Parallel Access to Volatile Memory by Processing Device for Machine Learning
A processing device, technology of machine learning, applied in the field of memory system
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0017] At least some aspects of the present disclosure relate to parallel access to volatile memory by a processing device that supports processing of machine learning (eg, neural networks).
[0018] Deep learning machines, such as those that support the processing of Convolutional Neural Networks (CNNs), process to determine an extremely large number of operations per second. For example, input / output data, deep learning network training parameters, and intermediate results are continuously fetched from and stored in one or more memory devices (eg, DRAM). DRAM-type memories are typically used due to their cost advantages when large storage densities are involved (eg, storage densities greater than 100MB). In one example of a deep learning hardware system, a computing unit (eg, a system on a chip (SOC), FPGA, CPU, or GPU) is attached to a memory device (eg, a DRAM device).
[0019] It has been recognized that existing machine learning architectures (eg, as used in deep learni...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap