Neural Networks

Source: Deep Learning on Medium

Neural networks and deep learning are big topics in Computer Science and in the technology industry, they currently provide the best solutions to many problems in image recognition, speech recognition and natural language processing.

Neural networks provide a ‘good’ parameterized class of nonlinear functions to learn nonlinear classifiers. They are useful for both classification and regression.

Steps in neural network formation:

  1. Pick the network architecture(initialize with random weights)
  2. Do a forward pass (Forward propagation)
  3. Calculate the total error(we need to minimize this error)
  4. Backpropagate the error and Update weights(Backpropagation)
  5. Repeat the process(2–4)for no of epochs/until the error is minimum.
A neural network representing its different layers.

Various Techniques used in neural networks are:

  • Backward propagation
  • Forward propagation
  • Gradient descent
  • Adjustment of weights