17813834. HYBRID MACHINE LEARNING ARCHITECTURE WITH NEURAL PROCESSING UNIT AND COMPUTE-IN-MEMORY PROCESSING ELEMENTS simplified abstract (QUALCOMM Incorporated)
Contents
- 1 HYBRID MACHINE LEARNING ARCHITECTURE WITH NEURAL PROCESSING UNIT AND COMPUTE-IN-MEMORY PROCESSING ELEMENTS
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 HYBRID MACHINE LEARNING ARCHITECTURE WITH NEURAL PROCESSING UNIT AND COMPUTE-IN-MEMORY PROCESSING ELEMENTS - A simplified explanation of the abstract
- 1.4 Simplified Explanation
- 1.5 Potential Applications
- 1.6 Problems Solved
- 1.7 Benefits
- 1.8 Original Abstract Submitted
HYBRID MACHINE LEARNING ARCHITECTURE WITH NEURAL PROCESSING UNIT AND COMPUTE-IN-MEMORY PROCESSING ELEMENTS
Organization Name
Inventor(s)
Mustafa Badaroglu of Leuven (BE)
Zhongze Wang of San Diego CA (US)
Titash Rakshit of Austin TX (US)
HYBRID MACHINE LEARNING ARCHITECTURE WITH NEURAL PROCESSING UNIT AND COMPUTE-IN-MEMORY PROCESSING ELEMENTS - A simplified explanation of the abstract
This abstract first appeared for US patent application 17813834 titled 'HYBRID MACHINE LEARNING ARCHITECTURE WITH NEURAL PROCESSING UNIT AND COMPUTE-IN-MEMORY PROCESSING ELEMENTS
Simplified Explanation
The patent application describes a hybrid architecture that combines neural processing units (NPU) and compute-in-memory (CIM) elements for performing machine learning tasks. This architecture includes a neural-network-processing circuit with CIM processing elements, NPU processing elements, and a bus connecting them.
- The architecture combines NPU and CIM elements for machine learning tasks.
- The neural-network-processing circuit includes CIM processing elements, NPU processing elements, and a bus.
- Data is processed in the circuit by transferring it between CIM and NPU processing elements via the bus.
Potential Applications
- Machine learning tasks
- Artificial intelligence applications
- Data analysis and pattern recognition
Problems Solved
- Improved performance and efficiency in machine learning tasks
- Enhanced processing capabilities for complex data analysis
- Integration of NPU and CIM elements for optimized machine learning algorithms
Benefits
- Faster and more efficient machine learning processing
- Improved accuracy and performance in data analysis
- Enhanced capabilities for AI applications
- Potential for reduced power consumption and cost in machine learning systems
Original Abstract Submitted
Methods and apparatus for performing machine learning tasks, and in particular, a hybrid architecture that includes both neural processing unit (NPU) and compute-in-memory (CIM) elements. One example neural-network-processing circuit generally includes a plurality of CIM processing elements (PEs), a plurality of neural processing unit (NPU) PEs, and a bus coupled to the plurality of CIM PEs and to the plurality of NPU PEs. One example method for neural network processing generally includes processing data in a neural-network-processing circuit comprising a plurality of CIM PEs, a plurality of NPU PEs, and a bus coupled to the plurality of CIM PEs and to the plurality of NPU PEs; and transferring the processed data between at least one of the plurality of CIM PEs and at least one of the plurality of NPU PEs via the bus.
