aimodules

AI

Understand basics of git, learn to use essential git commands & learn markdown documentation format :

  • Overview of git (Diagram needed here with visuals of basic terminologies)
  • Git commands : git clone, git config, git add, git status, git commit, git push, git pull, git branch, git checkout, and git merge
  • Git Workflow
  • Git Practice
  • Assignment : Summarise Git learning in Markdown format.

Learn complex problem solving skills :

  • Data Structures - Arrays, Linked List (SLL, DLL), Stack, Binary Search Tree, Hash Table, Dictionary
  • Time Complexity, Space Complexity.
  • Assignment : Solve a problem demonstrating above abilities : Peer review for best in class.

Learn to implement python programming concepts :

  • Datatypes : Containers, Lists, Dictionaries, Sets, Tuples, Functions, Classes
  • Numpy: Arrays, Array indexing, datatypes, Array math, Broadcasting
  • Jupiter Notebooks: Creating notebooks, Typical workflows
  • Assignment : Exercises

Understand basic machine learning algorithms :

  • Types of ML Algorithms
  • Random Forest Algorithm
  • SVM
  • KMeans
  • KNN
  • Naive Bayes

Understand architecture and working principles of Deep Neural Network :

  • DNN architecture
  • Working Principles of DNN
  • Forward Propogation
  • Backward Propogation , Activation functions
  • Important Terminologies : Epoch, Iteration, Batch_size, cost , learning rate , gradient descent.

Learn Basics of OpenCV and Image Processing :

  • OpenCV - Basics
  • OpenCV - Basics - Reading/Writing an Image
  • OpenCV - Image Processing - Accessing Pixels, Transform Color Spaces
  • OpenCV - Image Processing - Image Transforms
  • OpenCV - Image Processing - Scaling and Cropping
  • OpenCV - Image Processing - Filtering Images
  • OpenCV - Image Processing - Histograms

Learn Advanced functions of OpenCV used for AI :

  • OpenCV - Contour detection
  • OpenCV - Thresholding
  • OpenCV - Features detection, extraction and matching
  • OpenCV - Object Detection
  • OpenCV - Motion and Tracking

Understand basic architecture and working principles of CNN :

  • CNN Architecture
  • Working Principles of CNN
  • Introduction to CNN layers

Understand CNN layers in depth :

  • Deep study of CNN layers
  • Master a tool : A framework : To design CNN layers
  • Building CNN architecture

Understand and implement transfer learning :

  • What is transfer learning ?
  • Freezing layers
  • Determining layers to retrain
  • Model training

Understanding convolutional neural network layers in depth :

  • Architecture Overview
  • ConvNet Layers :
    Convolution layer
    Pooling Layer
    Normalization Layer
    Fully-connected layer
    Converting fully-connected layers to convolution layers
  • ConvNet Architecture :
    Layer Patterns
    Layer Sizing Patterns
  • Case Studies : (LeNet / AlexNet / ZFNet / GoogLeNet / VGGNet)
  • Computational Considerations

Align student to understand industry ready products :

  • Research paper study about chosen application
  • Deep study top 3 methods to understand working principles
  • Implementation
  • Tuning of model using hyper-parameters

Understand Tensorflow basics :

  • Tensors
  • Tensor : types, rank, shape
  • Constants, Variables, Placeholders, Graph, Session
  • Creating Tensorflow Graph and Session
  • Mathematical operations in tensorflow
  • Eager Execution
  • Practical : A Simple Tensorflow Program

Building a basic CNN model with tensorflow :

  • Understanding CNN building APIs in tensorflow
  • Building CNN model in tensorflow