aakashchauhan90 Goto Github PK

500-ai-machine-learning-deep-learning-computer-vision-nlp-projects-with-code

500 AI Machine learning Deep learning Computer vision NLP Projects with code

adopt-a-buddy---machine-learning

algorithm-design-manual

Data structures, algorithms, and practice problems from Steven S. Skiena's "The Algorithm Design Manual" (Second Edition).

awesome-ml-courses

Awesome free machine learning and AI courses with video lectures.

bert

TensorFlow code and pre-trained models for BERT

clustering_mall_customers

Clustering-Project To find the clusters or groups existing in the data set which is unlabelled so that the mall client can target their loyal customers in better way with their liked products. AIM: A mall has collected information about their client and given them spending score (1-100) on the basis of their spending, visit frequency, annual income, and age. The client has asked to categorize their customers into groups so that they can target them better. Also measure the accuracy achieved with applying K-Mean, Agglomarative Clustering and see which will perform better? Data Set: THe data set is called Mall_Customers.csv given by the client having 200 records, a very small data set which is to be used as POC project. The real data set we can't publish or talk about due to privacy concern. The data set has CustomerID, Genre, Age, Annual Income (k$), and Spending Score (1-100). Approach: It is a unlabelled data set and Clearly we don’t know how many clusters could be? It becomes a clustering problem. We used K-Mean clustering algorithm to find the number of the clusters. We used Elbow method to find visually how many clusters could be? Result: The are total of 5 clusters we are able to extract from the data set.The clusters were namely Target, Standard, Careless, Sensible, and Careful. Target: The annual income and spending score are higher. Standard: The annual income and spending score both are in mid range. Careless: Annual income are less but the spends more. Careful: Annual income on higher side but they spends less. Sensible: Both annual income and spending score are on lower side means their income are less so they donot spends more. The process based on the Elbow method and WCSS=Within cluster sum of square parameter to decide the number of clusters we can have.

cs224w-facebook-user-movement-network-analysis

CS224W Analysis of Network Project - People Movement Network During Disasters

d2l-study-group

Deep Learning Study Group

data-engineering-with-google-cloud-platform

Data Engineering with Google Cloud Platform, published by Packt

data-engineering-zoomcamp

Code for Data Engineer Zoomcamp course

data-science-interviews

Data science interview questions and answers

data-scientist-roadmap

Toturial coming with "data science roadmap" graphe.

data_cleaning_pandas

Basic Pandas function to clean Data

datasharing

The Leek group guide to data sharing

deep-learning-coursera

Deep Learning Specialization by Andrew Ng on Coursera.

deep-learning-specialization-coursera

Deep Learning Specialization by Andrew Ng on Coursera.

deep_learning

Implementation of N hidden layer based deep neural network

deep_learning_neural-network

driver-insurance-claim

Porto Seguro, one of Brazil’s largest auto and homeowner insurance companies. The main challenge here is to build a model that predicts the probability that a driver will initiate an auto insurance claim in the next year.

dsc_springboard

Repository for all the code written as part of the Springboard's Data Science Career Track

fashion_dress_classification

first-contributions

🚀✨ Help beginners to contribute to open source projects

getting-things-done-with-pytorch

Jupyter Notebook tutorials on solving real-world problems with Machine Learning & Deep Learning using PyTorch. Topics: Face detection with Detectron 2, Time Series anomaly detection with LSTM Autoencoders, Object Detection with YOLO v5, Build your first Neural Network, Time Series forecasting for Coronavirus daily cases, Sentiment Analysis with BERT.

gt-nlp-class

Course materials for Georgia Tech CS 4650 and 7650, "Natural Language"

heart-disease-prediction

Various classification algorithms are implemented to predict whether a person is prone to or is suffering from heart disease

heart-disease-prediction-1

The project involves training a machine learning model (K Neighbors Classifier) to predict whether someone is suffering from a heart disease with 87% accuracy.

heart-rate-prediction

Heart disease describes a range of conditions that affect your heart. Diseases under the heart disease umbrella include blood vessel diseases, such as coronary artery disease, heart rhythm problems (arrhythmias) and heart defects you’re born with (congenital heart defects), among others.

k-mean-clustering-project

To find the clusters or groups existing in the Mall data set which is unlabelled so that the mall client can target their loyal customers better with their liked products in a better way.

leetcode

🎓Leetcode solutions in Python 📚

leetcode-1

This repository contains the solutions and explanations to the algorithm problems on LeetCode. Only medium or above are included. All are written in C++/Python and implemented by myself. The problems attempted multiple times are labelled with hyperlinks.