Difference between revisions of "Auto Keras"
| Line 10: | Line 10: | ||
* [[Automated Machine Learning (AML) - AutoML]] | * [[Automated Machine Learning (AML) - AutoML]] | ||
* [http://autokeras.com/ Auto Keras.com] | * [http://autokeras.com/ Auto Keras.com] | ||
| + | * [[Keras]] | ||
* [http://www.kdnuggets.com/2018/08/auto-keras-create-deep-learning-model-4-lines-code.html Auto-Keras, or How You can Create a Deep Learning Model in 4 Lines of Code | Favio Vazquez = KDnuggets] | * [http://www.kdnuggets.com/2018/08/auto-keras-create-deep-learning-model-4-lines-code.html Auto-Keras, or How You can Create a Deep Learning Model in 4 Lines of Code | Favio Vazquez = KDnuggets] | ||
| + | * [http://www.analyticsindiamag.com/10-machine-learning-projects-every-tech-aficionado-must-work-on-in-2019/ 10 Machine Learning Projects Every Tech Aficionado Must Work On In 2019 | Ambika Choudhury - AnalyticsIndia] | ||
Auto Keras is an open source software library for automated machine learning ([[AutoML]]). It is developed by DATA Lab at Texas A&M University and community contributors. The ultimate goal of AutoML is to provide easily accessible deep learning tools to domain experts with limited data science or machine learning background. Auto Keras provides functions to automatically search for architecture and hyperparameters of deep learning models. | Auto Keras is an open source software library for automated machine learning ([[AutoML]]). It is developed by DATA Lab at Texas A&M University and community contributors. The ultimate goal of AutoML is to provide easily accessible deep learning tools to domain experts with limited data science or machine learning background. Auto Keras provides functions to automatically search for architecture and hyperparameters of deep learning models. | ||
| Line 17: | Line 19: | ||
<youtube>veWfGSZSzmE</youtube> | <youtube>veWfGSZSzmE</youtube> | ||
| + | <youtube>XK2KJqSYsBM</youtube> | ||
| + | <youtube>8xLezDE7DFM</youtube> | ||
Revision as of 07:09, 27 April 2019
YouTube search... ...Google search
- Automated Machine Learning (AML) - AutoML
- Auto Keras.com
- Keras
- Auto-Keras, or How You can Create a Deep Learning Model in 4 Lines of Code | Favio Vazquez = KDnuggets
- 10 Machine Learning Projects Every Tech Aficionado Must Work On In 2019 | Ambika Choudhury - AnalyticsIndia
Auto Keras is an open source software library for automated machine learning (AutoML). It is developed by DATA Lab at Texas A&M University and community contributors. The ultimate goal of AutoML is to provide easily accessible deep learning tools to domain experts with limited data science or machine learning background. Auto Keras provides functions to automatically search for architecture and hyperparameters of deep learning models.
An open source python package written in the very easy to use deep learning library Keras. Auto Keras uses Efficient Neural Architecture Search (ENAS), an efficient and most recent version of Neural Architecture Search. You can quickly and easily install the package with a pip install autokeras and voila, you’re ready to do your own architecture search on your own dataset … for free. Since all of the code is open source, you can even play around with some of the parameters if you want to do something really custom. It’s all Keras so the code is easy to understand and dive into, allowing developers to quickly create accurate models and researchers to take a deeper dive into architecture search. Auto Keras has everything a great open source project should have: quick install, easy to run, lots of examples, easy to modify, and you even get to see the network model that NAS found out at the end! Auto Keras: The Killer of Google’s AutoML | George Seif - KDnuggets
