Statinfer

204.5.6 Neural Network Intuition

Neural network at a glance.

Link to the previous post : https://statinfer.com/204-5-5-practice-implementing-intermediate-outputs-in-python/

Before going further into neural network algorithm, we need to understand and break down how the algorithm is working.

Neural Network Intuition

Final Output

y=out(h)=g(Wjhj)hj=out(x)=g(w(jk)xk)

y=out(h)=g(Wjg(w(jk)xk))

  • So h is a non linear function of linear combination of inputs – A multiple logistic regression line.
  • Y is a non linear function of linear combination of outputs of logistic regressions.
  • Y is a non linear function of linear combination of non linear functions of linear combination of inputs.
  • We find W to minimize ni=1[yig(Wjhj)]2
  • We find  Wj and wjk to minimize ni=1[yig(Wjg(w(jk)xk))]2
  • Neural networks is all about finding the sets of weights  Wj and wjk using Gradient Descent Method.

The Neural Networks

  • The neural networks methodology is similar to the intermediate output method explained above.
  • But ,we will not manually subset the data to crate the different models.
  • The neural network technique automatically takes care of all the intermediate outputs using hidden layers.
  • It works very well for the data with non-linear decision boundaries.
  • The intermediate output layer in the network is known as hidden layer.
  • In Simple terms, neural networks are multi layer nonlinear regression model.
  • If we have sufficient number of hidden layers, then we can estimate any complex non-linear function.

Neural Network and Vocabulary

Why are they called hidden layers?

  • A hidden layer “hides” the desired output.
  • Instead of predicting the actual output using a single model, build multiple models to predict intermediate output
  • There is no standard way of deciding the number of hidden layers.

Algorithm for Finding Weights

  • Algorithm is all about finding the weights/coefficients
  • We randomly initialize some weights; Calculate the output by supplying training input; If there is an error the weights are adjusted to reduce this error.

The next post is about the neural network algorithm .

Link to the next post : https://statinfer.com/204-5-7-the-neural-network-algorithm/

0 responses on "204.5.6 Neural Network Intuition"

Leave a Message

Blog Posts

Hurry up!!!

"use coupon code for FLAT 30% discount"  datascientistoffer        ___________________________________      Subscribe to our youtube channel. Get access to video tutorials.                

Contact Us

Statinfer Software Solutions#647 2nd floor 1st Main, Indira Nagar 1st Stage, 100 feet road,Indranagar Bangalore,Karnataka, Pin code:-560038 Landmarks: Opp. Namma Metro Pillar 48.

Connect with us

linkin fn twitter g

How to become a Data Scientist.?

top