bhuyanamit986/HSE-Introduction-to-deep-learning bhuyanamit986/HSE-Introduction-to-deep-learning

  • Stars
    star
    4
  • Rank 3,304,323 (Top 66 %)
  • Language
    Jupyter Notebook
  • Created almost 5 years ago
  • Updated almost 5 years ago
Twitter logo Share LinkedIn logo Share Facebook logo Share
bhuyanamit986/HSE-Introduction-to-deep-learning
github

bhuyanamit986

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

Here are my assignments that I completed in my course Introduction to Deep Learning by coursera from Higher School of Economics on coursera's environment.

More Repositories

1

Exploratory-Data-Analysis

Here I did EDA on the iris dataset using histograms, scatterplots, probability density function(PDF), cumulative distribution function(CDF), box plots, whisker ports
Jupyter Notebook
9
star
2

KNN-w-o-sklearn

I made my own KNearestNeighbors algorithm to get better intution of the algorithm which outperformed the scikit-learn's official KNeighborsClassifier's performance getting 98.24% accuracy on Breast Cancer Diagnostic Winscoin dataset.
Jupyter Notebook
8
star
3

Spam-Classifier

Spam Classifier Spam detection is one of the major applications of Machine Learning in the interwebs today. Pretty much all of the major email service providers have spam detection systems built in and automatically classify such mail as 'Junk Mail'. In this mission we will be using the Naive Bayes algorithm to create a model that can classify dataset SMS messages as spam or not spam, based on the training we give to the model. It is important to have some level of intuition as to what a spammy text message might look like. Usually they have words like 'free', 'win', 'winner', 'cash', 'prize' and the like in them as these texts are designed to catch your eye and in some sense tempt you to open them. Also, spam messages tend to have words written in all capitals and also tend to use a lot of exclamation marks. To the recipient, it is usually pretty straightforward to identify a spam text and our objective here is to train a model to do that for us! Being able to identify spam messages is a binary classification problem as messages are classified as either 'Spam' or 'Not Spam' and nothing else. Also, this is a supervised learning problem, as we will be feeding a labelled dataset into the model, that it can learn from, to make future predictions.
Jupyter Notebook
7
star
4

MatplotlibTutorials

Here I did some data visualisations with matplotlib.
Jupyter Notebook
6
star
5

Logistic-Regression-from-scratch

I created a logistic regression from scratch and plotted the decision regions to visualise the decision boundary.
Jupyter Notebook
6
star
6

Robust-Regression

Here I worked on reducing the effect of outliers in the boston housing data with the RANdom SAmple Consensus(RANSAC) Algorithm
Jupyter Notebook
6
star
7

Cat-vs-Dog

Here I made my own neural network from scratch during my Neural Networks and Deep Learning course from deeplearning.ai by Andrew Ng. I trained a class vs dog dataset on my neural network and had found accuracy of 80% on evaluation.
Jupyter Notebook
6
star
8

End-to-end-machine-learning

Here I prepared a basic machine learning project of Housing price prediction, in which I provided all the steps to create a machine learning project from end to end, from reading data, and visualisation to training it and choosing proper hyperparameters.
Jupyter Notebook
6
star
9

Jamming-with-spotify

JavaScript
5
star
10

MOVIE-RECOMMMENDOR-SYSTEM

Here I made a content based movie recomendor system using basic mathematics and used it to recommend movies based on the ratings of the customer given to the movies..
Jupyter Notebook
5
star
11

MNIST-DIGIT-CLASSIFIER

Here I made a MNIST digit classifier in which I imported the MNIST dataset and performed all the techniques of machine learning and showed how One Versus One and One Versus All techniques are used for multiclass classification.
Jupyter Notebook
5
star
12

get-your-food

JavaScript
4
star
13

Titanic-Dataset-EDA

Here I have done Exploratory Data Analysis and Predicted the outcomes manually by visualizing and interpreting from data, without using any machine learning algorithm and technique and got an accuracy of 81.48% which is quite fair.
Jupyter Notebook
4
star
14

Amazon-Fine-Food-Sentiment

I worked on kaggle kernel on Amazon Fine Food Reviews dataset and applied all the text cleaning, preprocessing and model fitting steps. I cleaned the deduplicated data after which nearly about 69% of original data remained. I applied preprocessor and tokenizer to remove stopwords and emoctions etc.. I used bag of words model and tfidf models to separate out the most useful words. Then I created a pipeline and evaluated the dataset on a logistic regression model to get accuracy of 93.24%%
Jupyter Notebook
4
star
15

HERE_COMES_THE_CUSTOMER

# Getting Started In this project, we will analyze a dataset containing data on various customers' annual spending amounts (reported in monetary units) of diverse product categories for internal structure. One goal of this project is to best describe the variation in the different types of customers that a wholesale distributor interacts with. Doing so would equip the distributor with insight into how to best structure their delivery service to meet the needs of each customer.
Jupyter Notebook
4
star
16

SENTIclass

Project Description
Jupyter Notebook
3
star
17

VarianceThreshold

Here I performed feature selection with the help of various methods.
Jupyter Notebook
3
star
18

StatsPreviewCard

# Frontend Mentor - Stats preview card component solution This is a solution to the [Stats preview card component challenge on Frontend Mentor](https://www.frontendmentor.io/challenges/stats-preview-card-component-8JqbgoU62). Frontend Mentor challenges help you improve your coding skills by building realistic projects. ## Table of contents - [Overview](#overview) - [The challenge](#the-challenge) - [Screenshot](#screenshot) - [Links](#links) - [My process](#my-process) - [Built with](#built-with) - [What I learned](#what-i-learned) - [Continued development](#continued-development) - [Useful resources](#useful-resources) - [Author](#author) - [Acknowledgments](#acknowledgments) **Note: Delete this note and update the table of contents based on what sections you keep.** ## Overview ### The challenge Users should be able to: - View the optimal layout depending on their device's screen size ### Screenshot ![](./screenshot.jpg) Add a screenshot of your solution. The easiest way to do this is to use Firefox to view your project, right-click the page and select "Take a Screenshot". You can choose either a full-height screenshot or a cropped one based on how long the page is. If it's very long, it might be best to crop it. Alternatively, you can use a tool like [FireShot](https://getfireshot.com/) to take the screenshot. FireShot has a free option, so you don't need to purchase it. Then crop/optimize/edit your image however you like, add it to your project, and update the file path in the image above. **Note: Delete this note and the paragraphs above when you add your screenshot. If you prefer not to add a screenshot, feel free to remove this entire section.** ### Links - Solution URL: [Add solution URL here](https://your-solution-url.com) - Live Site URL: [Add live site URL here](https://your-live-site-url.com) ## My process ### Built with - Semantic HTML5 markup - CSS custom properties - Flexbox - CSS Grid - Mobile-first workflow - [React](https://reactjs.org/) - JS library - [Next.js](https://nextjs.org/) - React framework - [Styled Components](https://styled-components.com/) - For styles **Note: These are just examples. Delete this note and replace the list above with your own choices** ### What I learned Use this section to recap over some of your major learnings while working through this project. Writing these out and providing code samples of areas you want to highlight is a great way to reinforce your own knowledge. To see how you can add code snippets, see below: ```html <h1>Some HTML code I'm proud of</h1> ``` ```css .proud-of-this-css { color: papayawhip; } ``` ```js const proudOfThisFunc = () => { console.log('πŸŽ‰') } ``` If you want more help with writing markdown, we'd recommend checking out [The Markdown Guide](https://www.markdownguide.org/) to learn more. **Note: Delete this note and the content within this section and replace with your own learnings.** ### Continued development Use this section to outline areas that you want to continue focusing on in future projects. These could be concepts you're still not completely comfortable with or techniques you found useful that you want to refine and perfect. **Note: Delete this note and the content within this section and replace with your own plans for continued development.** ### Useful resources - [Example resource 1](https://www.example.com) - This helped me for XYZ reason. I really liked this pattern and will use it going forward. - [Example resource 2](https://www.example.com) - This is an amazing article which helped me finally understand XYZ. I'd recommend it to anyone still learning this concept. **Note: Delete this note and replace the list above with resources that helped you during the challenge. These could come in handy for anyone viewing your solution or for yourself when you look back on this project in the future.** ## Author - Website - [Add your name here](https://www.your-site.com) - Frontend Mentor - [@yourusername](https://www.frontendmentor.io/profile/yourusername) - Twitter - [@yourusername](https://www.twitter.com/yourusername) **Note: Delete this note and add/remove/edit lines above based on what links you'd like to share.** ## Acknowledgments This is where you can give a hat tip to anyone who helped you out on this project. Perhaps you worked in a team or got some inspiration from someone else's solution. This is the perfect place to give them some credit. **Note: Delete this note and edit this section's content as necessary. If you completed this challenge by yourself, feel free to delete this section entirely.**
CSS
3
star
19

Machine-Learning-Techniques

Here I have applied many machine learning regression and classification technique in the Applied Machine Learning course by University of Michigan for understanding.
Jupyter Notebook
3
star
20

CHARITY-ML

In this project, we will employ several supervised algorithms of your choice to accurately model individuals' income using data collected from the 1994 U.S. Census. We will then choose the best candidate algorithm from preliminary results and further optimize this algorithm to best model the data. Our goal with this implementation is to construct a model that accurately predicts whether an individual makes more than $50,000. This sort of task can arise in a non-profit setting, where organizations survive on donations. Understanding an individual's income can help a non-profit better understand how large of a donation to request, or whether or not they should reach out to begin with. While it can be difficult to determine an individual's general income bracket directly from public sources, we can (as we will see) infer this value from other publically available features. The dataset for this project originates from the [UCI Machine Learning Repository](https://archive.ics.uci.edu/ml/datasets/Census+Income).
Jupyter Notebook
3
star
21

MoodDetector

# Introduction
Jupyter Notebook
2
star
22

Udacity-Course-Projects

# Udacity Deep Learning Nanodegree
Jupyter Notebook
2
star
23

DeepStyle

# Introduction to Neural Style Transfer
Jupyter Notebook
1
star
24

spam-prediction

HTML
1
star
25

Animated-Buttons

CSS
1
star
26

trivia-card

CSS
1
star
27

MyRecommendor

Recommendation System
HTML
1
star
28

hackerearthchallenge

zipfile
1
star
29

myportfolio

# Portfolio
HTML
1
star
30

Spammer

HTML
1
star
31

TV-halftime-shows-and-the-Big-Game

# Project Description
Jupyter Notebook
1
star
32

blog-palace

CSS
1
star
33

soundboard

CSS
1
star
34

microsoft-bot

JavaScript
1
star
35

BlogrLandingPage

CSS
1
star
36

FlowerClassification

# Flower Classification
Jupyter Notebook
1
star
37

myCIFAR10Keras

# Introduction
Jupyter Notebook
1
star
38

MyLIB

#coursera
Python
1
star
39

RESNET-50

# Introduction
Jupyter Notebook
1
star
40

profile-card-component

CSS
1
star
41

Number-guesser

JavaScript
1
star
42

Apple-Sign-Up-Form

CSS
1
star