Machine Learning

Learn how to create machine learning algorithms in Python with Research Experts.

What you'll learn
  • Master Machine Learning on Python
  • Use Machine Learning for personal purpose
  • Handle advanced techniques like Dimensionality Reduction
  • Handle specific topics like Reinforcement Learning, NLP and Deep Learning
  • Make powerful analysis
  • Make accurate predictions
  • Build an army of powerful Machine Learning models and know how to combine them to solve any problem
Machine Learning

Machine Learning

Automatic Learning - As the name suggests, science is about learning the machine through previous experiences. It is no less surprising that science has progressed to the limit where a computer is learned over time, but to mark your existence in the world as such, you must know how to teach your machine.

Course Content

Section A: Introduction of Machine Learning
  • Introduction to machine learning
  • Understanding the need
  • Understanding Big data and machine learning
  • Running machine learning under linux platform
  • Introduction to Redhat Enterprise linux
  • Why linux is important for machine learning with respect to future
  • Role of Python and R programming in this domain
  • Basic Introduction of Python syntax and programming logics
  • Deep dive with Supervised , Unsupervised and Reinforcement learning
  • Algo discussion with use case
  • Popular machine learning framework like tensorflow , scikit-learn
Section B: Python Programming
  • Basic of python and why python for machine learning
  • Installation of software on different OS.
  • Understanding basic syntax with data types
  • Number, String, List, Tuple, Dictionary
  • Extracting data from a file
  • Committing your code to GIT
Section C: More about Python Programming
  • Conditional statement and loops
  • Function and modules
  • File handling
  • Creating own modules / library
  • Web scraping with urllib2
  • Grabbing system information from Popen and os library
  • Scanning Network IP & MAC address with loops
  • Introduction to Ipython with jupyter notebook
  • Using jupyter notebook with Ipython & Python
  • UDP Socket programming
  • Exception & Signal handling
  • Making chat program with UDP socket
  • Extending chat programming
  • Introduction to pandas
  • Making data frames with pandas
  • Handling xls & csv files with pandas
  • Loading and extracting existing xls files
Section D: Libraries Used
  • Introduction to Numpy & Matplotlib
  • Managing arrary with numpy
  • Multidimensional array with numpy
  • Unit matrix handling & creating
  • Deleting indexes from matrix
  • Deep dive with Matplotlib
  • Drawing general purpose graphs
  • Graphs with mathematics
Section E: Machine learning Techniques
  • Advice of applying machine learning
  • Machine learning System Design
  • Decision Tree algo deep dive
  • Training your machine with real time datasets
  • Deep dive with UCI
  • Lab session for loading data from different apis
  • Detecting data from numpy and converting for training and testing data
  • Exercise with ML and others framework
  • Introduction to iris datasets
  • Understanding iris datasets
  • Modifying and loading with scikit-learn
  • Separating data with numpy
  • Training classifier
  • Algo data process view
Section F: Supervised learning
  • Regression
  • Classification
  • Case study learning in regression
  • Case study learning in classification
  • Comparing the result of Decision Tree and Navie Bayes algo
  • Graphploting with Matplotlib for comparison
Section G: Deep Learning for image search and Recognition
  • Searching for image
  • Loading image with cloud library
  • Registering image for training model
  • Browsing image from url and local
  • Training image datasets
  • Recognition of different images to detect face
  • Deregistering images from cloud library
  • Pushing code to github for automatic updates
Section H: Live Image Processing and ML
  • How image search is going to work
  • Taking pictures with python for image processing
  • Loading and registering images
  • Face detection with android sdk
  • Machine learning with Amazon cloud
  • Image processing with amazon cloud
  • Introduction to Reinforcement learning
  • An example implementation of reinforcement learning
Section I: Neural Networks Analysis
  • Understanding neural networks
  • Data learning and machine predictions
  • Neural networks real understanding
  • Neural network implementation with real datasets
Projects:
  • Face and expression recognition based Smart Music Player and Communication System using ML Algo’s
  • Smart Machine Learning System

Coming Soon...

Pre-Requesties
  1. 1. Basic Knowledge of Python.
  2. 2. Should have laptop.
Course Outcomes!!
  1. 1. Writing tip to showcase skills you have learnt in the course.
  2. 2. Mock interview practice and frequently asked interview questions.
  3. 3. Career guidance regarding hiring companies and open positions.
  4. 4. Certificates
  5. 5. Opportunity of Research Internship