Tag Archives: evolution

Building Intelligent systems: biological and software

There are amazing analogies between computer processors and the brain, and it is just a matter of time before the algorithms that define electronic processors mirror the functionality of the chemical processors of our brains. The biological neural systems rely on inputs and pattern recognition to learn. Computers are excellent at storing (remembering) facts, and are becoming proficient at recognizing relationships as defined by statistical patterns and neural networks. However, computers cannot yet create metaphors or learn how to independently process new information.

Metaphors are an important part of how humans think. We understand new information as we draw parallels and connections between it and prior information. Over-simply put, we learn by recognizing relationships between new information and old. Computers could do the same when their sets of data include enough relevant fields to be able to computationally identify systems that are described by similar dynamics. In other words, when a computer has data about how things works, it can find systems that work similarly to each other. The leap from there to drawing metaphors is a data-mining process: it can be solved by computational rote, where statistical relationships are identified, prioritized, and used for prediction.

This process also leads to “learning” about how to process new information. By recognizing the metaphors, new data can be classified and described according to how it is understood. And just like in our brains, there will be errors. Misunderstanding will occur as metaphors are calculated based on incomplete data sets. As more data is input, systems will have to be able to make corrections and re-calculate all of the other metaphors that included the corrected data. New corrections will be made and a cascade of corrections will result in a modified historical data record. A large number of calculations and recalculations will occur with each new input, and the storage of historical data (and calculated results) will require substantial processing and storage.

Recognizing metaphors will allow machines to output statements like: “It appears that ABC is driven in many similar ways to XYZ. The result we are seeking might be accomplished by A because a similar result was achieved in XYZ when X was applied.” Put more simply, computers will be able to express creative suggestions.

Interestingly, storage could be massively reduced by deleting large volumes of data that support the relationships that are strong enough to overcome some threshold level of certainty. For example, if everything falls, then we don’t have to keep all that data, just the relationship that everything falls. This may be analogous to forming intuitions.

The Evolvor Cycle

I think that the following cycle is an abstraction that applies to many forms of systems and, when implemented, can create very powerful evolutionary dynamics. It actively evolves the underlying system, so I name it ‘Evolvor cycle’.

Applied to a configuration, for example, it would set the original default for new users according to the implied preferences of the existing users. The option to signal new preferences continues the cycle and the default configuration evolves over time without any human administration.

Remote Storage and Analysis of Sensory Logs

Wireless connectivity can solve the problem of local storage constraints for PDAs and other portable devices (including wearables). In addition, external processing greatly increases the breadth and depth of analysis that can be performed on the data. For example:

  • Journaling
  • trend analysis and advice
  • recommendations of – media, medical, communications, reminders,
  • Statistical analysis of log data forecasts user reactions to new voice and other input.

Algorithm for self-improving "telepathic" input system

Concurrently record the output of a brain scan A and standard input devices of keyboard and mouse B. Then neural network N evaluates A, forecasting B. After training with good data populating A and B, the intricacy of the commands and the statistical accuracy will enable a brain-only interface with a breadth of controllability and interactivity speed that will far exceed our current tools.

Initial systems will most likely track eye movement and visceral biofeedback that can be measured using electrodes and buttons.

6/15/2001 – I have received feedback that the brain thinks in words and concepts, rather than the translation to spelled and typed words, and would therefor render this invention useless. However, the input system described above would actually benefit from this characteristic. Inputs should include a rolling period of time and to allow for words or concepts to be interpreted in N over a series of typed inputs.

Learning Biofeedback Input System

By recording and analysing biofeedback and keyboard inputs, an analysis of the concurrent data could identify correlations to yield a biofeedback powered input system. The system would “learn” to replace the keyboard over time with better and better accuracy, faster input speed, and extended breadth of input types. Biofeedback devices could initially include medical biofeedback devices

Entertainment is Evolving

Movies, music, images, and all sorts of digitally transferable media will migrate from broadcast to 2-way networks. Complex, and dynamically updating, personalization engines will determine content selection by default. The media will reach us over wired and wireless networks using highly compressed secure digital signals – rather than local storage. Centralized systems will have dominant personalization systems and data, and so will be the primary tool for selecting media and interface content. Media serving will be decentralized, however, as the media serving and the web serving are separated. Distribution will occur through all sorts of networked devices, including the personal computer… which will come to be characterized as a small wireless device used for all aspects of an individual’s computing needs. Mass media will evolve with the interface devices that are supported by personal computers. In other words, as our interface technology improves, mass media will be developed to take advantage of it. An example of this co-evolution will be the stereo monitor (one image for each eye) – allowing 3d graphics, and marking a key step for 3d media entertainment.