Deep Learning for Intermediate

Deep Learning
13
Mar

Duration:

3 days or 24 hours

Pre-requisites:

  • knowledge on python programming is appreciated
  • Knowledge on Basics of image processing
  • Note 1: Pre-requisites are strictly to be considered for the smooth maneuver of the workshop
  • Note 2: Case studies will be covered in much detail and will be implemented in real time.

Detailed Coverage:

  1. Introduction
    • What does artificial intelligence really mean?
    • Environment Setup for tensorflow
  2. Python Basics
    • Crash Course on Python
  3. Image Basics
    • Loading, Displaying and saving Images.
    •  Drawing Operations.
    • Image Basic operations
    •  Kernals
    • Morphological
    • Operations
    • Gradient &Edge Detection
    • Thresholding
    • Contours
  4. Feature Extraction
    • Color Channel Statistics
    • Color Histograms
    • Local Binary Patterns
    • HOG
    • Key Point Detectors
  5. Machine Learning
    • K-Nearest Neighbors
    • Support Vector Machines
    • Logistic Regression
    • Random forests
    • Case Studies
  6. Introduction to Deep Learning
    • Machine learning Algorithms and primer
    • Why Deep learning is becoming so popular?
    • Introduction to Deep Neural Networks
    • Sneak peek into open source python libraries
  7. Convolution Neural Network
    • The perception Algorithm
    • Multi-layer Network
    • Develop your first neural network using keras
    • Diving deep in to Convolution Neural Network – CNN Primer
    • It is all about dataset!! And How to gather them
  8. CNN Implementation
    • Training your own CNN (Shallow network) for Mnist Dataset
    • Training a Very deep CNN for Mnist Dataset
    • Improving Model Performance with Image Augmentation
    • Object Detection using CNN for CIFAR 10 dataset
  9. CNN Architechures
    • Implementing CNN Architechures
      • LeNet
      • KarpathyNet
      • MiniVGGNet
      • Over Feat Framework
  10. ImageNet architechures
    • State of the art ImageNet algorithms
    • Flower 17 Classification using
      • VGG16
      • VGG19
      • Inception-v3
      • ResNet50
    • Squeeze net CNN a simplified model for remote processor
  11. Case Study
    • Case Study 1 – Emotion Detection
    • Case Study 2 – Age and gender Detection
    • Case Study 3 – Car Model Identification
  12. Best Practices
    • Creating your own state of the art accuracy using Ensemble of features
    • Creating Datasets and Prime

Enroll Now

Course Content

Time: 3 days

Curriculum is empty

Instructor

4.5

2 rating

5 stars
50%
4 stars
50%
3 stars
0%
2 stars
0%
1 star
0%
  • Vikas R

    Great Experience

    I was looking for a program that would provide a strong foundation in coding with an emphasis on the tools and methods used in Data Science. I was excited to get a comprehensive introduction to a number of machine learning methods and theory.
  • Kiran

    "Great Academy for Transitioning to Data Science"

    The academy provided me the training and guidance build a small portfolio of data science projects, so that I was able to secure a job as a Senior Data Analyst at a great company.
Free

Customized, Immersive, Hands-On Driven

Includes

  • Real time virtual classes
  • Pre course reading material
  • Suppliment resources
  • Language: English
  • Certificate of completion

Enroll Now

Your Dream Course Is Only A Step Away





Your Dream Course Is Only A Step Away





Your Dream Course Is Only A Step Away