Nano Dimension has been granted a patent for a method that trains a new neural network to mimic a target neural network without access to the original training dataset. The method involves probing both networks with input data, detecting differences, and iteratively training the new network to minimize discrepancies. GlobalData’s report on Nano Dimension gives a 360-degree view of the company including its patenting strategy. Buy the report here.
Smarter leaders trust GlobalData
According to GlobalData’s company profile on Nano Dimension, Spacecraft 3D Printing was a key innovation area identified from patents. Nano Dimension's grant share as of May 2024 was 19%. Grant share is based on the ratio of number of grants to total number of patents.
Training new neural network to mimic target neural network
A recently granted patent (Publication Number: US11961003B2) outlines a method for training a new neural network to mimic a target neural network without direct access to the target network or its original training data. The method involves probing both networks with input data to detect differences in output, generating a divergent probe training dataset based on these differences, and training the new network to minimize variations between its output and the target network. This process is iteratively refined by updating the training dataset to focus on input-output pairs with significant differences, resulting in a new neural network with fewer layers and a smaller file size compared to the target network.
Furthermore, the patent describes a system with processors configured to implement this method, along with memories to store the training dataset. The processors can generate the dataset using additional neural networks or evolutionary models, adjust the dataset based on input data, and execute the trained new network in real-time. Additionally, a non-transitory computer-readable medium containing instructions for training the new network and executing it in a runtime phase is also detailed in the patent. This innovative approach to neural network training offers a novel way to mimic complex networks without direct access to their internal structures, potentially leading to more efficient and streamlined neural network models.
To know more about GlobalData’s detailed insights on Nano Dimension, buy the report here.
Data Insights
From
The gold standard of business intelligence.
Blending expert knowledge with cutting-edge technology, GlobalData’s unrivalled proprietary data will enable you to decode what’s happening in your market. You can make better informed decisions and gain a future-proof advantage over your competitors.
GlobalData, the leading provider of industry intelligence, provided the underlying data, research, and analysis used to produce this article.
GlobalData Patent Analytics tracks bibliographic data, legal events data, point in time patent ownerships, and backward and forward citations from global patenting offices. Textual analysis and official patent classifications are used to group patents into key thematic areas and link them to specific companies across the world’s largest industries.
