# neelesh sinha

## SOFTMAX ACTIVATION FUNCTION INTUTION

SoftMax is a non-linear activation function an activation function is a non-linear transformation that we do over the input before sending it to next layer of neuron output. Suppose if we have a neural network trained to predict based on some classes (A, B, C, D…) and use SoftMax layer as output the SoftMax function will predict probability (P1, P2, P3, …

## UNDERSTANDING THE INTUTION BEHIND TAN-H FUNCTION

Introduction  In Tan-h (Tangent hyperbolic function) which is non-linear when you pass any value from – infinity to + infinity it will always take up values between –1 and +1 the plot below shows how a tan-h function looks like. At – infinity the value of tan h becomes –1 and at infinity it becomes 1. The tanh function is …

## Cost vs Loss Function in Regression

INTRODUCTION Both Cost and Loss function are also known as error functions.  Loss function is a method of evaluating “how well your algorithm models your dataset”. If your predictions are totally off, your loss function will output a higher number. If they’re pretty good, it’ll output a lower number. As you tune your algorithm to …

## QUICK GUIDE TO RUN VS-CODE ON GOOGLE COLAB

Today we will see how we can use vscode IDE and execute code using google’s resources from google colab. By using an open source library called (link –  colabcode) created by Kaggle Grandmaster Abhishek Thakur.  The colabcode python script has different parametersdefined like port number, password, connection etc. That readily installs codeserver on your local machine and starts a server using ngrok which is an cross-platform application that enables …

## DEVELOP A CUSTOMER SEGMENTATION TO DEFINE MARKET STRATEGY USING DATA SCIENCE FOR BUSINESSES.

Libraries used –  NumPy  pandas  matplotlib  Stats-models  Sklearn  Notebook – google colab  Link – Customer segmentation notebook  ADVANCED DATA PREPARATION  Monthly average purchase and cash advance amount  Purchases by type (one-off, installments)  Average amount per purchase and cash advance transaction,  Limit usage (balance to credit limit ratio),  Payments to minimum payments ratio.  DATA CLEANING  First, I have …

## Multi-class image classification using Deep learning -implementation in TensorFlow keras.

A deep learning algorithm model mimics how the human brain functions and operates with the help of neural networks which is a structure to learn complex patterns. In Computer vision we use large image datasets to train a neural network which helps us classify unseen images/specifications by smallest amounts of computation time and much less …

## HANDS ON GUIDE TO GENERATE CUSTOM TENSORFLOW LITE MODEL USING TENSORFLOW/KERAS AND QUANTIZATION FOR EDGE DEVICES

INTRODUCTION Tensorflow Lite is a cross platform production ready framework for deploying machine learning models on mobile devices and embedded systems.Tensorflow lite models operate on low latency optimization which can process high volume of data with minimum delay and since the model is deployed on an edge device like a smartphone it offers a good …