About Us

Platonite will exploit a very rare opportunity: the opening-up of a vast
new technological field. This is made possible by the discovery of the
true data structure used by the brain. This neural code has the form of
rapidly switchable net fragments acting as puzzle pieces to compose the
representations we experience in our mind. This neural code will open
the door to autonomous intelligence in artificial systems.

Platonite’s immediate concern will be working towards human-level
artificial vision. This is urgently required for realizing
situation-cognizant autonomous cars, service robots and security
surveillance systems, a goal that so far has been blocked by fundamental
conceptual maladjustment both in computer vision and in neuroscience.

Net fragments are able to express the data structures and processes used
by computer graphics in generating complex visual scenes from a toolbox
of simple structural elements, the novelty being that they are able to
also invert those processes to extract intrinsic scene properties from
camera input. This opens the way for proof-by-reconstruction as the
ultimate basis for reliable sensation.

In distinction to current systems, Platonite’s technology can recognize
objects or situations after single inspection instead of thousands of
hand-labeled examples, and as it doesn’t require double-precision
connection weights it is a natural basis for neuromorphic implementation.

As first step we will construct a relatively simple prototype
demonstrating all necessary functionality.

“our integrative architecture
changes the game”

TO THIS DAY, CARS AND ROBOTS ARE
ESSENTIALLY BLIND

Computer vision is mired in a tangle of part-solutions

The human brain can see, but the attempt to understand it is in a four-decade stalemate

Deep learning is data-expensive and delivers only part-solutions

OUR EXCLUSIVE REVOLUTIONARY
DYNAMIC LINK ARCHITECTURE

is based on dynamic nets instead of single neurons as decision elements

implements the functional principle of the brain

learns from single examples

COMPETING TECHNOLOGIES
DEEP LEARNING HYPE

Reliance on brute-force learning of all variations of all objects.

Restriction to particular tasks
(e.g., classification or localization)

No concept of scene representation

Requirement for double precision weights precludes cheap implementation

COMPUTER VISION BLUES

Many functional component algorithmsLack of exploitation of synergy to reach reliability

Babylonian confusion of data structures

Low reliability due to lack of component synergy

No learning of content

OUR APPROACH

Based on the brain’s neural code

Natural integration of functional components

Inverse computer graphics

Reconstruction of scenes

Autonomous learning

Ultimate reliability by matching reconstruction to input

INVERTING COMPUTER GRAPHICS
Creation of great variety of instances by parameter-controlled transformation of one template
Recognition of full variety of instances by parameter-controlled transformation to one template
ONLY ONE TEMPLATE NEEDS TO BE STORED
THE REVOLUTION
STANDARD
unstructured sets of active neurons
a very weak data structure
OUR NEURAL CODE
Structured Nets
Produced by Network Self-Organization
Combine to Represent the Scene
COMPUTER GRAPHICS
Composing scenes from independent factors
PLATONITE
Decomposing scenes into factors
Inner model of reality validated by correct prediction of sensory signals