GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → shibuiwilliam → keras_gpyopt

shibuiwilliam / keras_gpyopt

Licence: other
Using Bayesian Optimization to optimize hyper parameter in Keras-made neural network model.

Programming Languages

Jupyter Notebook
11667 projects
python
139335 projects - #7 most used programming language

Labels

tensorflowkerasmnistbayesian-optimizationgpyoptkeras-gpyopt

Projects that are alternatives of or similar to keras gpyopt

playing with vae
Comparing FC VAE / FCN VAE / PCA / UMAP on MNIST / FMNIST
Stars: ✭ 53 (-5.36%)
Mutual labels:  mnist
MNIST-TFLite
MNIST classifier built for TensorFlow Lite - Android, iOS and other "lite" platforms
Stars: ✭ 34 (-39.29%)
Mutual labels:  mnist
crohme-data-extractor
A modified extractor for the CROHME handwritten math symbols dataset.
Stars: ✭ 18 (-67.86%)
Mutual labels:  mnist
PHYSBO
PHYSBO -- optimization tools for PHYsics based on Bayesian Optimization
Stars: ✭ 40 (-28.57%)
Mutual labels:  bayesian-optimization
image-defect-detection-based-on-CNN
TensorBasicModel
Stars: ✭ 17 (-69.64%)
Mutual labels:  mnist
numpy-neuralnet-exercise
Implementation of key concepts of neuralnetwork via numpy
Stars: ✭ 49 (-12.5%)
Mutual labels:  mnist
digdet
A realtime digit OCR on the browser using Machine Learning
Stars: ✭ 22 (-60.71%)
Mutual labels:  mnist
mindware
An efficient open-source AutoML system for automating machine learning lifecycle, including feature engineering, neural architecture search, and hyper-parameter tuning.
Stars: ✭ 34 (-39.29%)
Mutual labels:  bayesian-optimization
PaperSynth
Handwritten text to synths!
Stars: ✭ 18 (-67.86%)
Mutual labels:  mnist
cuda-neural-network
Convolutional Neural Network with CUDA (MNIST 99.23%)
Stars: ✭ 118 (+110.71%)
Mutual labels:  mnist
MNIST
Handwritten digit recognizer using a feed-forward neural network and the MNIST dataset of 70,000 human-labeled handwritten digits.
Stars: ✭ 28 (-50%)
Mutual labels:  mnist
MNIST-adversarial-images
Create adversarial images to fool a MNIST classifier in TensorFlow
Stars: ✭ 13 (-76.79%)
Mutual labels:  mnist
catseye
Neural network library written in C and Javascript
Stars: ✭ 29 (-48.21%)
Mutual labels:  mnist
differential-privacy-bayesian-optimization
This repo contains the underlying code for all the experiments from the paper: "Automatic Discovery of Privacy-Utility Pareto Fronts"
Stars: ✭ 22 (-60.71%)
Mutual labels:  bayesian-optimization
bayesopt-tutorial-r
Tutorial on Bayesian optimization in R
Stars: ✭ 15 (-73.21%)
Mutual labels:  bayesian-optimization
Bayesian-Optimization
Bayesian Optimization algorithms with various recent improvements
Stars: ✭ 70 (+25%)
Mutual labels:  bayesian-optimization
ESNAC
Learnable Embedding Space for Efficient Neural Architecture Compression
Stars: ✭ 27 (-51.79%)
Mutual labels:  bayesian-optimization
digitrecognition ios
Deep Learning with Tensorflow/Keras: Digit recognition based on mnist-dataset and convolutional neural-network on iOS with CoreML
Stars: ✭ 23 (-58.93%)
Mutual labels:  mnist
SimpNet-Tensorflow
A Tensorflow Implementation of the SimpNet Convolutional Neural Network Architecture
Stars: ✭ 16 (-71.43%)
Mutual labels:  mnist
gan-vae-pretrained-pytorch
Pretrained GANs + VAEs + classifiers for MNIST/CIFAR in pytorch.
Stars: ✭ 134 (+139.29%)
Mutual labels:  mnist
View All Similar Projects ➔

keras_gpyopt

Using Bayesian Optimization to optimize hyper parameter in Keras-made neural network model. This repository is a sample code for running Keras neural network model for MNIST, tuning hyper parameter with Bayesian Optimization.

Installing GpyOpt

Bayesian Optimization in the program is run by GpyOpt library. This is a Python library for Bayesian Optimization. http://sheffieldml.github.io/GPyOpt/ For installation of GpyOpt, run the followin commands.

conda update scipy
pip install GPy
pip install gpyopt

Bayesian Optimization

Bayesian Optimization assumes the equation between input and output as black box and tries to acquire distribution of the output by exploring and observing various inputs and outputs. Bayesian Optimization improves distribution assumption by sampling the inputs and outputs to get close to the actual distribution in exploitable time. See below for more. http://www.mlss2014.com/files/defreitas_slides1.pdf

How to use

Git clone the repository and run bopt_nn.py.

https://github.com/shibuiwilliam/keras_gpyopt.git
cd keras_gpyopt
python bopt_nn.py

This will give you optimized parameter for MNIST classification on Keras as well as its accuracy.

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].