I got a note recently that I should try Obie as a chat bot based on corporate knowledge provided in Slack. I have now used Slack for several projects, fine as a chat space for team projects, somewhat quirky, hard to integrate with typical and existing knowledge streams. One of our AI goals had been to figure out how to link AI with corporate knowledge streams, old and new, static and dynamic, internal, supplier and public knowledge, structured and unstructured. A remembrance engine we called it. Perhaps a Knowledge Graph? Is that what we are approaching here.? Back to the wall we ran into: How will it be maintained? Just by updates in chats? Back to the general problem of intelligent dialog.
Q&A With the Developers of Obie: A Chatbot for Company Knowledge by Roland Meertens
Tasytt launched Obie: a Slack chatbot for company knowledge. Teams can ask "what, how, or where" questions such as "What is our computer policy". Obie either finds the answer in one of your documents or will ask you to provide him with the answer so he can give it next time someone asks the same questions.
Obie has integrations with several existing services: Google Docs, Confluence, Google sites, Evernote and Dropbox. This means companies don't have to start from the ground up with training Obie. Giving Obie access to this existing knowledge ensures a short training period for Obie.
InfoQ reached out to founder and CEO Chris Buttenham to ask him some questions about Obie.
InfoQ: We tried Obie a little bit in our Slack, but had the idea that it did not analyze our previous conversations. Is this a feature that will be added in a future version?
You could probably imagine you’re not the first to ask this question! Although it would seem that content living in Slack would be a natural place Obie would start, we actually feel that most conversations are fairly unstructured and somewhat useless when it comes to organizing team knowledge. We’re definitely considering adding content that lives within Slack as something Obie can reference, but we feel the low hanging fruit is the rich content scattered across multiple sources within an organization. ... "
Showing posts with label Obie. Show all posts
Showing posts with label Obie. Show all posts
Monday, June 26, 2017
Wednesday, January 11, 2017
Transfer Learning for AI Projects
Had always thought that intelligence was about learning, so this concept struck me. Note mention of improbable events and model correctness maintenance, always of concern in such studies. Technical.
'Transfer learning' jump-starts new AI projects
Machine learning, once implemented, tends to be specific to the data and requirements of the task at hand. Transfer learning is the act of abstracting and reusing those smarts
'Transfer Learning' Jump-Starts New AI Projects in InfoWorld by James Kobielus
Abstracting and reusing knowledge gleaned from a machine-learning application in other, newer apps--or "transfer learning"--is supplementing other learning methods that constitute the backbone of most data science practices. Among the technique's practical uses is productivity acceleration modeling, which is viable when prior work can be reused without extensive revision in order to speed up time to insight. Another transfer-learning application involves the method helping scientists produce machine-learning models that exploit relevant training data from prior modeling projects.
This technique is particularly appropriate for addressing projects in which prior training data can easily become obsolete, which is a problem that frequently occurs in dynamic problem domains. A third area of data science in which transfer learning could yield benefits is risk mitigation. In this situation, transfer learning can help scientists leverage subsets of training data and feature models from related domains when the underlying conditions of the modeled phenomenon have radically changed.
This can help researchers ameliorate the risk of machine-learning-driven predictions in any problem domain vulnerable to extremely improbable events. Transfer learning also is critical to data scientists' efforts to create "master learning algorithms" that automatically obtain and apply fresh contextual knowledge via deep neural networks and other forms of artificial intelligence. ... "
'Transfer learning' jump-starts new AI projects
Machine learning, once implemented, tends to be specific to the data and requirements of the task at hand. Transfer learning is the act of abstracting and reusing those smarts
'Transfer Learning' Jump-Starts New AI Projects in InfoWorld by James Kobielus
Abstracting and reusing knowledge gleaned from a machine-learning application in other, newer apps--or "transfer learning"--is supplementing other learning methods that constitute the backbone of most data science practices. Among the technique's practical uses is productivity acceleration modeling, which is viable when prior work can be reused without extensive revision in order to speed up time to insight. Another transfer-learning application involves the method helping scientists produce machine-learning models that exploit relevant training data from prior modeling projects.
This technique is particularly appropriate for addressing projects in which prior training data can easily become obsolete, which is a problem that frequently occurs in dynamic problem domains. A third area of data science in which transfer learning could yield benefits is risk mitigation. In this situation, transfer learning can help scientists leverage subsets of training data and feature models from related domains when the underlying conditions of the modeled phenomenon have radically changed.
This can help researchers ameliorate the risk of machine-learning-driven predictions in any problem domain vulnerable to extremely improbable events. Transfer learning also is critical to data scientists' efforts to create "master learning algorithms" that automatically obtain and apply fresh contextual knowledge via deep neural networks and other forms of artificial intelligence. ... "
Friday, July 25, 2014
Cognitive Computing Webinar and Resources
New World of Cognitive Computing. Yesterday attended a webinar on Cognitive Computing. Which was a fairly good introduction, non technical and suitable for an extended technical executive introduction. Recorded one hour presentation is here. Just the slides here.
Panelists: Steve Ardire, James Kobielus (IBM), Adrian Bowles and Tony Sarris
" .. Cognitive Computing is a rapidly developing technology that has reached practical application and implementation. So what is it? Do you need it? How can it benefit your business?
In this webinar a panel of experts in Cognitive Computing will discuss the technology, the current practical applications, and where this technology is going. The discussion will start with a review of a recent survey produced by DATAVERSITY on how Cognitive Computing is currently understood by your peers. The panel will also review many components of the technology including:
Cognitive Analytics
Machine Learning
Deep Learning
Reasoning
And next generation artificial intelligence (AI) ... "
Panelists: Steve Ardire, James Kobielus (IBM), Adrian Bowles and Tony Sarris
" .. Cognitive Computing is a rapidly developing technology that has reached practical application and implementation. So what is it? Do you need it? How can it benefit your business?
In this webinar a panel of experts in Cognitive Computing will discuss the technology, the current practical applications, and where this technology is going. The discussion will start with a review of a recent survey produced by DATAVERSITY on how Cognitive Computing is currently understood by your peers. The panel will also review many components of the technology including:
Cognitive Analytics
Machine Learning
Deep Learning
Reasoning
And next generation artificial intelligence (AI) ... "
Subscribe to:
Posts (Atom)