Have any question? +91 92 4658 2537 info@algorithmica.co.in
Edua

Advanced Data Science/Analytics + Project

This course is an extension of basic data science course, and focus upon deep learning algorithms in data analysis. It allows you to understand state-of-the art research in analyzing image, text, video and voice data at very practical level.

Category: Data Analytics

  • Details
  • Objectives
  • Target Audience
  • Syllabus

Technical Details

Duration 60 Hours
Prerequisites Passion & Interest towards Data Engineering
Class Room Course Available
Video Course Unvailable

Upon successful completion of Data Science/Analytics course, participants will be able to:

  • Understand the power of neural networks
  • Understand how to automate feature extraction
  • Apply deep learning algorithms to practical problems
  • Analyze text, video and voice data
  • People under any of these following categories

  • Anyone who is passionate about understanding the world and intends to impact world with technology
  • Developers at all levels
  • BI professionals
  • DataWarehousing Professionals
  • Team Leads
  • Analytics Managers
  • Business Managers
  • 1. Review of data analytics life cycle
  • Data analytics life cycle
  • Summary of per-phase techniques
  • 3. Creational Patterns
  • Factory Method
  • Abstract Factory
  • Builder
  • Prototype
  • Singleton
  • Practical Applications
  • Assignment
  • 5. Behavioral Patterns
  • Command
  • Mediator
  • Chain of Responsibility
  • Iterator
  • Memento
  • Observer
  • State
  • Strategy
  • Template Method
  • Interpreter
  • Visitor
  • Practical Applications
  • Assignment
  • 7. Deep neural networks for machine learning
  • Neural network vs Deep neural network
  • Deep learning algorithms
  • Sparse coding
  • Deep belief networks
  • Deep sparse auto encoders
  • Speeding up deep learning: GPU based learning
  • 9. Deep learning frameworks
  • Theano
  • Caffe
  • Torch
  • TensorFlow
  • 11. Applying deep learning approaches for image based analytics
  • Deep networks for image analysis
  • Kaggle Problem:Detecting cats & dogs
  • Kaggle Problem:Face recognition
  • 2. Introduction to deep learning & unstructued data analysis
  • Types of unstructured data
  • Use cases for unstructured data analytics
  • How do you handle unstructured data for classification and regression analytics?
  • Nature of features in image, text, voice, audio & video data
  • What is deep learning?
  • Why do we care about deep learning now?
  • Benefits of deep learning
  • Limitations of deep learning
  • Applications of deep learning
  • 4. Pre-deep learning approaches for image based analytics
  • Image preprocessing
  • Handicrafted Feature extraction for image
  • Feature extraction
  • Color
  • SIFT
  • HOG
  • Edges
  • Keypoints
  • Bag of word feature representation
  • Bag of word with spatial pyramids
  • Part based feature representation
  • Solving Kaggle problem: Detecting cats & dogs
  • 6. Neural networks for machine learning
  • Modelling human brain learning to machines
  • Idea of neuron
  • Activation functions
  • Concept of neural network
  • Perceptron
  • Perceptron model
  • Perceptron learning
  • Multi-layer neural network
  • Multi-layer NN model
  • NN learning
  • Why are neural networks special?
  • Neural networks for supervised learning
  • Neural networks for unsupervised learning
  • 8. Practical deep learning networks
  • Fully connected deep networks(DNN)
  • Convolutional deep networks(CNN)
  • Recurrent deep networks(RNN/LSTM)
  • 10. Applying deep learning approaches for text based analytics
  • Deep networks for text analysis
  • Kaggle Problem:Named entity recognition
  • Kaggle Problem:Sentiment analysis on movie reviews