Syllabus

  • What is Deep Learning?
  • Why Learn It?
  • What is a real life application of Deep Learning?
  • Introduction to Computer Vision
  • What is Image Data
  • How computer read Image data
  • Basic OpenCV Functions
  • Image Processing using OpenCV and Python
  • Image Segmentation
  • Type of Learning
  • What is a Biological Neuron?
  • Artificial Neural Model
  • Single Layer Perceptron
  • Type of Activation functions
  • Back Propagation Learning
  • Metrics
  • Problems
  • Why Convolutions?
  • Convolution and pooling
  • Strided Convolutions and Padding
  • One Layer of a Convolutional Network
  • Regularization, Batchnorm
  • Deep convolutional models
  • Transfer Learning
  • Problems with Pytorch
  • Why RNN?
  • Sequential Processing
  • One Layer of a Recurrent Neural Networks (RNN)
  • Problem of Long-Term Dependencies
  • Gated Nets (LSTM, GRU)
  • Application Of RNN
  • State of Art Models using RNN
  • RNN with Pytorch
  • Optimization and Deep Learning
  • Convexity
  • Gradient descent and its types
  • Early stopping and momentum
  • Adagrad, Adadelta and Adam
  • Learning Rate Scheduling
  • Image Classification
  • Object Detection
  • Face recognition
  • Image captioning
  • Optical Character Recognition (OCR)

Key Features

End to end case studies
Build your portfolio
Mock interview
Q & A Session
Assignments
Certification and Job assistance

Related Courses