What you'll learn

  1. Understand the intuition behind multiple Neural Networks
  2. Understand the intuition behind Convolutional Neural Networks
  3. Understand the concepts behind Auto Encoders
  4. Build and train deep neural networks, identify key architecture parameters, implement vectorized neural networks and deep learning to applications
  5. Train test sets, analyse variance for DL applications, use standard techniques and optimization algorithms, and build neural networks in TensorFlow


  Introduction to Deep Learning

  • Introduction and history of Deep Learning
  • Basic structure of neuron and MLP
  • Optimisers-Gradient Descent
  • Back Propagation
  • Activation functions in depth
  • Where to use which activation
  • Optimisers in depth 1
  • Optimisers in depth 2
  • Weight Initialiser
  • Losses in Neural networks
  • Notes link

  Practical case of MLP

  • Handwritten number recognition using Keras part 1
  • Handwritten number recognition using Keras part 2 and Google Colab
  • Intro to tensorflow 1x
  • MNIST using tensorflow 1x

  Convolution neural networks

  • Understanding edge detection
  • Introduction to convolution
  • What is pooling
  • Backpropagation in CNN
  • Methods to avoid overfitting
  • ALexNet
  • VGGNet
  • InceptionNet
  • ResNet
  • Later versions of InceptionNet
  • Later versions of ResNet
  • Transfer Learning

  Practical Cases of CNN in image classification

  • MNIST using CNN
  • Transfer Learning Project Cats vs Dogs Classification

  Object Detection

  • Basics of Object Detection
  • RCNN Architecture
  • Fast RCNN Architecture
  • Faster RCNN Architecture
  • SSD Architecture
  • YOLO Architecure
  • Later YOLO architectures

  Implementing Object Detection

  • Tensorflow Object Detection
  • TFOD on custom data
  • TFOD on custom data using Google Colab
  • YOLO on pretrained data
  • YOLO training on custom data in local system.
  • YOLO training on custom data in Google Colab.

  Segmentation using CNNs

  • Mask RCNN

  Natural Language Processing

  • NLTK Library text preprocessing
  • Text Processing using TextBlob
  • Text Preprocessing using SpaCy
  • Frequency based Embedding


  • AutoEncoders and types
  • Understanding Word2Vec algorithm

  Sequence Based Model

  • RNN architecture
  • LSTM architecture
  • GRU architrcture


  • Sentiment analysis using LSTM
  • Image Captioning
  • Text OCR
  • Speech to Text
  • Text to Speech