Data Scientist @Philips. Passionate about ML,Statistics & hiking. Come say 👋LinkedIn:https://www.linkedin.com/in/pradeep-adhokshaja-5b512095/

In the previous posts, we covered the following

- Introduction to CNN
- Convolution Operation
- ReLU function, Max pooling function & Softmax Function.
- Back Propagation Through Fully Connected Layers
- Back propagation through convolutional output layer, max pool layer & convolutional filter

- Getting the training and testing data

*'''*

*Input functionality*

*'''*

import pandas as pd

import numpy as np

data = pd.read_csv('../input/Kannada-MNIST/train.csv')

data = data.sample(frac=1)

*#print(int(data.shape[0]/2))*

data_first_half = data.head(30000)

data_second_half = data.tail(30000)

*### get 100 data points *

*### making sure that the data is balanced*

tmp = pd.DataFrame()

for label **in** range(10):

if label==0:

tmp = data_first_half[data_first_half['label']==label].head(600)

else…

In the previous blog posts , I tried to explain the following

- Introduction of CNNs and Data Processing
- The Convolution Operation
- ReLU, Maxpooling and Softmax
- Backpropagation through fully connected layers

In this post, I will try to cover back propagation through the max pooling and the convolutional layers. We had worked our way through calculating the gradients till the first fully connect layers. Let’s re-visit the architecture once more through the following hand drawn image

In the previous sections , we covered

In the 4th part of this series on CNN, we will try to cover back propagation through the fully connected layers in the network.

Just to recap, our network has the following set of operations in order from start to finish

*Let N be the total number of images*

- It accepts an input matrix of size (
**N,1,28,28**) - This is then followed by the first convolutional filter of size (
**2,1,5,5**) - The convolution operation results in the matrix transforming to the size (
**N,2,24,24**). …

In the previous posts, I covered the following topics

In the third part of the series, I will cover three functions that will be used during forward propagation.

- ReLU
- Maxpooling
- Softmax

The ReLU function is a non-linear activation function which filters out negative values.

ReLU function applied in a neural network does not face problems such as vanishing gradients. ReLU function result in non zero gradients for positive values , unlike saturating functions such as sigmoid.

Given that the differential of a ReLU function is a constant, lesser time is need to compute the…

In the previous post, I gave a brief introduction to convolutional neural networks together with code for converting CSV data of flattened images to their actual shapes. In this post, I will try to explain the following

- Convolution operation
- Why is convolution needed?
- Implementing it using NumPy

In the context of ConvNets, the convolution operation involves **calculating the dot products between a fixed matrix and different regions of an image**. The fixed matrix is also known as the **convolutional filter**. The different regions of the image have the same shape as the fixed matrix. …

Convolutional Neural Networks (CNNs) are a class of neural networks that work well with grid-like data, such as images. They extract useful features from images to make the image recognition process more robust. These networks are inspired by the results of experiments conducted by **David Hunter Hubel & Torsten Nils Wiesel **who observed different neural activity in the cat’s brain in response to different orientations of a straight line.

The first convolutional neural network was the Neocognitron, implemented by Dr Kunihiko Fukushima in 1980. This system used a hierarchical structure to learn simple & complex features of an image. …

Neural Networks are a group of algorithms that consist of computational nodes, that take in an input, perform mathematical computations on it, and return an output. Complex mathematical operations can be performed based on the functions we choose to use on these computational nodes. These functions are also called “activations”.

Neural Networks can be used for the purpose of estimating real values(regression) ,categorical variables (classification) and generating data (generative models).

The Fashion MNIST Data set consists of 60,000 28 pixel by 28 pixel black and white images created by Zalando Research . Each image belongs to one of the following…

When working on a regression/classification problem involving data with a large number of features, we are often susceptible to the “Curse of Dimensionality”. As we keep increasing the number of features, we will reach a point where our regressor/classifier fails to perform well on test data.

This “Curse” can be avoided by reducing the number of features. This practice is called **Dimensionality Reduction. **…

The Human Activity recognition dataset consists of information collected from embedded accelerometer and gyroscopes while performing tasks like WALKING, WALKING_UPSTAIRS, WALKING_DOWNSTAIRS, SITTING, STANDING, and LAYING. The experiments have been carried out with a group of 30 volunteers within an age bracket of 19–48 years, with video evidence so as to label the observations correctly. The measurements result in a 561 feature vector. The data set for the same can be found at Kaggle.

The aim of this project is to effectively predict the observed activities multinomial logistic regression as the predicting algorithm. R will be used in the analysis.

Multinomial…

Zomato is a restaurant search application which was founded in 2008. It currently operates in 23 countries.

I will be using the `tidyverse`

library here for data munging and the `ggplot2`

package for data visualization.The data set has been imported using the `read.csv()`

function. The data set for this post can be found on Kaggle.

library(tidyverse)

library(ggplot2)

library(ggridges)

library(tidytext)zomato = read.csv('zomato.csv')zomato %>%

str()

Where are these restaurants located?

To find out the locations of the restaurant, I have used the world map. Each point on the world map is colored according to the price range they fall in.

`…`