Smart Engines researchers have been awarded a US patent for a proprietary development that significantly improves the performance of neural network architectures used for image recognition. The invention combines the blocks used in modern neural networks with a classic tool for analyzing real-world images – the Hough Transform. The inventors expect the proposed architecture to open a new chapter in the success story of neural network technology in computer vision. The patented solution is already being used in Smart Engines’ software products for autonomous scanning of documents. Additionally, the authors of the invention proposed a new neural network architecture that exercises in arithmetic, which correctly places the first and last digits of the result and even guesses its length, but puts the middle digits out of the blue.
Related Posts
