lenovor Goto Github PK

egads

Extendible Generic Anomaly Detection System

electronicmall-1

electronic buy somthing

emf

end-to-end-for-chinese-plate-recognition

多标签分类,端到端的中文车牌识别基于mxnet .

ensemble_amazon

Code to share different ensemble techniques with focus on meta-stacking , using data from Amazon.com - Employee Access Challenge kaggle competition

entitysentiment

Entity level sentiment analysis for product reviews using deep learning

estm60203

Introduction to Operations Research

exp-machines

Exponential Machines implementation

experimental-mf

cache-friendly multithread matrix factorization

expo-mf

Exposure Matrix Factorization: modeling user exposure in recommendation

factorizationmachine

fast-rcnn

Fast R-CNN

fastfm

fastfm-core

fbpca

Fast Randomized PCA/SVD

ffann

This is an easy to use minimal feed forward neural network library. Setup instructions are in the readme!

fifty-shades

Source code to support ACM RecSys'16 paper "Fifty Shades of Ratings: How to Benefit from a Negative Feedback in Top-N Recommendations Tasks"

fisher-discriminant

flexifact

Run large scale tensor and coupled matrix-tensor factorization on top of stock Hadoop.

fouriertalkoscon

Presentation Materials for my "Sound Analysis with the Fourier Transform and Python" OSCON Talk.

friso

High performance chinese tokenizer with both GBK and UTF-8 charset support developed by ANSI C

fundamentals-of-deep-learning-book

Code companion to the O'Reilly "Fundamentals of Deep Learning" book

gan-intro

gemdemo

gem demo

gpflow

Gaussian processes in TensorFlow

gplearn

Genetic Programming in Python, with a scikit-learn inspired API

gpyopt

Gaussian Process Optimization using GPy

gradientdescentexample

Example demonstrating how gradient descent may be used to solve a linear regression problem

gram-schmidt-pca

Implementation of PCA algorithm using Gram-Scmidt modification on NIPALS

gru4rec

GRU4Rec is the cleaned & simplified implementation of the algorithm of the "Session-based Recommendations with Recurrent Neural Networks" paper, published at ICLR 2016. The code is stripped of features that we had found to be unhelpful in increasing accuracy.