Live coding session on AI / ML using Google Tensorflow (Python) - Tanmoy Deb (Equonix Techlab Pvt. Ltd.)
0 likes142 views
The document presents an overview of TensorFlow as a machine learning library, highlighting its capabilities for deep learning, distributed and parallel processing on various devices. It contrasts deep learning with traditional machine learning and discusses TensorFlow's architecture, benefits, and application examples. The presentation is by Tanmoy Deb, founder and CEO of Equonix Tech Lab, aiming to enlighten on the future of intelligent applications using TensorFlow.
Live coding session on AI / ML using Google Tensorflow (Python) - Tanmoy Deb (Equonix Techlab Pvt. Ltd.)
- 1. Tensorflow in Data Prediction Presented By : TANMOY DEB Founder and CEO Equonix Tech LAB
- 2. AGENDA ❑ Deep Learning ❑ What is TensorFlow ❑ Under the hood ❑ Resources ❑ Examples
- 3. 3 About EQUONIX TECH LAB
- 5. 5 Deep Learning vs Old Machine Learning
- 6. How big is the data set?
- 7. 7 Results with Deep Learning
- 8. 8 Growth of Deep Learning in Google
- 9. 9 Important Property of Neural Networks Results get better with More data + Bigger models + More computation (Better algorithms, new insights, and improved techniques always help, too!)
- 11. 11 What is TensorFlow? • TensorFlow is a machine learning library enabling researchers and developers to build the next generation of intelligent applications. • Provides distributed, parallel machine learning based on general-purpose dataflow graphs • Targets heterogeneous devices: • single PC with CPU or GPU(s) • mobile device • clusters of 100s or 1000s of CPUs and GPUs
- 12. 12 Benefits of Tensorflow • General computational infrastructure • Works well for Deep Learning • Deep Learning is a set of libraries on top of the core • Also useful for other machine learning algorithms, maybe even more traditional high performance computing (HPC) work • Abstracts away the underlying devices
- 13. 13
- 14. 14
- 16. 16 Deep Learning vs Machine Learning
- 17. 17 Computation is a dataflow graph
- 18. 18 TensorFlow contains complete algorithms • Linear{Classifier,Regressor} • DNN{Classifier,Regressor} • DNNLinearCombined{Classifier,Regressor} • SVM • KMeansClustering • GMM
- 19. 19 Simple machine learning 1. classifier = learn.LinearClassifier(feature_columns=feature_co lumns, n_classes=10) 2. classifier.fit(data, labels, batch_size=100, steps=1000) 3. classifier.evaluate(eval_data, eval_labels) Tooling provided for distributed training and evaluation, graphical debugging, and export to production server (tensorflow/serving).
- 21. EXAMPLES
- 22. Announcements
- 23. Contact Me email : tanmoydeb@equonix.com mob: 9560633668 whatsapp : 9560633668
- 24. 24 Thank You