Skip to content

Updated: README to include hyperparameter tuning examples #277

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Jun 11, 2018
Merged

Updated: README to include hyperparameter tuning examples #277

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
35 changes: 25 additions & 10 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,6 +16,17 @@ These examples provide a gentle introduction to machine learning concepts as the
- [Video Game Sales](introduction_to_applying_machine_learning/video_game_sales) develops a binary prediction model for the success of video games based on review scores.
- [MXNet Gluon Recommender System](introduction_to_applying_machine_learning/gluon_recommender_system) uses neural network embeddings for non-linear matrix factorization to predict user movie ratings on Amazon digital reviews.

### SageMaker Automatic Model Tuning

These examples introduce SageMaker's hyperparameter tuning functionality which helps deliver the best possible predictions by running a large number of training jobs to determine which hyperparameter values are the most impactful.

- [XGBoost Tuning](hyperparameter_tuning/xgboost_direct_marketing) shows how to use SageMaker hyperparameter tuning to improve your model fits for the [Targeted Direct Marketing](introduction_to_applying_machine_learning/xgboost_direct_marketing) task.
- [TensorFlow Tuning](hyperparameter_tuning/tensorflow_mnist) shows how to use SageMaker hyperparameter tuning with the pre-built TensorFlow container and MNIST dataset.
- [MXNet Tuning](hyperparameter_tuning/mxnet_mnist) shows how to use SageMaker hyperparameter tuning with the pre-built MXNet container and MNIST dataset.
- [Keras BYO Tuning](hyperparameter_tuning/keras_bring_your_own) shows how to use SageMaker hyperparameter tuning with a custom container running a Keras convolutional network on CIFAR-10 data.
- [R BYO Tuning](hyperparameter_tuning/r_bring_your_own) shows how to use SageMaker hyperparameter tuning with the custom container from the [Bring Your Own R Algorithm](advanced_functionality/r_bring_your_own) example.
- [Analyzing Results](hyperparameter_tuning/analyze_results) is a shared notebook that can be used after each of the above notebooks to provide analysis on how training jobs with different hyperparameters performed.

### Introduction to Amazon Algorithms

These examples provide quick walkthroughs to get you up and running with Amazon SageMaker's custom developed algorithms. Most of these algorithms can train on distributed hardware, scale incredibly well, and are faster and cheaper than popular alternatives.
Expand All @@ -39,6 +50,7 @@ These examples provide more thorough mathematical treatment on a select group of

- [Streaming Median](scientific_details_of_algorithms/streaming_median) sequentially introduces concepts used in streaming algorithms, which many SageMaker algorithms rely on to deliver speed and scalability.
- [Latent Dirichlet Allocation (LDA)](scientific_details_of_algorithms/lda_topic_modeling) dives into Amazon SageMaker's spectral decomposition approach to LDA.
- [Linear Learner features](scientific_details_of_algorithms/linear_learner_class_weights_loss_functions) shows how to use the class weights and loss functions features of the SageMaker Linear Learner algorithm to improve performance on a credit card fraud prediction task

### Advanced Amazon SageMaker Functionality

Expand All @@ -56,19 +68,22 @@ These examples that showcase unique functionality available in Amazon SageMaker.
- [Bring Your Own MXNet Model](advanced_functionality/mxnet_mnist_byom) shows how to bring a model trained anywhere using MXNet into Amazon SageMaker
- [Bring Your Own TensorFlow Model](advanced_functionality/tensorflow_iris_byom) shows how to bring a model trained anywhere using TensorFlow into Amazon SageMaker

### Amazon SageMaker TensorFlow and MXNet Pre-Built Containers and the Python SDK
### Amazon SageMaker Pre-Built Deep Learning Framework Containers and the Python SDK

These examples focus on the Amazon SageMaker Python SDK which allows you to write idiomatic TensorFlow or MXNet and then train or host in pre-built containers.

- [cifar 10 with MXNet Gluon](sagemaker-python-sdk/mxnet_gluon_cifar10)
- [MNIST with MXNet Gluon](sagemaker-python-sdk/mxnet_gluon_mnist)
- [MNIST with MXNet](sagemaker-python-sdk/mxnet_mnist)
- [Sentiment Analysis with MXNet Gluon](sagemaker-python-sdk/mxnet_gluon_sentiment)
- [TensorFlow Neural Networks with Layers](sagemaker-python-sdk/tensorflow_abalone_age_predictor_using_layers)
- [TensorFlow Networks with Keras](sagemaker-python-sdk/tensorflow_abalone_age_predictor_using_keras)
- [Introduction to Estimators in TensorFlow](sagemaker-python-sdk/tensorflow_iris_dnn_classifier_using_estimators)
- [TensorFlow and TensorBoard](sagemaker-python-sdk/tensorflow_resnet_cifar10_with_tensorboard)
- [Distributed TensorFlow](sagemaker-python-sdk/tensorflow_distributed_mnist)
- [Chainer CIFAR-10](sagemaker-python-sdk/chainer_cifar10) trains a VGG image classification network on CIFAR-10 using Chainer (both single machine and multi-machine versions are included)
- [Chainer MNIST](sagemaker-python-sdk/chainer_mnist) trains a basic neural network on MNIST using Chainer (shows how to use local mode)
- [Chainer sentiment analysis](sagemaker-python-sdk/chainer_sentiment_analysis) trains a LSTM network with embeddings to predict text sentiment using Chainer
- [CIFAR-10 with MXNet Gluon](sagemaker-python-sdk/mxnet_gluon_cifar10) trains a ResNet-34 image classification model using MXNet Gluon
- [MNIST with MXNet Gluon](sagemaker-python-sdk/mxnet_gluon_mnist) trains a basic neural network on the MNIST handwritten digit dataset using MXNet Gluon
- [MNIST with MXNet](sagemaker-python-sdk/mxnet_mnist) trains a basic neural network on the MNIST handwritten digit data using MXNet's symbolic syntax
- [Sentiment Analysis with MXNet Gluon](sagemaker-python-sdk/mxnet_gluon_sentiment) trains a text classifier using embeddings with MXNet Gluon
- [TensorFlow Neural Networks with Layers](sagemaker-python-sdk/tensorflow_abalone_age_predictor_using_layers) trains a basic neural network on the abalone dataset using TensorFlow layers
- [TensorFlow Networks with Keras](sagemaker-python-sdk/tensorflow_abalone_age_predictor_using_keras) trains a basic neural network on the abalone dataset using TensorFlow and Keras
- [Introduction to Estimators in TensorFlow](sagemaker-python-sdk/tensorflow_iris_dnn_classifier_using_estimators) trains a DNN classifier estimator on the Iris dataset using TensorFlow
- [TensorFlow and TensorBoard](sagemaker-python-sdk/tensorflow_resnet_cifar10_with_tensorboard) trains a ResNet image classification model on CIFAR-10 using TensorFlow and showcases how to track results using TensorBoard
- [Distributed TensorFlow](sagemaker-python-sdk/tensorflow_distributed_mnist) trains a simple convolutional neural network on MNIST using TensorFlow

### Using Amazon SageMaker with Apache Spark

Expand Down