Towhee is a framework that is dedicated to making neural data processing pipelines simple and fast.

Curated list of open source tooling for data-centric AI on unstructured data.

This repository provides examples of image feature vector classification using PySpark and scikit-learn, offering flexibility in choosing between the two popular machine learning libraries.

End-to-end Automatic Speech Recognition for Madarian and English in Tensorflow

web based plagiarism detection system for word documents using information retrieval based methods

Extract a feature vector for any image and find the cosine similarity for comparison using Pytorch. I have used ResNet-18 to extract the feature vector of images. Finally a Django app is developed to input two images and to find the cosine similarity.

image perceptual hash experiment using convolutional neural net models

Gender classification using a Spider Web Model (given by tutors). - FVAB exam course project

The program uses HOG and LBP features to detect human in images. First, use the HOG feature only to detect humans. Next, combine the HOG feature with the LBP feature to form an augmented feature (HOG-LBP) to detect human. A Two-Layer Perceptron (feedforward neural network) will be used to classify the input feature vector into human or no-human.

Design and Implementation of Random Forest algorithm from scratch to execute Pacman strategies and actions in a deterministic, fully observable Pacman Environment.

Explore various natural language processing models using Python.

A capstone project to predict the adoption-speed of listed pets

Lo scopo dell'applicazione è quello di costruire un feature vector per la predizione dei pasti in base a valori registrati da sensori di qualità dell'aria. Le feature prodotte verranno automaticamente unite a feature statistiche già presenti in alcuni files. Per la classificazione utilizzare il Knowledge Flow Enviroment di Weka impostato nel fi…

A project on text classification

Generates Caption from sample Images Using Deep Neural Networks

Framework for correlating two or more well logs using feature vectors generated from CNN's in Pytorch

Creating a function that takes an image, a color space conversion, and the resolution to convert it into a feature vector

Invariant Superpixel Features for Object Detection

The spam classifier classifies the emails into ham or spam depending on the type of mail and based on the Naives bayes machine learning model used in the Project.