xupengai Goto Github PK

28_ml_7

K Nearest Neighbor: Basketball players season 2013-14

adl-fall-19

deeplearning

Python for《Deep Learning》，该书为《深度学习》(花书) 数学推导、原理剖析与源码级别代码实现

hothands

tests if the "hot hands effect" is true for NBA basketball players

lewansoul-lx16a

Library and UI to configure and control LewanSoul LX-16A servos

librealsense

Intel® RealSense™ SDK

machinelearning

Machine learning resources

nba-data-analysis-project

A project where I use Python with Pandas to analyse a lot of data related to NBA statistics to answer some questions i'm curious about. For example, who is the most overpaid player in terms of statistics? What

nba-positions

Exploration of player positions in this new era of small-ball basketball

nba_analytics_tutorial

nba_machinelearning_project

Using Scikit-learn, perform analyses on per player NBA data

nn_from_scratch

B站视频系列-从零开始的神经网络

openbilibili-go-common

嘘，不要问！我也不清楚这些是啥…

pylx-16a

A Python library for controlling LewanSoul's LX-16A servos

python-100-days

Python - 100天从新手到大师

roboschool

Open-source software for robot simulation, integrated with OpenAI Gym.

statistical-classification-of-nba-data

The purpose of this research is to examine the use of different statistical classification methods for predicting the outcome of basketball matches in the National Basketball Association (NBA). Statistical data from 4920 NBA games were collected and used to train and test a variety of classification techniques such as the KNN method and Decision Tree. Classification was chosen as the model to identify new observations as a “Win” or “Loss”. Methods used in this research are the supervised machine learning algorithms K-Nearest Neighbours (KNN) and Decision Trees. The hill climbing method, with random feature selection, was used to determine the value of neighbours and features used in the models. The experiment showed how adding and removing features differed the overall results in the predictability of the outcome of an NBA game via Decision Trees and the K-NN Methods. The K-NN method provided a more accurate predictability in determining the outcome of an NBA basketball match with the Cross validation across five folds of data produced precision ratings between 76 - 79%. Future research could look at analysing individual players and see how their performances influence match outcome.

tensorflow

An Open Source Machine Learning Framework for Everyone

the-best-college-basketball-players

This is based by the different position

usefulwebsites

实用网址整理,欢迎共享

vrep_tutorial