We have been pleased with the results so far and have confidence that HTMs can be applied to many other problems we have not tried. We also know of problems that our current implementation of HTM will not solve today, and we have yet to build very large networks. Time will tell what obstacles we will encounter in the future, but for now we are encouraged by how well the technology is working.

The idea of marrying computer science with brain research came to me soon after I graduated in electrical engineering from Cornell University, in 1979. For many years I pursued the interest part time while working as an engineer for a number of companies (including two I cofounded-Palm Computing and Handspring), and for one year I worked at it full time, as a graduate student in biophysics at the University of California at Berkeley.

In 2002, with the encouragement of some neuroscientist friends, I created the Redwood Neuroscience Institute. For three years, I worked with about 10 other scientists there on all aspects of neocortical anatomy, physiology, and theory. During those years, more than 100 other scientists visited the RNI for discussion and debate, and I made progress on HTM theory.

By 2004 I had developed the essence of HTM, but the theory was still rooted in biology (I published part of that biological theory in 2004 in my book On Intelligence). I did not know how to turn the biological theory into a practical technology. A colleague of mine, Dileep George, was aware of my work and created the missing link. He showed how HTM could be modeled as a type of Bayesian network, a well-known technique for resolving ambiguity by assigning relative probabilities in problems with many conflicting variables. George also demonstrated that we could build machines based on HTM.

His prototype application was a vision system that recognized line drawings of 50 different objects, independent of size, position, distortion, and noise. Although it wasn't designed to solve a practical problem, it was impressive, for it did what no other vision system we were aware of could do.

In 2005, with a theory of the neocortex, a mathematical expression of that theory, and a working prototype, George and I decided to start Numenta, in Menlo Park, Calif. Our experience in industry and academia taught us that people move more quickly in industry, especially if there is an opportunity to build exciting products and new businesses. Today, the RNI continues as the Redwood Center for Theoretical Neuroscience at UC Berkeley. George and 15 other employees work at Numenta, and I split my time between Numenta and Palm.

To help Numenta jump-start an industry built on the ideas of HTM, we embarked on creating a set of tools that allow anyone to experiment with HTMs and to use HTMs to solve real-world problems. By making the tools broadly available, providing source code to many parts of the tools, and encouraging others to extend and commercialize their applications and enhancements, we hope to attract engineers, scientists, and entrepreneurs to learn about HTM. The tools together constitute an experimental platform for HTM that is meant to attract many developers by giving them the chance to create successful businesses.

We realize it will take a lot of time and effort to learn an entirely new way of computing. One of the things I have learned is to never become an obstacle to a developer working hard on a new platform. To this end we have created lots of documentation and several examples. We provide complete source code for two of the platform's three components.

The first part is the run-time engine. This component is a set of C++ routines that manage the creation, training, and running of HTM networks on standard computer hardware. It's highly scalable, meaning you can run the entire platform on anything from a laptop with a single CPU to PCs with multiple cores, to a large computer cluster. Significant development can be done on a single CPU; however, as applications grow in size, multiple CPUs may be needed for performance.

Today the run-time engine runs on Linux. Our employees and customers use both PCs and Macs. When designing HTM-based systems, the developer needs to experiment with different configurations. Running concurrent tests saves a lot of time. Our tools make parallel testing easier.