In this post we will discuss the math behind a few steps of Neural Network algorithms. Math- How to update the weights? We update the weights backwards by iteratively calculating the error The formula for weights updating is done using gradient descent method or delta rule also known as Widrow-Hoff …

Read More »## 203.5.13 Neural Networks Conclusion

Real World Applications Self driving car by taking the video as input Speech recognition Face recognition Cancer cell analysis Heart attack predictions Currency predictions and stock price predictions Credit card default and loan predictions Marketing and advertising by predicting the response probability Weather forecasting and rainfall prediction Some exaples Face …

Read More »## 203.5.12 Practice : Digit Recognizer

As promised in the first post of the series we will build a Neural Network that will read the image of a digit and correctly identify the number. LAB: Digit Recognizer Take an image of a handwritten single digit, and determine what that digit is. Normalized handwritten digits, automatically scanned …

Read More »## 203.5.11 Hidden Layers and Their Roles

In this post we will understand one of the most important part of a Neural Network : Hidden Layers. We will be able to use this information to control the parameters related to hidden layers. Hidden layers and their role Multi Layer Neural Network The Role of Hidden Layers The …

Read More »## 203.5.10 Local vs. Global Minimum

In previous post we built a Neural Network model and found the accuracy of the model. In this post we will go further into the algorithm again and understand a simple concept of Local and Global Minima. This helps us build a neural network model which works best for us. …

Read More »## 203.5.9 Building a Neural Network in R

Building the Neural Network The good news is… We don’t need to write the code for weights calculation and updating There readymade codes, libraries and packages available in R The gradient descent method is not very easy to understand for a non mathematics students Neural network tools don’t expect the …

Read More »## 203.5.8 Neural Network Algorithm-Demo

In previous post we briefly discussed how the algorithm works. In this post we will implement the algorithm on a simple case. Neural network Algorithm-Demo Looks like a dataset that can’t be separated by using single linear decision boundary/perceptron Lets consider a similar but simple classification example XOR Gate Dataset …

Read More »## 203.5.7 The Neural Network Algorithm

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 …

Read More »## 203.5.6 Neural Network Intuition

Before going further into neural network algorithm, we need to understand and break down how the algorithm is working. Neural Network Intuition Final Output 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 …

Read More »## 203.5.5 Practice : Implementing Intermediate outputs in R

In this post we will learn how to implement the concept of intermediate outputs using R. We will cover many things in this session. Dataset: Emp_Productivity/ Emp_Productivity_All_Sites.csv Filter the data and take first 74 observations from above dataset . Filter condition is Sample_Set<3 Build a logistic regression model to predict …

Read More »