Project Name | Stars | Downloads | Repos Using This | Packages Using This | Most Recent Commit | Total Releases | Latest Release | Open Issues | License | Language |
---|---|---|---|---|---|---|---|---|---|---|
Thesemicolon | 312 | 6 years ago | 16 | Jupyter Notebook | ||||||
This repository contains Ipython notebooks and datasets for the data analytics youtube tutorials on The Semicolon. | ||||||||||
Deep Learning Coursera | 102 | 6 years ago | 1 | mit | Jupyter Notebook | |||||
Projects from the Deep Learning Specialization from deeplearning.ai provided by Coursera | ||||||||||
Machine Learning In Python Workshop | 54 | 4 years ago | Jupyter Notebook | |||||||
My workshop on machine learning using python language to implement different algorithms | ||||||||||
Machine_learning_course | 44 | 4 years ago | 1 | Jupyter Notebook | ||||||
Artificial intelligence/machine learning course at UCF in Spring 2020 (Fall 2019 and Spring 2019) | ||||||||||
Learning Rate | 25 | 6 years ago | Jupyter Notebook | |||||||
Implementation of Learning Rate Finder, SGDR and Cyclical Learning Rate in Keras | ||||||||||
Keras Cosine Annealing | 17 | 4 years ago | 2 | Python | ||||||
Keras implementation of Cosine Annealing Scheduler | ||||||||||
Keras Normalized Optimizers | 13 | 6 years ago | 1 | mit | Jupyter Notebook | |||||
Wrapper for Normalized Gradient Descent in Keras | ||||||||||
Self Driving Robot Using Neural Network | 9 | 3 years ago | mit | Python | ||||||
This project introduces the autonomous robot which is a scaled down version of actual self-driving vehicle and designed with the help of neural network. The main focus is on building autonomous robot and train it on a designed track with the help of neural network so that it can run autonomously without a controller or driver on that specific track. The robot will stream the video to laptop which will then take decisions and send the data to raspberry pi which will then control the robot using motor driver. This motor driver will move the robot in required directions. Neural Network is used to train the model by first driving the robot on the specially designed track by labeling the images with the directions to be taken. After the model is trained it can make accurate predictions by processing the images on computer. This approach is better than conventional method which is done by extracting specific feature from images. |