Skip to main content

what i learned from Machine Learning Hackathon?

https://cdn-images-1.medium.com/max/1600/1*dE4F_nf8P60V2baaaOxgLQ.jpeg

First i will tell you what my topic is all about, my idea is to integrate AI with Restaurant based app

okay what is the big deal?
  • Using the bills we can predict how much raw material can be bought so we can minimize food wastage
  • We can also able to identify customer pattern which are more likely to buy after x item 
  • Last thing based on the feedback we can find mistake in us and improve it
Let's see what are the algorithm we are planned to use

Avoid Food Wastage: Using Time Series algorithm

For identify Customer pattern : FP Mining ( Frequent Pattern Mining ) is an algorithm that will predict the y after x items bought but we need to train it with existing data

Feedback : Sentimental analysis which separate the positive and negative comments then we will apply another algorithm to predict negative comments about which food item using naive bayes we give keywords such as Briyani,Rice.. the algorithm check whether it is available or not and how many times the keyword used

This what we planned,but we cannot complete the hack on time

Just explained our ideas to the people

Other cool project in the hackathon are
  • Chat Summarizer - Which learn to summarize the chat and present you with important message 
      • Usecase: when you have more than 60+ message most of them avoid reading it this project help them to read it 
  • Malware detection - This uses Navie bayes algorithm to learn malware detection 
  • Fill Form - You can fill a form just taking a picture of the data what you need to enter.Algorithm used - OCR (Optical Character Recognition) , address parsing , phone parsing 
  • Build a Form - Using OCR(Optical Character Recognition) you can able to construct a form 
  • BlackMirror - The project which is similar to TLDR in which you can paste the policy agreement it will summarize and tell you the essential thing in short and crisp manner
  • Markovian Chains for In-product Help
and lot more that's all i can remember

Lot of fun and cool experience

Attend lot of Hackathon find new friends and learn new things

Comments

Post a Comment

Popular posts from this blog

My experience in iOS Hackathon

This is my second hackathon, my first hackathon was on machine learning if you want to check out that article by following the below link https://thangaayyanar.blogspot.com/2018/02/what-i-learned-from-machine-learning.html So let's get started First let us discuss about the idea of what we are trying to achieve in this hackathon. From the above image you can able to know that we are going to recognize text from the image and use it to do find which field it is.  we separated this idea into three modules Identify the region Recognize the text  Field classification Module I : Identify the region To identify the selected region we used Vision framework ( ML framework provided by apple to detect the object ). The vision framework give us the boundary of the text region ( i.e frame - x,y,width,height ).  Then using the above region we crop the selected region and pass it to the next module. Module II : Recognize the text To recognize the text we ...
Post a Comment
Read more

Docker

Docker is used to run software packages called "containers". Containers are isolated from each other and bundle their own tools, libraries and configuration files; they can communicate with each other through well-defined channels                                                                                                --Wikipedia  I have already written a article about the containers you can check out in here https://thangaayyanar.blogspot.com/2018/06/containers.html This time, let's learn more about docker engine how we can use this. The important things we need to know in docker are Docker Image:  The container can be created with the help of Image. The Image file consists of code, libraries, environment variable...
Post a Comment
Read more

BlockChain

As the name says chain of block Now what is a block?       A block typically contains a  cryptographic hash of the previous block,  a timestamp transaction data    Where it is used?      It is the backbone of cryptocurrency i.e it ensure the security and integrity of data. The usage doesn't stop here well blockchain are resistant to modification of the data. so it can used in Bank Identity verification Hospital records and much more   How it ensures security and integrity of data? Block added to the chain, contain the hash ( result obtained from hash algorithm such as MD5,SHA) of the previous block so changes in one block lead to mismatch. Proof of work algorithm - Adding a node in the block chain require validation whether the new block is valid or not which is done my miner if they find the valid hash they will be rewarded How to do one?      The most interesting part ...
Post a Comment
Read more