top of page
W háttér 1.png

​Mathematical R&D

Industry 4.0

REALTIME  METAHEURISTIC TECH 2.0

"RM2" 

We have created a brand new Metaheuristic technology (RM2) that is able to endow intelligent systems on specific areas with infinite knowledge. It allows for the optimization of a function or process without the need for knowledge of the internal workings of the function or process. This means that the optimization can be done even if the function or process is not fully understood or if it is too complex or expensive to analyze.

 
RM2 the long-awaited high-efficiency alternative for AI-based innovations, robotics and many areas for particularly efficient business returns;
 

1. For real-time decisions
This tool can be used for countless decision needs and tasks, because it can always make the best decision in real time (!) considering the infinite combinations of real interactions behind the available information.

  

2. For much more high-quality training data
In the development of artificial intelligence technologies or robotics, it is a huge advantage if we can produce a large amount of high-quality training data in a very short time... however, in the case of the SINEXTON solution, it is not a problem if the quality of the input data is very low or very noisy (!)

  

3. For process optimization and parameter optimization
RM2 can be used in all areas where with large amounts of data and complex problems. It can parametrize the missing (even several) components of any process, construction or system in real time mathematically perfectly and simultaneously, taking into account complex conditions. (Always guaranteeing a global optimum.) (!) It's an excellent new, relatively quickly deployable efficiency-enhancing tool, e.g. in marketing, cyber security, drug development and countless other areas.

FOR EXAMPLE,
IN WHICH SECTORS might RM be needed?

Energy

optimizing renewable energy systems and energy usage in buildings.

      

Transportation

Optimizing routing and scheduling for logistics and delivery.
 

Self driving

Unprecedented level of reliable real-time decision in several different areas, or to generate training data for Reinforcement Learning methodology for AI-based self-driving.

  

Manufacturing
Optimizing production processes for increased efficiency and reduced waste.

      

Finance

Optimizing investment portfolios and risk management.
        

Healthcare

Optimizing patient treatment plans and drug development.

This technology helps by providing a systematic approach to finding the best solution to a problem based on a set of objectives and constraints, allowing organizations to identify and implement new, more efficient and effective solutions.

 

Additionally, it enables companies to test and evaluate multiple solutions quickly, which can lead to faster innovation.

What sets our solution apart from others?

  • General black-box optimizer

        

  • Non-parametric

              

  • Almost only global optima   â€‹

          

  • ​More precision

               

  • No restart tick

            

  • No assumptions are needed about the problem

             

  • ​​Not required to be differentiable

              

  • Solve noisy data as well

SINEXTON Black Box Optimizer

matek kék3.png
kör ábra SZ 2.png

Exceptionally good fault tolerance

We've been stress testing our solution and comparing it against other well-known methods with great success.    

Extremely robust.    

Even the most complex functions do not cause problems

x30 - 68 - 47 * cos( x12 ) ^ x30 + 53 * 22 - x5 + 54 - 52 + x30 + 101 + x25 + 54 * x3 * sinh( x30 ) + 75 - x13 ^ 14 * tanh( x30 ) ^ x6 - 46 * x30 ^ 81 * 55 + 97 + x30 + 15 - 47 * x10 - x11 * x20 * x26 * x30 - sinh( x4 ) + x2 - 2 - sinh( x30 ) - 82 * tan( x15 ) * 21 + 5 * 75 * x23 - x30 * cos( x30 ) - 41 + 25 + 12 * 38 + sinh( x17 ) - 75 * 23 * x29 ^ x22 - tan( x7 ) ^ x19 - sinh( x30 ) * x8 * x30 + x18 - 3 - 18 * tan( x30 ) + 64 - 97 * x21 * x30 ^ 53 - sinh( x30 ) - 27 * 50 + 23 + 30 + 24 + 2 * 83 - 73 * 45 - 80 + 89 * x10 + 15 - x4 * tan( x28 ) * 10 + 55 * 10 * exp( x2 ) - 4 + x9 + cosh( x14 ) ^ x24 * 80 + x1 ^ sin( x27 ) ^ x16 * x4 + 49 + 26 = 100

 

( error 0, time 2.21s )

x1 = 0.43847643622855487

x2 = 0.46929961542364773

x3 = -0.22739104890647494

x4 = 0.5419443297863478

x5 = -0.5487106409433273

x6 = 0.6862159575182608

x7 = 0.3809093553736538

x8 = -0.2790904768113744

x9 = 0.7098757786923025

x10 = 0.07842643908661656

x11 = -0.0817442135773003

x12 = 0.442795812830219

x13 = 0.38427484689331487

x14 = -0.6565246308968888

x15 = -0.8437142735692804

x16 = 0.12579756898717992

x17 = 0.4923442585462639

x18 = 0.523572942374683

x19 = 0.21694979463611894

x20 = -0.09079774813410064  

x21 = 0.519963214975034

x22 = 0.6087180159291697

x23 = 0.8651529146552689

x24 = 0.52404542812148

x25 = 0.6183467400711733

x26 = -0.44056998043975537

x27 = 0.17027625860936058

x28 = -0.13984902234792382

x29 = 0.16878526770059354

x30 = 0.1762607949000223    

kontakthoz

How did we get to this result?

Our technological research and development of inventory optimization needed help in general problem-solving. This is how this solution was created.

   

The development has taken 2 years.

bottom of page