qqgeogor's repositories
ultrasound-nerve-segmentation
Deep Learning Tutorial for Kaggle Ultrasound Nerve Segmentation competition, using Keras
RecomendationDL
RecomendationDL
awesome-very-deep-learning
A curated list of papers and code about very deep neural networks (especially residual networks) :sunglasses:
chadslab
Automatically exported from code.google.com/p/chadslab
conditional-dcgan-keras
Keras implementation of the conditional GAN.
dcgan_vae_torch
An implementation of the deep convolutional generative adversarial network, combined with a varational autoencoder
deep-ctr
An attempt of training DNN models to predict ad click-through rate, implemented with Theano.
fast_tffm
fast_tffm: Tensorflow-based Distributed Factorization Machine
kaggle-allstate-claims-severity-1
2nd place solution for Allstate Claims Severity competition at Kaggle
kaggle-telstra
My code for Telstra Network Disruptions Kaggle competition
Kaggle_HomeDepot
Turing Test's Solution for Home Depot Product Search Relevance Competition on Kaggle (https://www.kaggle.com/c/home-depot-product-search-relevance)
keras-resnet
Residual networks implementation using Keras-1.0 functional API
libfm
Library for factorization machines
lightfm
A Python implementation of LightFM, a hybrid recommendation algorithm.
LightGBM
LightGBM is a fast, distributed, high performance gradient boosting (GBDT, GBRT, GBM or MART) framework based on decision tree algorithms, used for ranking, classification and many other machine learning tasks.
luna16
LUNA16 Lung Nodule Analysis - NWI-IMC037 Final Project
numdifftools
Solve automatic numerical differentiation problems in one or more variables.
santander_2016
The 3rd place solution for Santander Customer Satisfaction competition
Theano
Theano is a Python library that allows you to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. It can use GPUs and perform efficient symbolic differentiation.
triplet_recommendations_keras
An example of doing MovieLens recommendations using triplet loss in Keras
tsne
A python wrapper for Barnes-Hut tsne
vowpal_wabbit
Vowpal Wabbit is a machine learning system which pushes the frontier of machine learning with techniques such as online, hashing, allreduce, reductions, learning2search, active, and interactive learning.
wide-residual-networks
3.8% and 18.3% on CIFAR-10 and CIFAR-100
xgboost
Scalable, Portable and Distributed Gradient Boosting (GBDT, GBRT or GBM) Library, for Python, R, Java, C++ and more