txd866 Goto Github PK

2014

Official content for the Fall 2014 Harvard CS109 Data Science course

2014-alibaba-big-data-competition

2014 Alibaba Big Data Competition, Team leader, implemented a recommendation algorithm with logistic regression and participated in final season(500 out of over 5000)

2014_data

Data directory for the CS109 Data Science course

acdc-torch

ACDC: A Structured Efficient Linear Layer

action-recognition-visual-attention

Action recognition using soft attention based deep recurrent neural networks

alibaba

The alibaba competitions

alitianchi

2015阿里巴巴天池大数据竞赛

allenai

amazon-dsstne

Deep Scalable Sparse Tensor Network Engine (DSSTNE) is an Amazon developed library for building Deep Learning (DL) machine learning (ML) models

arctic-capgen-vid

automatic video description generation with GPU training

arrayfire

ArrayFire: a general purpose GPU library.

arrayfire-python

Python bindings for ArrayFire

attention-lvcsr

End-to-End Attention-Based Large Vocabulary Speech Recognition

awesome-r

A curated list of awesome R frameworks, packages and software.

bayesboost

Bayesian Optimization using xgboost and sklearn API

bayesianlearning

bayesianoptimization

A Python implementation of global optimization with gaussian processes.

benchm-ml

A minimal benchmark for scalability, speed and accuracy of commonly used open source implementations (R packages, Python scikit-learn, H2O, xgboost, Spark MLlib etc.) of the top machine learning algorithms for binary classification (random forests, gradient boosted trees, deep neural networks etc.).

bidirectional-random-walk

Random Walk (Personalized PageRank) Algorithms for Large Graphs

binding

Code for the "Binding via Reconstruction Clustering" paper

blog-files

Public code files for the DDL blog

bosen

SailingLab's Petuum project.

bpl

Bayesian Program Learning model for one-shot learning

caffe

Caffe: a fast open framework for deep learning.

caffe-lstm

LSTM implementation on Caffe

caffe-multigpu

Originally cloned from puzzledqs's mpi-parallel version. New features are added.

caffe-parameter-server

Proof of concept prototype to perform distributed training using BVLC/caffe, based on a parameter server implementation using MPI. Data parallelism only

caffe-parsenet

Modifications to ParseNet

caffe-windows

Configure Caffe in one hour for Windows users.

caffe2

This is currently an experimental refactoring of Caffe.