This repository contains works on a computer vision software pipeline built on top of Python to identify Lanes and vehicles in a video. This project is not part of Udacity SDCND but is based on other free courses and challanges provided by Udacity. It uses Computer vision and Deep Learrning Techniques. Few pipelines have been tried on SeDriCa, I…

Hierarchical self-organizing maps for unsupervised pattern recognition

Code for IoT Journal paper 'ML-MCU: A Framework to Train ML Classifiers on MCU-based IoT Edge Devices'

Code for paper 'Train++: An Incremental ML Model Training Algorithm to Create Self-Learning IoT Devices'

Python library for classifier calibration

source : zero-to-mastery https://github.com/mrdbourke/zero-to-mastery-ml

Code for AAAI poster 'Training up to 50 Class ML Models on 3 $ IoT Hardware via Optimizing One-vs-One Algorithm'

💬 NN-Based intent detection and middleware support for RiveScript

Fruit Classifier with ANN

This project allows the use of machine learning to predict the ingredients of a recipe. In particular, it has been implemented on a poke recipe in which a series of ingredients (i.e. 8) are passed as input and the software returns 2 missing (for example the topping and the sauce). The model used is Multi Target Forest and Scikit Learn ML library

automatically geocode aid projects by applying natural language processing techniques

Classification of Clear Cell Renal Cell Carcinoma using CT textural feature analysis

42 • A guide to implement a linear classification model: logistic regression.

Human skin detection and segmentation 👨‍👩‍👧‍👦

Final Project submitted CIS 600 Data Mining Course Spring 2020. Supervised ML project on a job posting dataset to predict fake postings.

Java Implementation of the simplified strength based learning classifier system

Contains the codes for Extended Histogram of Gradients for object recognition developed by me during my PhD studies.

A neural network built from scratch using NumPy in Python to classify handwritten digits from the MNIST dataset containing 70,000 28x28 images. Becomes more accurate with Machine Learning methods.

Web/PHP based image annotator that creates Darknet/YOLO txt files.

DeepNet is simple node based cli tool for creating machine learning classifiers you can use on the web.