Skip to main content

Roadmap

complete roadmap to prepare for deep learning

  • Foundational - Introduction to Neural Network, Loss Function, Optimizers - Gradient Descent, SGD, Adagrad, RMSProp, Adam
    • Everyone is using Adam optimizer, since it is able to change the momentum i.e. the learning rate as your training is going on
  • Activation function - ReLU, Sigmoid, Tanh
  • Geoffrey Hinton - inventor of backpropogation algorithm
  • Inputs, weights, bias

Artificial Neural Network (ANN)​

  • Weight Initialization
  • Hyper parameter tuning
  • How to decide, how many number of hidden layers will be there.
  • How to decide on number of neurons should I take in the hidden layer
  • Keras Tuner
  • Auto Keras

Convolutional Neural Network (CNN)​

  • Convolution
  • Image + Video
  • Filters, Strides, Layers
  • Transfer Learning

Recurrent Neural Network (RNN)​

  • NLP
  • Sequence to sequence data
    • Sentence
    • Sales Forecasting
  • Neural language translation
  • HuggingFace, Ktrain

Complete Road Map To Prepare For Deep Learning🔥🔥🔥🔥 - YouTube