Perfection.AI is an abstraction layer over standard AI technologies. Our main focus is on simplicity and usability. Here are some technologies we are using to solve game development optimization problems:


Sparse Distributed Representation (SDR)

Technology originally invented by Numenta. An SDR consists of thousands of bits where at any point in time a small percentage of the bits are 1’s and the rest are 0’s. The bits in an SDR correspond to neurons in the brain, a 1 being a relatively active neuron and a 0 being a relatively inactive neuron.

The most important property of SDRs is that each bit has meaning. Therefore, the set of active bits in any particular representation encodes the set of semantic attributes of what is being represented. Because of this semantic overlap property, systems based on SDRs automatically generalize based on semantic similarity.


Differentiable Neural Computer (DNC)

Technology originally invented by DeepMind. DNC combines the learning and pattern-recognition strengths of deep neural networks with the ability to retain information in complex data structures such as graphs in a computer memory. The memory can be retained indefinitely, while the DNC uses what it has learned to solve related problems.

DNCs have the capacity to solve complex, structured tasks that are inaccessible to neural networks without external read–write memory. The whole system is differentiable, and can therefore be trained end-to-end with gradient descent, allowing the network to learn how to operate and organize the memory in a goal-directed manner.