TensorFlow Technology
- 2. Agenda 1. What is TensorFlow? 2. How to install on windows? 3. Why would you use it? 4. How does it works? 5. Who will use it?
- 4. What is Tensorflow? • Python-based neural network framework • Google open source project on Github • Released November 2015 • Runs highly optimized C++ code for actual calculations • Higher level APIs on top of tensorflow available, like skflow to fit within the Scikit Learn API • TensorFlow provides primitives for defining functions on tensors and automatically computing their derivatives. • opensource
- 5. Tensor? Simply put: Tensors can be viewed as a multidimensional array of numbers. This means that: ● A scalar is a tensor, ● A vector is a tensor, ● A matrix is a tensor
- 6. Data Flow Graph? ● Computations are represented as graphs: ● Nodes are the operations (ops) ● Edges are the Tensors (multidimensional arrays)
- 7. Installation on windows ● Download Anaconda ● Create an environment with all must-have libraries. $ conda create -n tensorflow python=3.5 $ activate tensorflow $ conda install pandas matplotlib jupyter notebook scipy scikit $ pip install tensorflow
- 8. Why would you use NN? Neural Networks (NNs) are universal function approximators that work very well with huge datasets ● NNs / deep networks do unsupervised feature learning ● Track record, being SotA in: ○ image classification, ○ language processing, ○ speech recognition,
- 9. Neural Machine Translation Neural Machine Translation
- 10. Recurrent Neural Networks for Drawing Classification
- 12. Advantage of TensorFlow - Cross platform - android ,linux, etc - Quick turn around to production - Effiient computaion utlizing cpu, gpu - Neural Machine Translation - Image Recognition
- 13. What is a Convolutional Neural Network?
- 14. Companies using Tensorflow ● Google ● OpenAI ● DeepMind ● Snapchat ● Uber ● Airbus ● eBay ● Dropbox
- 15. Thank you