"The Future of Machine Learning & JavaScript"Asim Hussain
0 likes941 views
The document discusses the future of machine learning with a focus on JavaScript, neural networks, and their applications in web development. It highlights the power of neural networks, their conceptual simplicity, and tools like TensorFlow.js and MobileNet for image analysis. Additionally, it mentions Generative Adversarial Networks (GANs) for image generation, emphasizing the computational requirements and browser compatibility for model execution.
"The Future of Machine Learning & JavaScript"Asim Hussain
- 1. The Future of Machine Learning & JavaScript @jawacheNodeUkraine 2019
- 5. @jawache
- 8. @jawache
- 16. (2) Use a Neural Network @jawache
- 22. 1.1 4.2 0.3 4 12 93 @jawache 8 - 8 = -53 Neural Networks
- 23. 1.1 4.2 0.3 4 12 93 @jawache - 8 = -53 8 Neural Networks
- 26. https://<region>.api.cognitive.microsoft.com/face/v1.0/detect { "url": "<path-to-image>" } @jawache
- 27. @jawache
- 28. Summary @jawache
- 29. • Neural Networks are incredibly powerful • Conceptually, they are simple to understand @jawache Summary
- 31. @jawache
- 32. @jawache
- 33. @jawache
- 37. https://azure.microsoft.com/services/cognitive-services/computer-vision/ @jawache
- 42. Summary @jawache
- 43. • TensorFlow.js doesn't have any dependancies • MobileNet is a simple way to analyse images • Azure Computer Vision API ❤ @jawache Summary
- 49. @jawache
- 50. @jawache
- 51. @jawache
- 57. Summary @jawache
- 58. • GANs learn to generate new images • They take a lot of compute to train • But the generator model can be run in the browser @jawache Summary