18166859. NEUROMORPHIC APPARATUS HAVING 3D STACKED SYNAPTIC STRUCTURE AND MEMORY DEVICE HAVING THE SAME simplified abstract (Samsung Electronics Co., Ltd.)

From WikiPatents
Jump to navigation Jump to search

NEUROMORPHIC APPARATUS HAVING 3D STACKED SYNAPTIC STRUCTURE AND MEMORY DEVICE HAVING THE SAME

Organization Name

Samsung Electronics Co., Ltd.

Inventor(s)

Jaechul Park of Yongin-si (KR)

Sangwook Kim of Seongnam-si (KR)

NEUROMORPHIC APPARATUS HAVING 3D STACKED SYNAPTIC STRUCTURE AND MEMORY DEVICE HAVING THE SAME - A simplified explanation of the abstract

This abstract first appeared for US patent application 18166859 titled 'NEUROMORPHIC APPARATUS HAVING 3D STACKED SYNAPTIC STRUCTURE AND MEMORY DEVICE HAVING THE SAME

Simplified Explanation

The patent application describes a neuromorphic apparatus that includes a three-dimensionally-stacked synaptic structure. It consists of multiple unit synaptic modules, each containing multiple synaptic layers. The unit synaptic modules also include decoders for accessing the synaptic layers and memristers.

  • The neuromorphic apparatus has a three-dimensional structure with stacked synaptic layers.
  • It includes multiple unit synaptic modules, each containing multiple synaptic layers.
  • Each unit synaptic module has a decoder that allows access to the synaptic layers.
  • A second decoder provides a level selection signal to the first decoder for accessing a specific unit synaptic module.
  • A third decoder generates an address for accessing specific memristers in the synaptic layers.

Potential applications of this technology:

  • Artificial intelligence and machine learning systems
  • Neuromorphic computing
  • Brain-inspired computing architectures

Problems solved by this technology:

  • Efficient and compact implementation of neuromorphic systems
  • Improved performance and scalability of artificial intelligence systems
  • Simulating the behavior of biological neural networks

Benefits of this technology:

  • Higher computational density and efficiency
  • Reduced power consumption
  • Faster processing speeds
  • Improved accuracy and reliability in neural network simulations


Original Abstract Submitted

A neuromorphic apparatus includes a three-dimensionally-stacked synaptic structure, and includes a plurality of unit synaptic modules, each of the plurality of unit synaptic modules including a plurality of synaptic layers, each of the plurality of synaptic layers including a plurality of stacked layers, and each of the plurality of unit synaptic modules further including a first decoder interposed between two among the plurality of synaptic layers. The neuromorphic apparatus further includes a second decoder that provides a level selection signal to the first decoder included in one among the plurality of unit synaptic modules to be accessed, and a third decoder that generates an address of one among a plurality of memristers to be accessed in a memrister array of one among the plurality of synaptic layers included in the one among the plurality of unit synaptic modules to be accessed.