machinelearning
Machine learning is the practice of teaching a computer to learn. The concept uses pattern recognition, as well as other forms of predictive algorithms, to make judgments on incoming data. This field is closely related to artificial intelligence and computational statistics.
Here are 4,393 public repositories matching this topic...
Technology for Independent Neural Automation for AUN Appliances
-
Updated
Nov 30, 2016 - Java
[Work in Progresss] Become so good in machine learning - a complete machine learning study plan to become a Machine learning rockstar (and a ML engineer).
-
Updated
Mar 25, 2018
-
Updated
Aug 2, 2017 - MATLAB
Creating a perception pipeline for the pr2 robot in simulation, to perform pick and place tasks
-
Updated
Dec 14, 2017 - C++
This is a jupyter notebook for the Kaggle Regression Day 1 challenge on the Bikes dataset. It is my first Kaggle kernel and also my first attempt to apply ML concepts on real data. You can find the New Yorks bikes data set from the kaggle website for your own reference or practice.
-
Updated
Dec 9, 2017 - HTML
-
Updated
Apr 30, 2017 - HTML
Sentiment Analysis using machine learning approach on cloud environment
-
Updated
May 20, 2017 - Python
This is a Neural Network class I created in Python along with some test data.
-
Updated
Feb 14, 2017 - Python
Uses Weka to perform Machine Learning on two DataSets.
-
Updated
Feb 5, 2017 - Java
Simulation of Linear Regression algorithm using P5.JS
-
Updated
Jun 2, 2018 - JavaScript
Machine learning used to develop an unbeatable player of "NIM game" programmed in Python
-
Updated
Mar 23, 2018
Implementation of gradient descent to find the line of best fit.
-
Updated
Aug 5, 2018 - Jupyter Notebook
Predict the Price value of owner occupied homes.
-
Updated
Aug 12, 2018 - Jupyter Notebook
Machine learning library with visualisation GUI to help teach or understand machine learning and how different classifiers learn
-
Updated
Aug 8, 2018 - Java
This project involves the implementation of efficient and effective polynomial SVC on MNIST data set. The MNIST data comprises of digital images of several digits ranging from 0 to 9. Each image is 28 x 28 pixels. Thus, the data set has 10 levels of classes.
-
Updated
Dec 24, 2017 - Jupyter Notebook
factor selection, exploratory data analysis, statistical learning on both qualitative and quantitative data in R
-
Updated
Dec 22, 2018 - R
IOS application that detect objects using VGG16. CoreML framework predicts images using trained or learning models.
-
Updated
Nov 15, 2018 - Swift
- Followers
- 77.5k followers
- Wikipedia
- Wikipedia