Difference between revisions of "Google"
| Line 13: | Line 13: | ||
* [[TensorFlow]] | * [[TensorFlow]] | ||
* [http://www.tensorflow.org/hub TensorFlow Hub] is a library for reusable machine learning modules that you can use to speed up the process of training your model. A [[TensorFlow]] module is a reusable piece of a [[TensorFlow]] graph. With transfer learning, you can use [[TensorFlow]] modules to preprocess input feature vectors, or you can incorporate a [[TensorFlow]] module into your model as a trainable layer. This can help you train your model faster, using a smaller dataset, while improving generalization. | * [http://www.tensorflow.org/hub TensorFlow Hub] is a library for reusable machine learning modules that you can use to speed up the process of training your model. A [[TensorFlow]] module is a reusable piece of a [[TensorFlow]] graph. With transfer learning, you can use [[TensorFlow]] modules to preprocess input feature vectors, or you can incorporate a [[TensorFlow]] module into your model as a trainable layer. This can help you train your model faster, using a smaller dataset, while improving generalization. | ||
| − | * [[AI Hub]] - explore and use a variety of AI asset categories. [[AI Hub]] offers a collection of components for developers and data scientists building artificial intelligence (AI) systems. Use [[AI Hub]] to: [1] | + | * [[AI Hub]] - explore and use a variety of AI asset categories. [[AI Hub]] offers a collection of components for developers and data scientists building artificial intelligence (AI) systems. Use [[AI Hub]] to: [1] Find, deploy, and use [[Kubeflow Pipelines]] and components, [2] explore code and learn in interactive [[Jupyter]] notebooks, [3] explore and reuse [[TensorFlow]] modules, Explore, deploy, and use trained models, [4] use prepackaged virtual machine (VM) images to quickly set up your AI environment, and [5] share AI components with your colleagues. |
| − | Find, deploy, and use [[Kubeflow Pipelines]] and components, [2] explore code and learn in interactive [[Jupyter]] notebooks, [3] explore and reuse [[TensorFlow]] modules, Explore, deploy, and use trained models, [4] use prepackaged virtual machine (VM) images to quickly set up your AI environment, and [5] share AI components with your colleagues. | ||
* [http://deepmind.com/research/open-source/ DeepMind - Open Source] | * [http://deepmind.com/research/open-source/ DeepMind - Open Source] | ||
** [[Google DeepMind AlphaGo Zero]] | ** [[Google DeepMind AlphaGo Zero]] | ||
Revision as of 18:12, 2 October 2019
YouTube search... ...Google search
- Platforms: Machine Learning as a Service (MLaaS)
- Colaboratory (Colab) - Jupyter notebooks
- Google Developers Codelabs
- TensorFlow
- TensorFlow Hub is a library for reusable machine learning modules that you can use to speed up the process of training your model. A TensorFlow module is a reusable piece of a TensorFlow graph. With transfer learning, you can use TensorFlow modules to preprocess input feature vectors, or you can incorporate a TensorFlow module into your model as a trainable layer. This can help you train your model faster, using a smaller dataset, while improving generalization.
- AI Hub - explore and use a variety of AI asset categories. AI Hub offers a collection of components for developers and data scientists building artificial intelligence (AI) systems. Use AI Hub to: [1] Find, deploy, and use Kubeflow Pipelines and components, [2] explore code and learn in interactive Jupyter notebooks, [3] explore and reuse TensorFlow modules, Explore, deploy, and use trained models, [4] use prepackaged virtual machine (VM) images to quickly set up your AI environment, and [5] share AI components with your colleagues.
- DeepMind - Open Source
- AI Platform
- Google Natural Language
- Kubeflow Pipelines ML workflows on Kubernetes
- Google Cloud
- Google Cloud Code and Google Kubernetes Engine (GKE)
- Google AutoML
- Cloud Vision
- Cloud Vision API - drag & drop picture on webpage
- Automated Machine Learning (AML) - AutoML
- We’re making tools and resources available so that anyone can use technology to solve problems | Google AI
- Dopamine - reinforcement learning algorithms
- Google AI Experiments
- ML Engine
- Prediction API
- Grow with Google
- Learn from ML experts at Google
- Tools and Resources
- Google Internet of Things (IoT)
- Psychlab for testing virtual agents in 3D environments
- Deep Reinforcement Learning (DRL) - Importance Weighted Actor-Learner Architecture (IMPALA)
- Google AIY Projects Program
- Android Neural Networks API
- BiqQuery ML (BQML)
- Firebase | Google
- DialogFlow
- Bidirectional Encoder Representations from Transformers (BERT)
- Google Analytics
- Gboard on Pixel phones now uses an on-device neural network for speech recognition | Kyle Wiggers - VentureBeat
The Path From Cloud AutoML to Custom Model (Cloud Next '19)
by Sara Robinson
