# General problem solver

**URL:** <https://discourse.numenta.org/t/general-problem-solver/11157>\
**Category:** Community\
**Tags:** question, community\
**Created:** [December 17, 2023, 1:16pm UTC](https://discourse.numenta.org/t/general-problem-solver/11157 "2023-12-17T13:16:53Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![Prakash](https://yyz2.discourse-cdn.com/flex030/user_avatar/discourse.numenta.org/prakash/32/6117_2.png) [@Prakash](https://discourse.numenta.org/u/Prakash)\
**Post date:** [December 17, 2023, 1:16pm UTC](https://discourse.numenta.org/t/general-problem-solver/11157/1 "2023-12-17T13:16:54Z")

</div>

There are some criterias that any network should follow in order to become a good general problem solver.

1. Model with continuous function & plasticity property. (Continuous function - Incoming input information meeting the demands of the old information)
2. Model should have a in-built preference for specific information.
3. Model should have destabilizing mechanism. This mechanism can make the model to become continuous.
4. Easy access to some stored information - More like preference but not.

Architecture for a model that satisfies the above stated criteria:  
[Higher valued clusters(blocks) will always get high priority for the algorithm search]

1. Divide the network space into blocks - Meets the demand for plasticity and extracts above-average information from the input.[(1)]
2. The blocks get narrower as the model produces good results, the number of random neurons increases in those blocks - Meets the demand for preference criteria and reward criteria.[(2),(4)]
3. Confirmation of good output by clustering nearby blocks and not clustering far-away blocks. If a cluster happens, the blocks multiply (number increases and size decreases within the selected block that was clustered), and if a cluster doesn’t happen, the cluster will be combined into one(number decreases and size increases) - Meets the destabilizing mechanism that maintains the equilibrium state and continuous function in the model, where precision of information also increases. To keep the model continuously working, the introduction of a destabilizing mechanism is necessary. [(1),(3)]
4. Far-away clusters will become singular this will meet the demand for the decaying of weights in neural connection criteria.[(3)]

Visual representation -

 ![Untitled75_20231217143828](https://canada1.discourse-cdn.com/flex030/uploads/numenta/original/2X/a/a9d072dc46917bc9234257fee59239e13648b010.png)

Blocks multiply by nearby clusters & becomes singular by far-away clusters.

 ![Untitled76_20231216185029](https://canada1.discourse-cdn.com/flex030/uploads/numenta/original/2X/6/689f4ec80c3fb25aa5f81f9138abf59639296799.png)

A detailed look at the architecture -

 ![Untitled71](https://canada1.discourse-cdn.com/flex030/uploads/numenta/original/2X/9/91bb73dcfb7e919817d25175ceeedde1ff9d0775.jpeg)

![Screenshot_2023-12-17-18-44-51-867-edit_com.linkedin.android](https://canada1.discourse-cdn.com/flex030/uploads/numenta/original/2X/7/72351f4de2c2f1ba5277f2afc083fa5658c8cbe5.jpeg)

Nearby clusters are valuable -

 ![Untitled77_20231216193152](https://canada1.discourse-cdn.com/flex030/uploads/numenta/original/2X/9/9a74f4d13ab989552411ae90e48441ead01e5e11.jpeg)

This architecture was designed based on the insight - In brain Neurons were not fixed to other neurons, they are fixed to spaces.