In 2015 IBM announced that “100 of its Watson partners have now introduced cognitive enabled apps, products and services into the market.” At the time this was billed by IBM as a major milestone and validation that IBM was building an AI Platform that would rival the Mainframe, PC, Cloud and Mobile. I know this because I was there. Of course each of those previous ‘eras’ did produce game-changing Platforms led by the IBM 360, Windows, AWS and IOS. Watson never achieved Platform status, but instead became a brand that encompasses technology, products and services.
Last month OpenAI announced that…
Over the weekend, I came across the video for a class I taught almost a year ago on Cognitive Computing. Wow time flies..
The goal of this introductory class was 3 fold: 1) Define cognitive computing (trying to move away from the buzzword), 2) introduce machine learning and machine perception concepts to a non-technical audience and 3) highlight machine learning best practices that we’ve learned through building apps with Watson Ecosystem partners. And wrap all of this in as many demos as possible.
First thing I concluded is that I would have been better…
Back in May, my colleague Alisha Lehr and I had the opportunity to speak at Twilio’s Signal developer conference where we launched and demoed 2 Watson/Twilio Add-ons in their new marketplace. The Twilio team is amazing and a model for anyone who wants to build great tools for developers. This week we put the code for one of the demos up on github with a simple tutorial. Check it out!
The Message Insights add-on leverages Watson entity, keyword, concept extraction and targeted sentiment to enrich SMS messages with meaningful metadata.
The Message Sentiment add-on leverages Watson document sentiment.
As discussed in Part 1 and Part 2, the IBM Watson Retrieve and Rank service enables developers to configure a solr search cluster on IBM Bluemix and train a machine-learning powered ranking model to improve the relevance of search results.
R&R has a set of native feature scorers that score lexical overlap between a given query/document pair. Those scores are generated through a custom solr plugin in Retrieve. Scores are then sent to the ranker which outputs a ranked list of documents for the query based on its learning. Depending on solr configuration, each feature will score various fields or…
I’ll maintain this article for useful links to Watson (and other relevant ML) resources.
IBM Watson Github — https://github.com/IBM-Watson
WDC GIT Repo — https://github.com/watson-developer-cloud
Cognitive Catalyst — https://github.com/cognitive-catalyst
Alchemy Blog — http://blog.alchemyapi.com/
Alchemy SDK Home — http://www.alchemyapi.com/developers/sdks
Zach W Blog — http://blog.alchemyapi.com/author/zach-walchuk
Anthony S GIT — https://github.com/biosopher
Ryan A GIT — https://github.com/rustyoldrake/R_Scripts_for_Watson
Chris M GIT — https://github.com/tankcdr?tab=repositories
Chris M Blog — http://cmadison.me/
Ryan A Blog — https://dreamtolearn.com/ryan/r_journey_to_watson
Dan T Blog — https://dtoczala.wordpress.com/
I recently put together a lab to help developers understand how to integrate the Natural Language Classifier, Retrieve and Rank, and Dialog services to build a virtual agent for support desk. We typically complete this lab (among others) during Architecture Workshops which are a formal offering of the Watson Ecosystem so the instructions are a little less explicit then you might expect, but no reason developers could not complete the lab independently if you work with the WDC documentation and API reference. The code can be found on github.
Virtual Agent is a self-service engagement application that helps a user…
In Part 1 we stood up a Retrieve and Rank cluster on Bluemix and configured solr. In Part 2 we will build our ground truth and train and test our ranker.
If machine learning can be defined as a set of techniques to make predictions from data where the performance of those predictions improves with experience, then ground truth is the experience. In the case of Retrieve and Rank, ground truth comprises examples of input questions and output documents with associated relevance labels. A perfect answer should get a high relevance score and a bad answer, a low score. …
The Retrieve and Rank (R&R) service on the Watson Developer Cloud is a great tool that enables enhancement of standard search implementations with natural language and machine learning capabilities. R&R is really 2 services bolted together. Retrieve is Apache Solr in the cloud and offers all the rich feature set of Solr. There are 2 visible enhancements: 1) a custom query builder optimized for natural language search and 2) a set of algorithms to score semantic relationships between a given query and a Solr document which get fed into the Rank portion of R&R. …
I lead AI Product Development at AlphaSense. I'm interested in sharing what I've learned about productizing AI