kmcowan, Author at Capture Club - Page 2 of 4

Case Study: Sphere and the Case of Contextually Related Content.

We began working with related content provider Sphere over a decade ago.  Sphere was the nexus between thousands of “long-tail” bloggers (E.g. private individuals) and high-volume news sites like CNN, Time and the Wall St. Journal.  Personally, I would say that it was easily one of my most exciting opportunities.  Working there, you really felt […]

kmcowan 1 August, 2018 0

Why a ‘Research’ Engine is better than Search.

Why would you want to use a Research Engine over a Search Engine?  The answer is simple:  You want a more in-depth answer than a search engine could ever provide.  When we first started showing our platform to the world, the first thing we heard was:  “Oh, okay, so you’re a search engine.” Well, no, […]

kmcowan 27 July, 2018 2

HAIDIE: Heuristic Analytics Integrated Data Interpretation Engine

HAIDIE — Heuristic Analytics Integrated Data Interpretation Engine In metaphorical terms, HAIDIE rules the roost.  It uses near-real-time Machine Learning coupled with the persisted Deep Learning data provided by EMPATHS to predict highly-relevant responses to your question.   We do this via a set of proprietary cross-validation algorithms coupled with industry standard TF*IDF and BM25.  Under […]

TAME: Truly Asynchronous Messaging Environment

When we talk about asynchronous communication on the internet, we’re not really talking about pure asynchronicity.   When a JavaScript client makes a standard AJAX request, it is waiting for a response — a single response — and that completes that particular communication event.  The reason this is called “asynchronous” is because it happens after the […]

kmcowan 26 July, 2018 0

Capture Club Predictive Research Engine Architecture

We are NOT a Search Engine.  We are a Research Engine. Over the years, we have developed a fast, robust, resource-friendly, distributed framework for handling near-real-time Machine Learning and Predictive Analytics. From a high-level, our architecture looks like this: External datasources (E.g. websites, documents, file systems, etc) are ingested using our proprietary Indexing Engine, and […]

Natural Language Processing

Natural language processing is the process of identifying semantic elements contained in text.  Basically,  provide context to works in a sentence.  Semantic elements are usually extracted using a sentence structure that defines elements such as nouns and verbs.   But what if your content is a just a “utterance” or incomplete sentence that has no punctuation or capitalization?  […]

ZEN

Zero Experience Necessary (ZEN) The method of application development that uses a conversational agent to assist and direct users to achieve their end goal while using a piece of software.   The application developer knows far more than anyone else in what the application can do.    The “interaction” with the user is required to get “input” […]

Our Enterprise Application Service Offerings

Applications and Services offered by Capture Club –    The HAIDIE-ZEN Research Engine        Our Research Engine uses near-real-time Machine Learning and persisted Deep-Learning to provide a rich, highly-relevant result set. –    Natural Language Search Analysis:       Using natural language parsing and heuristic text analytics, our search technology is able to compare a spoken […]

kmcowan 22 July, 2018 0

MemeFinder: No Dictionaries Needed

When I was working for the related content provier Sphere, I was presented with an interesting problem. We were using Apache Lucene back before using Lucene was cool, and overall it worked very well. However, there were some contextual gotchas that were causing them trouble. Homonyms, in particular, were causing un-related results to appear. Being […]