• No products in the cart.

203.5.7 The Neural Network Algorithm

Steps of neural network algorithm.

In previous section, we studied about Neural Network Intuition

In all previous posts we progressed to this part. We will breakdown the steps how a neural network starts and ends.

The Neural Network Algorithm

  • Step 1: Initialization of weights: Randomly select some weights .
  • Step 2 : Training & Activation: Input the training values and perform the calculations forward.
  • Step 3 : Error Calculation: Calculate the error at the outputs. Use the output error to calculate error fractions at each hidden layer
  • Step 4: Weight training: Update the weights to reduce the error, recalculate and repeat the process of training & updating the weights for all the examples.
  • Step 5: Stopping criteria: Stop the training and weights updating process when the minimum error criteria is met.

Randomly Initialize Weights

Training & Activation

Error Calculation at Output

Error Calculation at hidden layers

Calculate weight corrections

Update Weights

Stopping Criteria

The next post is a Demo on Neural Network Algorithm.


Statinfer derived from Statistical inference. We provide training in various Data Analytics and Data Science courses and assist candidates in securing placements.

Contact Us


+91- 9676098897

+91- 9494762485


Our Social Links

© 2020. All Rights Reserved.