Unsupervised Learning
1. Apache Mahout,
2. Tensorflow,
3. MLPACK
1. Installing Python
2. Execute Python program
3. Writing your first program
4. Python keywords & Identifiers
5. Python Indentation
6. Getting input output
7. Variables
8. Numbers
9. Strings
10. Lists
11. Tuple
12. Dictionary
13. Control Flow Statements
14. While loop
15. for loop
16. break & continue statement
17. pass statement
18. Calling a function
19. Function arguments
20. Built-in functions
21. Scope of variables
22. Passing function to a function
23. Decorators
24. Lambda
25. Module
26. Import a module
27. Command line arguments using sys module
28. Standard module-OS
29. Introduction about classes & objects
30. Creating a class & object
31. Inheritance
32. Methods Overriding
33. Data hiding
34. Writing data to a file
35. Reading data from a file
36. Additional file methods
37. Working with files
38. Working with Directories
1. Model Representation
2. Cost Function
3. Gradient Descent
4. Multiple Features
5. Gradient Descent For Multiple Variables
6. Features and Polynomial Regression
7. Normal Equation
1. Setting up opencv
2. Loading and displaying images
3. Applying image filters
4. Tracking faces
5. Face recognition
1. What is Hadoop?
2. MapReduce
3. File handling with Hadoop
1. Hypothesis Representation
2. Decision Boundary
3. Cost Function
4. Simplified Cost Function and Gradient Descent
5. Multiclass Classification: One-vs-all
6. Logistic regression
1. Gaussian process regression,
2. Support vector machines,
3. Random forests,
4. Information fuzzy networks(IFN),
5. Bayesian statistics,
6. Decision tree algorithms,
7. Linear classifier,
8. k-nearest neighbors algorithm(KNN),
9. Association rule learning algorithms such as Apriori and Eclat
1. Hierarchical clustering,
2. Fuzzy clustering,
3. k-means clustering,
4. BIRCH
5. Anomaly detection,
6. EM algorithm
1. Feature selection,
2. Feature extraction,
3. Principal component analysis(PCA),
4. Principal component regression(PCR),
5. Linear discriminant analysis(LDA),
6. Factor analysis,
7. Multidimensional scaling(MDS),
1. The Problem of Overfitting
2. Cost Function
3. Regularized Linear Regression
4. Regularized Logistic Regression
1. Model Representation
2. Examples and Intuitions
3. Multiclass Classification
4. Cost Function
5. Backpropagation Algorithm
6. Backpropagation Intuition
7. Gradient Checking
8. Random Initialization
1. Introduction to Convolutional Neural Networks (CNN)
2. Convolutional Autoencoders
3. Deep CNN
4. Image Searching

Projects

Study of pharma products
Study of World weather patterns

FAQs

College students, Working professionals, Developers, Analytical Managers, Business Analysts, Architects, Analytics Professionals, Graduates and Experienced Professionals.
We cover 2 major projects
Yes all the sessions are classroom based.

Course Reviews

Template Designed by © Zenways.Io All rights reserved.
Skip to toolbar