-
Updated
Nov 11, 2019 - Jupyter Notebook
#
hyperparameters
Here are 73 public repositories matching this topic...
Open-source implementation of Google Vizier for hyper parameters tuning
A collection of 100+ pre-trained RL agents using Stable Baselines, training and hyperparameter optimization included.
reinforcement-learning
optimization
openai-gym
hyperparameters
openai
gym
hyperparameter-optimization
rl
zoo
hyperparameter-tuning
hyperparameter-search
pybullet
stable-baselines
-
Updated
Feb 6, 2021 - Python
This is the repository of our article published in RecSys 2019 "Are We Really Making Much Progress? A Worrying Analysis of Recent Neural Recommendation Approaches" and of several follow-up studies.
deep-learning
neural-network
reproducible-research
collaborative-filtering
matrix-factorization
hyperparameters
bpr
recommendation-system
recommender-system
reproducibility
recommendation-algorithms
knn
matrix-completion
evaluation-framework
content-based-recommendation
hybrid-recommender-system
funksvd
bprmf
bprslim
slimelasticnet
-
Updated
Jan 9, 2021 - Python
Tuning hyperparams fast with Hyperband
machine-learning
hyperparameters
hyperparameter-optimization
hyperparameter-tuning
gradient-boosting-classifier
gradient-boosting
-
Updated
Aug 15, 2018 - Python
Population Based Training (in PyTorch with sqlite3). Status: Unsupported
deep-learning
hyperparameters
hyperparameter-optimization
deepmind
hyperparameter-tuning
pbt
hyperparameter-search
population-based-training
-
Updated
Jan 31, 2018 - Python
Workflow engine for exploration of simulation models using high throughput computing
workflow
scala
grid
workflow-engine
distributed-computing
hyperparameters
scientific-computing
parameter-estimation
modeling-tool
parameter-search
egi
parameter-tuning
dirac
-
Updated
Feb 16, 2021 - Scala
A thoughtful approach to hyperparameter management.
-
Updated
Oct 30, 2020 - Python
Streamlined machine learning experiment management.
-
Updated
Apr 27, 2020 - HTML
Adventures using keras on Google's Cloud ML Engine
-
Updated
May 18, 2017 - Python
csala
commented
Jan 28, 2020
Current save/load methods focus on dumping and loading the pipeline definition in its JSON form, but provide no means to save a fitted pipeline and load it later to make predictions, being the usage of pickle outside of the pipeline the only way to go.
Let's re-implement the save/load methods to save the whole pipeline instance, and move the current save functionality to a to_json method.
Machine learning algorithms in Dart programming language
dart
classifier
data-science
machine-learning
algorithm
linear-regression
machine-learning-algorithms
regression
hyperparameters
sgd
logistic-regression
softmax-regression
dartlang
stochastic-gradient-descent
softmax
lasso-regression
batch-gradient-descent
mini-batch-gradient-descent
softmax-classifier
softmax-algorithm
-
Updated
Feb 18, 2021 - Dart
Purely functional genetic algorithms for multi-objective optimisation
scala
functional-programming
genetic-algorithm
hyperparameters
hyperparameter-optimization
hyperparameter-tuning
optimisation
parameter-tuning
-
Updated
Jan 5, 2021 - Scala
How to initialize Anchors in Faster RCNN for custom dataset?
python
computer-vision
aspect-ratio
detection
hyperparameters
anchor
faster-rcnn
object-detection
kmeans
clusters
distance-metric
bounding-boxes
tensorflow-models
iou
custom-dataset
anchor-box
-
Updated
Aug 18, 2020 - Jupyter Notebook
Easily declare large spaces of (keras) neural networks and run (hyperopt) optimization experiments on them.
-
Updated
Feb 6, 2017 - Python
ES6 hyperparameters search for tfjs
-
Updated
Sep 18, 2020 - JavaScript
Deep learning, architecture and hyper parameters search with genetic algorithms
-
Updated
Dec 6, 2020 - Python
Tuning XGBoost hyper-parameters with Simulated Annealing
-
Updated
Apr 26, 2017 - Jupyter Notebook
Automatic and Simultaneous Adjustment of Learning Rate and Momentum for Stochastic Gradient Descent
-
Updated
Aug 4, 2020 - Python
A Machine Learning Approach to Forecasting Remotely Sensed Vegetation Health in Python
python
machine-learning
r
h2o
prediction
artificial-intelligence
hyperparameters
forecasting
gbm
ensemble
satellite-imagery
modis
drought
ensemble-model
landuse
vegetation-health
-
Updated
Feb 22, 2021 - Python
Spark Parameter Optimization and Tuning
machine-learning
spark
optimizer
hyperparameters
hyperparameter-optimization
machinelearning
vowpal-wabbit
grid-search
hyperparameter-tuning
random-search
optimization-algorithms
-
Updated
Apr 11, 2018 - Scala
ParamHelpers Next Generation
-
Updated
Feb 23, 2021 - R
AutoML - Hyper parameters search for scikit-learn pipelines using Microsoft NNI
tool
scikit-learn
sklearn
hyperparameters
automl
scikit-learn-api
hyperparameter-search
sklearn-library
nni
neural-network-intelligence
-
Updated
Feb 2, 2021 - Python
How optimizer and learning rate choice affects training performance
-
Updated
Apr 12, 2018 - Python
OptKeras: wrapper around Keras and Optuna for hyperparameter optimization
-
Updated
Apr 1, 2020 - Python
-
Updated
Jan 21, 2021 - Python
-
Updated
Jan 4, 2019 - Jupyter Notebook
Using DDPG and A2C reinforcement learning algorithms to solve a math puzzle
reinforcement-learning
ai
puzzle
deep-learning
neural-network
artificial-intelligence
hyperparameters
ddpg
actor-critic
a2c
-
Updated
Sep 3, 2019 - Python
Introductory Kaggle competition
-
Updated
Jun 13, 2016 - Jupyter Notebook
Argload, easy reloading of command line arguments
-
Updated
May 9, 2018 - Python
Improve this page
Add a description, image, and links to the hyperparameters topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the hyperparameters topic, visit your repo's landing page and select "manage topics."
Is your feature request related to a problem? Please describe.
https://stackoverflow.com/questions/64477316/how-to-implement-a-repository-for-lazy-data-loading-with-neuraxle/64850395#64850395
Describe the solution you'd like
I provided an answer on the StackOverflow question above.
Additional context
We should edit the page [here](https://www.neuraxle.org/stable/intro.html#r