Unique features of PANN™
- High-speed training (with high accuracy) for approximation, classification and interpolation.
- Training on CPU is at least 3,000 times faster in comparison with existing ANN
- Training with one GPU is 200,000 times faster and proportional to the number of GPUs
- 100%-parallel computation; linear increase in training speed with additional GPUs.
- Batch training of the entire training set: weight correction after every epoch of images, not after every image. Recognition of the entire batch of images, not of a single image, one after another.
- Ability to train the network with additional images without retraining the entire network.
PANN™ allows to create really smart software with high processing speed and unlimited amount of processed information.
- PANN™ is scalable. Can be built in any size.
- PANN™ architecture and training algorithm have been discovered within biological analogs.
- Complex calculations are not necessary.
- Multiple repeating calculations are not necessary.
- Calculations and weight correction by matrix algebra. (US Patent application 15/449,614)
- Replacing existing ANN in order to obtain:
- High speed training
- High accuracy of training
- High reliability and scalability
- Dynamical changes of ANN stricture
- Solution for XOR and overfitting problems
- Development of the new advanced software for:
- Big and super big data
- Fast performance
- Processing unindexed data
- Data protection
- High system reliability
- Solving unsolved problems, etc.
PANN™ is extremely fast on Graphical Process Units. This makes possible creation of a Supercomputer based on both GPUs and PANN™. Market of GPUs supercomputers is already about $18B.
The market is ready for this:
- Many supercomputer development companies use GPUs for parallel mathematical operations, thus increasing calculation speed. For example, Cray, IBM, Dell, and HPE.
- Some companies use GPUs for ANN speed increasing. nVidia, for example, uses GPU to increase ANN speed 20+ times in comparison with CPU.