wujian16 Goto Github PK

autograd

Efficiently computes derivatives of numpy code.

chinese_chess_in_ocaml

CS 3110 Final Project

conda-moe

conda recipe for MOE (A global, black box optimization engine for real world metric optimization.)

cornell-moe

A Python library for the state-of-the-art Bayesian optimization algorithms, with the core implemented in C++.

darts

Differentiable architecture search for convolutional and recurrent networks

deeplearningimplementations

Implementation of recent Deep Learning papers

demandforecast

hpolib

HPOlib is a hyperparameter optimization library. It provides a common interface to three state of the art hyperparameter optimization packages: SMAC, spearmint and hyperopt. This package is discontinued, please read the longer note in the info box below.

hyperband

Tuning hyperparams fast with Hyperband

hypergrad

Exploring differentiation with respect to hyperparameters

keras

Deep Learning library for Python. Convnets, recurrent neural networks, and more. Runs on Theano or TensorFlow.

learning-to-learn

Learning to Learn in TensorFlow

neural-net-bayesian-optimization

We use a modified neural network instead of Gaussian process for Bayesian optimization.

openaerostruct

OpenAeroStruct is a lightweight tool to perform aerostructural optimization using OpenMDAO.

reinforcement-learning-an-introduction

Python implementation of Reinforcement Learning: An Introduction

restaurantrevenueprediction_orie6125

The Final Project of ORIE 6125

robo

RoBO: a Robust Bayesian Optimization framework

scikit-learn

scikit-learn: machine learning in Python

sgmcmc

Stochastic Gradient MCMC algorithms implemented in theano (and autograd)

takg

supplementary materials for the taKG paper published at UAI 2019

tensorflow

Computation using data flow graphs for scalable machine learning

tensorflow-examples

TensorFlow Tutorial and Examples for beginners

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.

twostep-bayesopt

NeurIPS 2019 Paper