COGNITIVE SERVICES MACHINE LEARNING FOR DEVELOPERS Chris Noring
- Slides: 33
COGNITIVE SERVICES MACHINE LEARNING FOR DEVELOPERS Chris Noring @chris_noring
Machine Learning finds patterns in data and uses those patterns to predict the future @chris_noring
WHAT FOOTBALL TEAM IS GOING TO WIN THE LEAGUE? DETECTING CREDIT CARD FRAUD What can we use it for? DETERMINING WHETHER A CUSTOMER IS LIKELY TO SWITCH TO A COMPETITOR DETERMINE WHEN TO DO PREVENTIVE MAINTENANCE ON A ROBOT @chris_noring
Takes lots of data, the more data, the better our predictions Takes lots of compute power Why is ML popular? We have effective machine learning algorithms Do you know what takes a lot of computing power? @chris_noring
Business leaders, wants solutions to problems Who Benefits? Software developers, wants to create better applications Data Scientists, wants powerful, easy-to-use tools @chris_noring
Machine Learning – NN and Math @chris_noring
Programming Algorithm Answers Data @chris_noring
Machine Learning Answers Algorithm Data @chris_noring
Machine Learning Answers Model Data @chris_noring
Machine Learning Answers Data Model Predictions Data @chris_noring
Artificial Intelligence @chris_noring
Microsoft AI Platform Azure AI Services Tools Azure Infrastructure @chris_noring
Microsoft AI Platform Azure AI Services Tools Azure Infrastructure @chris_noring
Azure Cognitive Services A set of simple APIs that harness Machine Learning so you can add AI (without needing a deep understanding of AI) @chris_noring
Azure Cognitive Services Vision Image Tagging, Thumbnails OCR, Handwriting recognition Customized image recognition Face detection Emotion recognition Video insights - people detection, visual search, keyframe detection, object recognition Image and video moderation Speech to text (Speech Transcription) Customized speech Transcription (complex word, noisy environment) Text to speech Speaker ID and authentication Real-time speech translation Language Contextual language understanding – customized intent analysis Sentiment analysis, key phrase detection text translation up to 60+ languages Text Moderation Spell checking Knowledge Customized decision making with reinforcement learning Q&A service and bot training with personality Search Visual Search with object detection Comprehensive news, image, and video results Custom Search Tailored and customized search experiences Automatic search suggestions Entity information augmentation @chris_noring
How to use? Header Ocp-Apim-Subscription-Key Base URL https: //westeurope. api. cognitive. microsoft. com Specific API URL text/analytics/v 2. 1/languages @chris_noring
Sending/receiving let documents = { 'documents': [{ 'id': '1’, 'text': 'This is a document written in English. ’ }, { 'id': '2', 'text': 'Este es un document escrito en Español. ’ } ] }; { "documents": [{ "id": "1", "detected. Languages": [{ "name": "English", "iso 6391 Name": "en", "score": 1 }] }, { "id": "2", "detected. Languages": [{ "name": "Spanish", "iso 6391 Name": "es", "score": 1 }] }], "errors": [] module. exports = documents; } @chris_noring
Language detection Sentiment analysis (bad or good) Let’s focus on Language APIs Key phrase detection Translation and more… @chris_noring
DEMO text, keyphrase, sentiment @chris_noring
GOOD: I REALLY ENJOY THE NEW XBOX ONE S. IT HAS A CLEAN LOOK, IT HAS 4 K/HDR RESOLUTION AND IT IS AFFORDABLE. BAD: ESTE HA SIDO UN DIA TERRIBLE, LLEGUÉ TARDE AL TRABAJO DEBIDO A UN ACCIDENTE AUTOMOBILISTICO. Sentiment analysis This is about determining whether something is good or bad @chris_noring
Thumbnails OCR with handwriting Let’s focus on Vision APIs Customized image recognition Face detection Emotion recognition @chris_noring
Sometimes the Cognitive service is not good enough
Sometimes the services are not enough When you need a better Model The Model is not specific enough Then you can train the Model yourself @chris_noring
Azure Custom Cognitive Services Vision Image Tagging, Thumbnails OCR, Handwriting recognition Customized image recognition Face detection Emotion recognition Video insights - people detection, visual search, keyframe detection, object recognition Image and video moderation Speech to text (Speech Transcription) Customized speech Transcription (complex word, noisy environment) Text to speech Speaker ID and authentication Real-time speech translation Language Knowledge Search Contextual language understanding – customized intent analysis Customized decision making with reinforcement learning Visual Search with object detection Sentiment analysis, key phrase detection Q&A service and bot training with personality text translation up to 60+ languages Text Moderation Spell checking Comprehensive news, image, and video results Custom Search Tailored and customized search experiences Automatic search suggestions Entity information augmentation @chris_noring
Custom Vision API When the vision API model isn’t good enough • When you want to detect a specific person • When you want to identify a specific tool over “tools” • https: //www. customvision. ai/ • Add tags • Train with images • Choose iteration and use API @chris_noring
• Select a model in the right domain Select • Create all the tags you need Create Train an existing model • Upload an image and assign a tag Upload • Train = produce iteration Train Call
Test our model with an API call
DEMO Custom Vision, upload file @chris_noring
Summary Cognitive Services is ML for Developers There are tons of REST APIs, you just need a key Send JSON and get JSON Major areas: Vision, Speech, Language, Knowledge, Search You can make models better by training them with images in customvision. ai, any service marked as custom, can be trained @chris_noring
Thank you • • aka. ms/azure-signup-cogservices customvision. ai aka. ms/azure-textapis aka. ms/azure-cogservices-overview @chris_noring
- Cognitive and non cognitive religious language
- Sql server machine learning services
- Concept learning task in machine learning
- Analytical learning in machine learning
- Pac learning model in machine learning
- Machine learning t mitchell
- Inductive vs analytical learning
- Combining inductive and analytical learning
- Instance based learning in machine learning
- Inductive learning machine learning
- First order rule learning in machine learning
- Eager learning algorithm
- Deep learning vs machine learning
- Labana developers
- Moodle developers
- Erp for real estate developers
- Krowemo meaning
- Sticky notes developers
- Inutamago
- Bon patron
- Reactive extensions net core
- Facbook
- Developers google speed
- Dr tracy hall
- Manitoba prospectors and developers association
- Game developers
- Google forms developers
- Aesthetics developers
- Builders and property developers module in tally.erp 9
- Developers android com
- Android boot camp for developers using java
- Android boot camp for developers using java
- Cuadro comparativo entre e-learning b-learning y m-learning
- Python azure cognitive services