Downloaded 235 times
Uploaded byDataWorks Summit/Hadoop Summit
Machine Intelligence at Google Scale: TensorFlow
- TensorFlow is Google's open source machine learning library for developing and training neural networks and deep learning models. It operates using data flow graphs to represent computation. - TensorFlow can be used across many platforms including data centers, CPUs, GPUs, mobile phones, and IoT devices. It is widely used at Google across many products and research areas involving machine learning. - The TensorFlow library is used along with higher level tools in Google's machine learning platform including TensorFlow Cloud, Machine Learning APIs, and Cloud Machine Learning Platform to make machine learning more accessible and scalable.
More Related Content
Similar to Machine Intelligence at Google Scale: TensorFlow
More from DataWorks Summit/Hadoop Summit
Machine Intelligence at Google Scale: TensorFlow
- 1. Machine Intelligence atGoogle Scale: TensorFlow
- 2. Data is Everything. Howwell you use your data can determine the degree of your success.
- 3. What is MachineLearning? data algorithm insight
- 4.
- 5.
- 6. Human: Someone is usinga small grill to melt his sandwich. Neural Model: A person is cooking some food on a grill.
- 7. One example (of100s): “Neural Art” in TensorFlow An implementation of "A neural algorithm of Artistic style" in TensorFlow, for ● Introductory, hackable demos for TensorFlow, and ● Demonstrating the use of importing various Caffe cnn models (VGG and illustration2vec) in TF. github.com/woodrush/neural-art-tf
- 8. Growing Use ofDeep Learning at Google Number of directories containing model description files UniqueProjectDirectories Q1 Q2 Q3 Q4 Q1 Q2 Q3 Q4 Q1 Q2 Q3 Q4 Q1 Q2 Q3 2000 1500 1000 500 0 Across many products/areas ● Apps ● Maps ● Photos ● Gmail ● Speech ● Android ● YouTube ● Translation ● Robotics Research ● Image Understanding ● Natural Language Understanding ● Drug Discovery 2012 2013 2014 2015 Q4
- 9. The Machine LearningSpectrum TensorFlow Cloud Machine Learning Machine Learning APIs Data Scientist
- 10.
- 11. ● Google's opensource library for machine intelligence ● Tensor: N-dimensional array ● Flow: data flow computation framework (like MapReduce) ● tensorflow.org launched in Nov 2015 ○ Most popular Machine Learning library ○ 20,000+ stars / 7000+ forks ○ 165 contributors / > 3000 commits What is TensorFlow?
- 12. Portable ● Training on: ○Data Center ○ CPUs, GPUs and etc ● Running on: ○ Mobile phones ○ IoT devices
- 13. Computation as aDataflow Graph Graph of Nodes, also called operations (ops) MatMul Add Softmax biases weights inputs targets Xent
- 14. Dataflow Graph (forward) Edgesare N-dimensional arrays: Tensors MatMul Add Softmax biases weights inputs targets Xent
- 15. Dataflow Graph (backwardgraph and updates) Backward graph and update are added automatically to graph Add Mul biases ... learning rate −=... 'Biases' is a variable −= updates biasesSome ops compute gradients
- 16. Dataflow Graph ● Inpractice often very complex with 100s or 1000s of nodes and edges ● “Inference” means to execute just the forward path of the graph
- 17. Example: Logistic Regression 1.N examples of data ○ Input xn ○ Target tn 2. Model with parameters (weights W, biases b) ○ yn = Softmax(W * xn + b) 3. CrossEntropy loss to minimize ○ loss = -Sum(tn * ln(yn )) 4. Minimization by Gradient Descent ○ requires gradients of loss with respect to parameters W, b ● TensorFlow does automatic differentiation ● Gradient calculation done by TF once model & loss defined
- 18.
- 19.
- 20. Portable ● Training on: ○Data Center ○ CPUs, GPUs and etc ● Running on: ○ Mobile phones ○ IoT devices
- 21.
- 22. The Machine LearningSpectrum TensorFlow Cloud Machine Learning Machine Learning APIs Application Developer Data Scientist
- 23. Cloud Machine LearningPlatform Pre-Processing Training ML Authoring ML Analysis Hosted Model Monitoring & Logging Training Prediction ● Intelligent Text Processing ● Image Feature Processing ● Managed Infrastructure ● Scalable Algorithms ● HW Acceleration Evaluation ● Detailed Model Metrics ● In-process model viz ● No-ops experience Batch Real-Time input output ● Hosted Model experience ● AutoScaling ● Anytime access Data Console Model & Job Mgmt Datalab
- 24. Can I HugThat?
- 25. Can I HugThat? Images Labels Trained Classifier Question Hug / Not Hug
- 26.
- 28. Confidential & ProprietaryGoogleCloud Platform 28 Easy to use API: pass in an image, we give you insight: Google Cloud Vision API Label Detection OCR Explicit Content Detection Facial Detection Landmark Detection Logo Detection