ai-one’s Biologically Inspired Neural Network

February 1st, 2015

ai-one’s Learning Algorithm: Biologically Inspired Neural Network
– Introduction to HSDS vs ANN in Text Applications

Unlike any of the traditional neural nets, the neural network based on ai-one, the HoloSemantic Data Space neural network (invented by Manfred Hoffleisch) or in short “HSDS”, are massively connected, asymmetrical graphs which are stimulated by binary spikes. HSDS do not have any neural structures pre-defined by the user. Their building blocks resemble biological neural networks: a neuron has dendrites, on which the synapses from other neurons are placed, and an axon which ends in synapses at other neurons.

The connections between the neurons emerge in an unsupervised manner while the learning input is translated into the neural graph structure. The resulting graph can be queried by means of specific stimulations of neurons. In traditional neural systems it is necessary to set up the appropriate network structure at the beginning according to what is to be learned. Moreover, the supervised learning employed by neural nets such as the perceptron requires that a teacher be present who answers specific questions. Even neural nets that employ unsupervised learning (like those of Hopfield and Kohonen) require a neighborhood function adapted to the learning issue. In contrast, HSDS require neither a teacher nor a predefined structure or neighborhood function (note that although a teacher is not required, in most applications programmatic teaching is used to insure the HSDS has learned the content needed to meet performance requirements). In the following we characterize HSDS according to their most prominent features.

Exploitation of context

In ai-one applications like BrainDocs, HSDS is used for the learning of associative networks and feature extraction. The learning input consists of documents from the application domains, which are broken down into segments rather than entered whole: all sentences may be submitted as is or segmented into sub-sentences according to grammatical markers. By way of experimenting, we have discovered that a segment should ideally consist of 7 to 8 words. This is in line with findings from cognitive psychology. Breaking down text documents into sub-sentences is the closest possible approximation to the ideal segment size. The contexts given by the sub-sentence segments help the system learn. The transitivity of term co-occurrences from the various input contexts (i.e. segments) are a crucial contribution to creating appropriate associations. This can be compared with the higher-order co-occurrences explored in the context of latent semantic indexing.

Continuously evolving structure
The neural structure of a HSDS is dynamic and changes constantly in line with neural operations. In the neural context, change means that new neurons are produced or destroyed and connections reinforced or inhibited. Connections that are not used in the processing of input into the net for some time will get gradually weaker. This effect can also be applied to querying, which then results in the weakening of connections that are rarely traversed for answering a query.

Asymmetric connections
The connections between the neurons need not be equally strong on both sides and it is not necessary that a connection should exist between all the neurons (cp. Hopfield’s correlation matrix).

Spiking neurons
The HSDS is stimulated by spikes, i.e. binary signals which either fire or do not. Thresholds do not play a role in HSDS. The stimulus directed at a neuron is coded by the sequence of spikes that arrive at the dendrite.

Massive connectivity
Whenever a new input document is processed, new (groups of) neurons are created which in turn stimulate the network by sending out a spike. Some of the neurons reached by the stimulus react and develop new connections, whereas others, which are less strongly connected, do not. The latter nevertheless contribute to the overall connectivity because they make it possible to reach neurons which could not otherwise be reached. Given the high degree of connectivity, a spike can pass through a neuron several times since it can be reached via several paths. The frequency and the chronological sequence in which this happens determine the information that is read from the net

General purpose
There is no need to define a topology before starting the learning process because the neural structure of the HSDS develops on its own. This is why it is possible to retrieve a wide range of information by means of different stimulation patterns. For example, direct associations or association chains between words can be found, the words most strongly associated with a particular word can be identified, etc.

Rumsfeld Conundrum- Finding the Unknown Unknown

January 27th, 2015

Since we began the process of building applications using our AI engine, we have been focused on working with ideas or concepts. With BrainDocs we built intelligent agents to find and score similarity for ideas in paragraphs, but still fell short of the vision we have for our solution. Missing was an intuitive and visual UI to explore content interactively using multiple concepts and  metadata (like dates, locations, etc). We want to give our users the power to create a rich and personal context to power through their research. What do I call this?

Some Google research led me to a great visualization and blog by David McCandless on the Taxonomy of Ideas. While the words in his viz are attributes of ideas, not the ideas themselves, it got me thinking in different ways about the problem.

Taxonomy of Ideas

If you substitute an idea (product or problem) in David’s matrix and add the dimension of time, you create a useful framework. If the idea above was “car”, then the top right might be Tesla and bottom left a Yugo (remember those?). Narrow the definition to “electric car” or generalize to “eco-friendly personal transportation” and the matrix changes. But insert an unsolved problem and now you have trouble applying the attributes. You also arrive at an innovator’s dilemma (not the seminal book by Clayton Christensen), the challenge of researching something that hasn’t been labeled and categorized yet.

Ideas begin in someone’s head. With research, debate, and engineering, they become products. Products have labels and categories that facilitate communication, search and commerce. The challenge for idea search on future problems is that the opposite occurs: products are not yet ideas and the problems they solve may not have been defined yet. If I may, Donald Rumsfeld nailed the problem with this famous quote:

“There are known knowns. These are things we know that we know. There are known unknowns. That is to say, there are things that we know we don’t know. But there are also unknown unknowns. There are things we don’t know we don’t know.”

And if it’s an unknown unknown, it certainly hasn’t been labeled yet so how do you search for it? Our CEO Walt Diggelmann used to say it this way, “ai-one gives you an answer to a question, you did not know that you have to ask….!

Innovators work in this whitespace.

If you could build and combine different intelligent (idea) agents for problems as easily as you test different combinations of words in a search box, you could drive an interactive and spontaneous exploration of ideas. In some ways this is the gift of our intelligence. New ideas and innovation are in great part combinatorial, collaborative and stimulated by bringing together seemingly unrelated knowledge to find new solutions.

Instead of pumping everything into your brain (or an AI) and hoping the ideas pop out, we want to give you the ability to mix combinations of brains, add goals and constraints and see what you can create. Matt Ridley termed this “ideas having sex”. This is our goal for Topic-Mapper (not the sex part).

So what better place to apply this approach than to the exploration of space? NASA already created a “taxonomy of ideas” for the missions of the next few decades. In my next blog I’ll describe the demo we’re working on for the grandest of the grand challenges, human space exploration.


AI, AGI, ASI, Deep Learning, Intelligent Machines.. Should you worry?

January 17th, 2015

If the real life Tony Stark and technology golden boy, Elon Musk, is worried that AI is an existential threat to humanity, are we doomed? Can mere mortals do anything about this when the issue is cloaked in dozens of buzzwords and the primary voices on the subject are evangelists with 180 IQs from Singularity University? Fortunately, you can get smart and challenge them without a degree in AI from MIT.

There are good books on the subject. I like James Barrat’s Our Final Invention and while alarmist, it is thorough and provides a guide to a number of resources from both sides of the argument. One of those was the Machine Intelligence Research Institute (MIRI) founded by Eliezer Yudkowsky. This book was recommended on the MIRI website and is a good primer on the subject.

Smarter Than Us by Stuart ArmstrongSmarter Than Us – The Rise of Machine Intelligence by Stuart Armstrong can also be downloaded at iTunes.

“It will sharpen your focus to see AI from a different view. The book does not provide a manual for Friendly AI, but its shows the problems and it points to the 3 critical things needed. We are evaluating the best way for ai-one to participate in the years ahead.” Walt Diggelmann, CEO ai-one.

In Chapter 11 Armstrong recommends we take an active role in the future development and deployment of AI, AGI and ASI. The developments are coming; the challenge is to make sure AI plays a positive role for everyone. A short summary:

“That’s Where You Come In . . .

There are three things needed—three little things that will make an AI future bright and full of meaning and joy, rather than dark, dismal, and empty. They are research, funds, and awareness.

Research is the most obvious.
A tremendous amount of good research has been accomplished by a very small number of people over the course of the last few years—but so much more remains to be done. And every step we take toward safe AI highlights just how long the road will be and how much more we need to know, to analyze, to test, and to implement.

Moreover, it’s a race. Plans for safe AI must be developed before the first dangerous AI is created.
The software industry is worth many billions of dollars, and much effort (and government/defense money) is being devoted to new AI technologies. Plans to slow down this rate of development seem unrealistic. So we have to race toward the distant destination of safe AI and get there fast, outrunning the progress of the computer industry.

Funds are the magical ingredient that will make all of this needed research.
In applied philosophy, ethics, AI itself, and implementing all these results—a reality. Consider donating to the Machine Intelligence Research Institute (MIRI), the Future of Humanity Institute (FHI), or the Center for the Study of Existential Risk (CSER). These organizations are focused on the right research problems. Additional researchers are ready for hire. Projects are sitting on the drawing board. All they lack is the necessary funding. How long can we afford to postpone these research efforts before time runs out? “

About Stuart: “After a misspent youth doing mathematical and medical research, Stuart Armstrong was blown away by the idea that people would actually pay him to work on the most important problems facing humanity. He hasn’t looked back since, and has been focusing mainly on existential risk, anthropic probability, AI, decision theory, moral uncertainty, and long-term space exploration. He also walks the dog a lot, and was recently involved in the coproduction of the strange intelligent agent that is a human baby.”

Since ai-one is a part of this industry and one of the many companies moving the field forward, there will be many more posts on the different issues confronting AI. We will try to keep you updated and hope you’ll join the conversation on Google+, Facebook, Twitter or LinkedIn. AI is already pervasive and developments toward AGI can be a force for tremendous good. Do we think you should worry? Yes, we think it’s better to lose some sleep now so we don’t lose more than that later.


(originally posted on

The State of A.I. and Switzerland

June 28th, 2016

the-state-of-artificial-intelligence-in-15-visuals-1050x580As you know, Artificial intelligence, or AI, has been a part of our world at ai-one since our founding in 2003.  Don’t be confused by the latest buzzwords, deep learning, machine learning, artificial intelligence and biologically inspired intelligence (our Nathan) are all part of the field of A.I.    It’s a hot subject now but the languages, techniques and algorithms have been around for decades, often as part of an application (Google search and map directions for example).

In order to become it’s own industry A.I. needs a large number of companies, money and its own problems to solve.  This is the real news of the last few years and Max Wegner and our friends at have created “State of Artificial Intelligence Infographic” to tell the story.

Today A.I. is a significant and growing sector of the technology industry; billions of dollars are invested in new AI developments, and companies around the world are working on new AI applications as you read this. And while most AI companies have been in existence for less than a decade (the average age is around four or five years), the tech behind AI is evolving, and the role of AI in our lives in the coming years is all but certain to grow.

One of the surprises in the report is the ranking of Switzerland as the second largest location in the world by amount of VC funding received and third by number of companies.  With almost all of the companies less than 10 years old, ai-one was clearly early, before the cloud and big data brought in the new era. Our biologically inspired intelligence is another differentiation from all but a few of these companies.

It is a new era and with all the competition comes the demand from the business community to make significant investments in A.I. powered applications.  We see the change in the character of the inbound leads from our website.  In the past those inquiries were from PhDs, engineers and startups where today they are almost exclusively from product managers at larger enterprises.  This is the type of demand that will drive growth and we’re excited to be in this space.

If you want to put see what our AI can do for your enterprise, please connect.


ISC Consulting Powers Pytheas AI with BrainDocs

June 24th, 2016

We are pleased to publish ISC’s submission under the DIUx program.  The new  “Defense Innovation Unit Experimental (DIUx) serves as a bridge between those in the U.S. military executing on some of our nation’s toughest security challenges and companies operating at the cutting edge of technology.” Powered by ai-one’s Nathan ICE artificial intelligence core for language, ISC’s Pytheas AI will provide ISC with the technology to assist researchers and help our governments keep us safe.  Some proprietary sections have been deleted in the version below.

ISC White Paper for DIUx Technology Area of Interest: Knowledge Management

By Jeremy Toor, ISC Consulting Group

Executive Summary

ISC/ai-one develops a prototype using Pytheas artificial intelligence (Pytheas AI) which will provide automated intelligent information management, or knowledge management (KM) of multiple data sources.  Pytheas AI fingerprints the flow of data from almost any source including chat, email, message traffic, and other data.   This AI core then supports the user in a publish/subscribe architecture, with building knowledge from the fingerprinted data through queries and intuitive alerts that understand the difference and importance of contextual situations.

The abundant quantity of data that is available to users, analysts, and commanders today can make it challenging to build a concise and accurate picture from which dynamic assessments can be made. Both Command and Control (C2) and intelligence systems are largely data-centric. Users that are required to make strategic and tactical decisions will benefit from a task-centric user experience that is able to manage information as it is created and presented, and distil many sources of data into a manageable data flow.  This user experience, facilitated by Pytheas AI will deliver an KM Engine that can accelerate the decision making process.

Through Pytheas AI the user will be presented with data that has gone through automated processes to be categorized, tagged, and ranked according to its value in the current context of operations.  Pytheas AI will give the user flexibility to tailor their focus area and pull information from a wide breadth of sources as they build situational awareness and confidence to take action.


ISC/ai-one proposes a three phase project.  Phase 1 will include one-week for initial installation, configuration and user training. Phase 2 will include a five-month period to support data ingestion, intelligent agent training and dashboard customization. Phase 3 will include a three-week evaluation and close out.


Pytheas AI is built with an artificial intelligence core to collect, organize and analyze language to uncover key links and patterns within large volumes of unstructured text.  The application empowers analysts to find the relationships necessary to discover, manage, process and exploit data.  Key features and attributes of Pytheas include:

  • Discovery of Concepts through the use of Intelligent Agents
  • Agent collections can be built from existing plans, roadmaps and strategy documents
  • DoD analysts can use common KM collections or build and share concept agents
  • Agents provide classification for query and tagging of documents
  • Application core is language independent
  • Fast and lightweight running on PC class machines or VMs

Pytheas AI is built upon ai-one’s BrainDocs software application (with NathanICE API core) which is a commercially ready and viable technology that has been applied to several use-cases similar to the requirements in the technology area of interest, knowledge management, that DIUx is seeking.  Our prototype for KM is ready for demonstration using sample data.

Pytheas uses the ability of ai-one’s proprietary NathanICE API to discern patterns in the words and associations that are central to the meaning of all or a portion of a text document (in the same way as the brain).  Nathan extracts these keywords and associations, filtering out the noise to create a proprietary fingerprint array of the concept that can be used in many ways.

Pytheas uses the fingerprint of a trained concept to find (rank) similar concepts within a corpus of information (documents, websites, databases) and returns paragraph-level results sorted by “similarity”. These results support a variety of workflows in enterprise compliance, classification, search and knowledge management.  Agent similarity scores are exported to Excel or your database to support analytics and BI tools. This can be done by the analyst for small ad hoc studies.  Agents can also be used to code years of legacy data without additional training.

Users employ agents in Pytheas AI to organize text based on contextual ideas and metadata dimensions, improving accuracy, consistency and saving substantial amounts of time in this tedious process.

The Basic Elements of Pytheas

Documents – Pytheas is capable of analyzing any form of unstructured text. In fact, our technology works best with semantically-rich content written in your business vernacular without external taxonomies or ontologies.  Working at the paragraph level it has been used on everything from text messages to database fields to long documents always with full traceability to source.

Conceptual Fingerprints – This is the “secret sauce” of our discovery capabilities. Pytheas uses the Nathan API keywords and associations to create semantic “fingerprints” of concepts. Because one concept can be written in multiple ways, our algorithm does not rely on word counts, natural language processing (NLP) or latent semantic analysis (LSA) when identifying and fingerprinting concepts.

Intelligent Agents – Pytheas agents examine and compare the conceptual fingerprints to find traces of concepts buried within your data. Our premise is that analyst is the expert and needs to be able to train their own army of software agents to “read” documents and deliver the relevant paragraph. Used as a collection, the scores from a collection of agents set the context for a user’s query.

Paragraph Level Concept Discovery – Pytheas provides the ability to categorize and display concept results at the paragraph-level. Users do not need to hunt through documents trying to find a concept that a search engine claims to be present. Our system will return the paragraph(s) that closely match a concept, sort and group the concepts by similarity to one another. Paragraphs can be evaluated and traced back to their source document for reporting and distribution.

Topic Mapper Entity and Sentiment

Figure 1. Topic Mapper Entity and Sentiment in SEC Filings

Ease of Integration – Pytheas application can be used with conventional desktop tools for ad hoc projects.  For workflow automation a Restful API provides developers an easy method to process documents and export results to SQL or other DBs for reporting and visualizations.

Optional Entity Extraction and Sentiment (Figure 1 above) – Complementing paragraph level concept detection is the ability to extract entities and/or score for sentiment so this information can be added to visualizations and follow on workflows.  Clients can use their own technology for this purpose or add custom analytics to further refine the insight for social network analysis, tagging existing file headers or streamlining the flow of information into the analyst.

Defense Utility

The immediate benefit to DoD is increased productivity, consistent analysis and more effective information management.  The long-term benefit is an ability to perform quicker, more informed decisions.

Operational users of this prototype include any person that has to search through data.  This includes anyone using SharePoint and other common organizational databases.  Analysts who must sift through massive amounts of data in order to discover relevant information will save countless hours through the employment of our prototype.   Through the employment of a similar use case at NASA, our customer was able to complete a typical six-week project in one-week!

Company and Relevant Use Case

Lead by ISC, personnel from ISC Consulting and ai-one inc. will execute the project.

ISC Consulting Group is a Service Disabled Veteran-Owned Small Business (SDVOSB). We are headquartered in Sierra Vista, Arizona, with operational offices at Ft. Huachuca, AZ; Orlando, FL; Ft. Gordon, GA; and Northern Virginia. ISC provides a full-spectrum of services, products & solutions supporting the DOD Intelligence Community and key commercial clients with advanced capabilities in Instructional Solutions, Cyber Security, Command and Control planning and operations, Intelligence operations, Information Technology, and Data Analytics through Artificial Intelligence products and services.

ai-one inc. is the developer of a proprietary core technology that emulates the complex pattern recognition functions of the human brain that can detect the key features and contextual meaning of text, time-series and visual data.  This technology will enable DIUx to score and analyze any piece of textual content and discover information by concept, bringing the dimension of AI understanding to knowledge management. This technology automatically generates a lightweight ontology that easily detects all relationships among data elements; solving the immediate problems facing the DIUx knowledge management based process and schedule.

Existing Customers

ISC has served several clients with Pytheas technology, including NASA Marshall Space Flight Center (MSFC).   Currently, Pytheas is being used by MSFC’s Advanced Concepts Office (ACO) under a Cooperative Agreement to assist in technology roadmap development and separately by the Office of Strategic Analysis and Communication (OSAC) to manage and report on their portfolio of project investments (similar to SBIR grants).   For example, the roadmap project is described below:

Overview of the NASA Advanced Concepts TAPP Pilot Project

The Advance Concepts Office (ACO) at MSFC, NASA is developing and refining methods and processes for performing Information Based Decisions for Strategic Technology Investments.  This system is currently referred to as TAPP, Technology Alignment & Prioritization Process.   This process supports the evaluation of the technologies for investment by NASA and MSFC to insure alignment with NASA mission plans, technology area priorities and strategic knowledge gaps.

TAPP creates an interactive system for exploring the almost mind boggling complexity of planning for multiple missions using over 400 technologies (many still in basic research) and hundreds of interrelated elements/sub-elements over 30-year planning horizons.

Pytheas provides NASA the capability to have data mining agents parse and score unstructured content against the nearly 400 technologies identified in the 15 Technology Roadmaps.  This ability to score proposals with agents allows ACO to perform statistical analysis within the Information Based Decision framework for Strategic Investments.

The immediate benefit to ACO is increased productivity and consistent analysis. The long-term benefit is an ability to perform quicker, more informed technology assessments, feasibility analysis, and concept studies that align with NASA evolving strategic goals and multiple mission objectives.


Given a six-month prototype build period, ISC/ai-one will demonstrate to DIUx that ISC/ai-one’s Pytheas AI application will enable the organization to save critical time and human capital in the implementation and operation of knowledge management systems.  Pytheas will empower the IC to rapidly and effectively sort through vast volumes of text data in order to gain knowledge and position decision makers with the right information to achieve stated organizational analytical research outcomes.

ai-one Powers Competitive Intelligence Analytics as a Service

June 7th, 2016

ai-one inc and KDD Analytics put their artificial intelligence and business intelligence expertise to work for competitive analysts.  After collaboration on projects from aerospace research to marketing surveys, the companies are pleased to announce a new service for C-Suite executives and analysts.

This blog was posted earlier on our Analyst Toolbox website.

Day in the Life of a Financial Competitive Analyst

“It’s 10:00 PM, the night before the quarterly board meeting, and we are still pulling together financial data on our company and competitors into presentation worthy graphics.

Procrastination?  No, the tools and processes just make it a recurring battle. One key section of our report is hampered by a lack of standardization in SEC filings.  Our auditors routinely deliver the internal financials at the last minute.  Reformatting the financials in a way consistent with comparatives, let alone making them visual, interactive and providing scenario analysis capability is a time consuming hassle.

We always run out of time to actually “analyze” the results…there has to be a better way”.

– Earl Harvey, Senior Financial Competitive Analyst

Sound familiar?  Earl’s problem led him to KDD Analytics and ai-one, and ultimately to a collaboration developing CIaaS (Competitive Intelligence as a Service).

The State of Financial Competitive Intelligence

Financial data on your competitors comes from SEC filings (10q/10k) via companies such as Dow Jones FactSet, Edgar Online, ThomsonOne and Bloomberg who provide aggregated financial data (typically) in Excel worksheets or through an API “firehose” that requires programming resources to navigate.

But then what?

The data still needs to be standardized across companies and reporting periods and presented in a visually digestible manner; often for people using different devices (desktop, tablet, mobile).  Moreover, this process needs to be repeatable every quarter with a consistent visual format and ideally delivered several days before the board meeting…a tall order for resource constrained competitive intelligence analysts.  As a result, “burning the midnight oil” sessions are the rule not the exception.

How Do You Avoid This Last Minute Stress?

Avoiding this fire drill (without hiring on more resources) is possible by using a service that has:

  • Standardized the data
  • Developed the visuals, charts and scenarios
  • Loaded and analyzed the latest data, and ideally,
  • Used A.I. to “read” and organize the relevant text from the docs.

That is, a source that will deliver a finished, interactive solution in a timely manner allowing you to focus on insight and analysis of the financial data, so you’re ready to be brilliant on demand (and getting more sleep).

Introducing the Financial Analyst Toolbox (FaTbx™), financial competitive intelligence as a service.

Currently in beta as a custom service, FaTbx™ is a set of more than 30 presentation ready Tableau dashboards, displaying interactive, comparative financial data for your company and other public companies critical to your business ecosystem.

Get the big picture fast: rankings and financial health, trends and topic heat maps (from our tech stocks demo).

FaTbx BIg Pic 3 slides

Then drill down:  Income statement waterfalls, balance sheet, cash flow details and topics (see how Apple, Google and Microsoft 2015 Q3 results compare below).

FaTbx Waterfall Pic 3 slides

Developed by experienced competition, artificial intelligence, analytics and visualization experts, FaTbx™ shows your company and competitors’ financials in a consistent, standardized and easily digestible manner.  Using the financials to spot issues and trends, the AI engine powers drill down to the disclosure text in the filings: no need to pull up a 10k and look for the narrative.

Filters adjust for financial category (e.g. income, cash flow, balance sheet, ratios), company, growth measure (e.g. quarter over quarter, year over year, CQGR), TTM and displayed time span.  Custom filters can be added based on your company’s need.

FaTbx™ is available as a cost effective annual subscription with quarterly or monthly updates.  The standard service includes comparatives for three publicly traded competitors, suppliers or customers.  It is delivered online via Tableau Server Edition or through a private web portal.  Subscription tiers depend on the level of support, customization, information sources and macroeconomic data desired.  Custom integration with internal KPIs can be provided.

FaTbx™ – Financial CI as a Service.   We streamline the grunt work of financial competitive analysis so you can focus on your company’s strategy and response. To learn more, contact me about the beta program or request a live demo.


ai-one and the Machine Intelligence Landscape

January 12th, 2015

In the sensationally titled Forbes post, Tech 2015: Deep Learning And Machine Intelligence Will Eat The World, author Anthony Wing Kosner surveys the impact of deep learning technology in 2015. This is nothing new for those in the field of AI. His post reflects the recent increase in coverage artificial intelligence (AI) technologies and companies are getting in business and mainstream media. As a core technology vendor in AI for over ten years, it’s a welcome change in perspective and attitude.

We are pleased to see ai-one correctly positioned as a core technology vendor in the Machine Intelligence Landscape chart featured in the article. The chart, created by Shivon Zilis, investor at BloombergBETA, is well done and should be incorporated into the research of anyone seriously tracking this space.

Especially significant is Zilis’ focus on “companies that will change the world of work” since these are companies applying AI technologies to innovation and productivity challenges across the public and private sectors. The resulting solutions will provide real value through the combination of domain expertise (experts and data) and innovative application development.

This investment thesis is supported by the work of Erik Brynjolfsson and Andrew McAfee in their book “The Second Machine Age”, a thorough discussion of value creation (and disruption) by the forces of innovation that is digital, exponential and combinatorial. The impact of these technologies will change the economics of every industry over years if not decades to come. Progress and returns will be uneven in their impact on industry, regional and demographic sectors. While deep learning is early in Gartner’s Hype Cycle, it is clear that the market value of machine learning companies and data science talent are climbing fast.

This need for data scientists is growing but the business impact of AI may be limited in the near future by the lack of traditional developers who can apply them. Jeff Hawkins of Numenta has spoken out on this issue and we agree. It is a fundamentally different way to create an application for “ordinary humans” and until the “killer app” Hawkin’s speaks about is created, it will be hard to attract enough developers to invest time learning new AI tools. As the chart shows, there are many technologies competing for their time. Developers can’t build applications with buzzwords and one size fits all APIs or collections of open source algorithms. Technology vendors have a lot of work to do in this respect.

Returning to Kosner’s post, what exactly is deep learning and how is it different from machine learning/artificial intelligence? According to Wikipedia,

Deep learning is a class of machine learning training algorithms that use many layers of nonlinear processing units for feature extraction and transformation. The algorithms may be supervised or unsupervised and applications include pattern recognition and statistical classification.

  • are based on the (unsupervised) learning of multiple levels of features or representations of the data. Higher level features are derived from lower level features to form a hierarchical representation.
  • are part of the broader machine learning field of learning representations of data.
  • learn multiple levels of representations that correspond to different levels of abstraction; the levels form a hierarchy of concepts.
  • form a new field with the goal of moving toward artificial intelligence. The different levels of representation help make sense of data such as images, sounds and texts.

These definitions have in common (1) multiple layers of nonlinear processing units and (2) the supervised or unsupervised learning of feature representations in each layer, with the layers forming a hierarchy from low-level to high-level features.

While in the 4th bullet this is termed a new field moving toward artificial intelligence, it is generally considered to be part of the larger field of AI already. Deep learning and machine intelligence is not the same as human intelligence. Artificial intelligence in this definition above and in the popular press usually refers to Artificial General Intelligence (AGI). AGI and the next evolution, Artificial Super Intelligence (ASI) are the forms of AI that Stephen Hawking and Elon Musk are worried about.

This is powerful stuff no question, but as an investor, user or application developer in 2015 look for the right combination of technology, data, domain expertise, and application talent applied to a compelling (valuable) problem in order to create a disruptive innovation (value). This is where the money is over the new five years and this is our focus at ai-one.


Analytics In M&A – Avoid Overpaying for Revenue

November 5th, 2014

“New, fast, desktop analytics tools enable CEOs to measure top line impact of acquisitions during due diligence, avoiding revenue misses and integration problems after closing.  We can now complete the analysis and publish a dashboard to a CEO’s desktop during due diligence while there is still time to negotiate.” Says KDD Analytics President, Dr. Duffy-Deno.

Driven by the need for better insight into vast amounts of customer information in websites, market surveys, company profiles, sales reports, emails and research reports, KDD Analytics (KDD) has been partnering with ai-one to create innovative ways to visualize this data in Tableau dashboards.

When KDD showed us ZIP Pointe© and told us the story of the CEO in the following presentation, we knew he had a winner.


Any CEO or management team that’s been through the M&A process knows how difficult it is to analyze the target’s revenue in the brief and stressed period of due diligence.  ZIP Pointe© provides the insight you would expect from a SOR enterprise solution within the time and cost constraints of M&A.  A CEO can’t afford not to use it.

Developed for CMOs and CSOs on a tight budget trying to meet planning deadlines, KDD’s new SaaS offering, ZIP Pointe© is used to analyze and size geographic markets down to the 6-digit NAICS level.  And with the custom integration of customer data, it can be used to profile customers, estimate market and wallet share, identify specific market segments of high spend potential and generate a list of ZIP codes sorted by opportunity for targeting purposes.

ZIP Pointe© summarizes and enhances US Census Bureau data for over 7 million private sector business sites with paid employees across the US.  This data is enhanced with estimates of revenue and payroll per site and measure(s) of potential spend per site (what companies could spend on software for example).  The data is reformatted and displayed online in an interactive Tableau dashboard.

Integration of customer data in ZIP Pointe© allows for customer base profiling, estimation of market and wallet share, identification of whether the correct segments are being targeted in terms of revenue and potential spend per site and the degree of success in penetrating specific markets.  When used to support M&A due diligence, integration of the target customer base immediately shows how it aligns (or doesn’t) with current customers and expectations.

ZIP Pointe© is offered on an annual subscription basis at a very affordable $1,999 or $2,999 per user, depending on desired capabilities.  Integration of customer data adds a one-time cost, the amount of which depends on whether firmographics need to be appended to the customer file.  In the case of an M&A application, the total cost would likely be $5,000 to $10,000, a steal when acquisition costs are in the millions.  Check out ZIP Pointe© at

KDD provides expertise in predictive analytics and Tableau visualizations, with domain specialization in B2B quantitative marketing analytics.  If you’re looking to attack your growth plan for 2015 backed by powerful marketing analytics, or need analytical support for M&A due diligence, contact Dr. Duffy-Deno at or give me a call and I’ll introduce you.