Integrated Optical Circuit Emulating Neuron Functionality
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional computing architectures, such as the von Neumann computer architecture, are inefficient in terms of power consumption and space requirements, and there is a challenge in developing compact devices that emulate the plasticity of biological synapses for neuromorphic computation.
Innovation Solution
An integrated optical circuit configured to process phase-encoded optical input signals, utilizing an optical interferometer system and a phase-shifting device to emulate neuron functionality, allowing for efficient signal restoration and implementation of neuron and synapse functions in the optical domain.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Use of energy by stationary object
If conventional von Neumann computer architecture is used, then computing tasks can be performed, but power consumption is high and space requirements are large
Solution Approach 1:
The patent replaces conventional electronic von Neumann architecture with an optical computing system using photonic integrated circuits. Optical signals replace electrical signals for data transmission and processing, eliminating the need for electron-based logic gates and memory access mechanisms that consume high power in traditional systems
Solution Approach 2:
The patent transitions from electronic domain to optical domain, utilizing light-based computation. This dimensional change enables parallel processing capabilities and eliminates the sequential bottlenecks of conventional architecture, achieving higher computational efficiency with lower power consumption
2Adaptability or versatility
If biological synapse plasticity is emulated in conventional electronic devices, then neuromorphic computation can be achieved, but device compactness is compromised
Solution Approach 1:
The patent uses phase-change materials that can switch between different refractive index states in response to optical signals. This parameter change enables the emulation of synapse plasticity - the ability to strengthen or weaken connections - within a compact photonic integrated circuit structure, achieving biological-like adaptability without requiring large device volumes
Solution Approach 2:
The patent employs composite photonic structures combining waveguides, interferometers, and phase-change materials. This composite approach integrates multiple functions (signal transmission, interference-based computation, and plasticity emulation) into a single compact device, achieving both synapse plasticity and small form factor
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
The solution enables efficient emulation of neuron and synapse functions, decoupling phase from propagation losses and amplifying reduced amplitudes, thereby providing a compact and power-efficient implementation of neuromorphic networks.
Implementation Method 1
The optical interferometer system is configured to superimpose the plurality of optical input signals and the optical reference signal into a plurality of first interference signals
Implementation Method 2
The phase-shifting device is configured to provide the phase-encoded optical output signal in dependence on the second interference signal
Data Source
Figure 1~2
Figure 3~4
Figure 5~6
AI summary
An integrated optical circuit for an optical neural network is provided. The optical circuit is configured to process a plurality of phase-encoded optical input signals and to provide a phase-encoded optical output signal depending on the phase-encoded optical input signals. The phase-encoded optical output signal emulates a neuron functionality with respect to the plurality of phase-encoded optical input signals. Such an embodied optical circuit uses the phase to encode information in the optical domain. A related method and a related design structure are further provided.