Semiconductor materials contain a large number of ingredients such as resins, fillers and additives in various mixing ratios; by optimizing these formulations high-performance materials are obtained. However, the theoretical number of combinations for the development theme that we are working on is enormous, exceeding 10 to the 50th power. Thus, it would take decades to explore all possible combinations of these ingredients and their mixing ratios with conventional artificial intelligence (AI) models, and for this reason only a portion of the theoretical combinations had been extracted to search for the optimal combination of formulations.
To reduce the time required for the exploration, we focused on Fujitsu Ltd's Digital Annealer(1), the first quantum-inspired digital technology(2). In order to utilize Digital Annealer, input in the form of an Ising model(3), an analysis method of statistical mechanics, is required. We were successful in expressing an originally developed AI model, capable of predicting the characteristics of semiconductor materials from the complex compounding conditions of materials, in the Ising model. By simulating the Ising model on Digital Annealer, we have reduced the required exploration time to tens of seconds, or about 1/72,000 of the time required by conventional AI models, which search by conditions limiting the type and amount of compounding. In addition, we were able to obtain a formula that achieves 30% higher performance as a semiconductor material.
In our "Long-term Vision for Newly Integrated Company," the Showa Denko Group announced that it would commit itself to the research and development of AI and computational science, the core of its fundamental R&D activities. The results of this development are an example of the achievements of R&D activities based on the application of "Chemistry to Think" and "Chemistry to Formulate," both of which the Group has defined as basic frameworks for technological development. The Group will apply this development to various materials, accelerate its development activities, and provide customers with solutions for problems, thereby contributing to a sustainable society.
(1) Digital Annealer: Domain specific architecture (basic computer design consisting of memory and computing circuits) specialized in solving computationally intensive combinatorial optimization problems. (https://www.fujitsu.com/global/services/business-services/digital-annealer/)
(2) Quantum-inspired computing technology: High-performance computing technology inspired by quantum technology, though not directly using quantum effects.
(3) Ising model: A statistical mechanical model for describing the behavior of spins in magnetic materials. The model describes the macroscopic magnetization of a magnetic material by considering the interaction between the spins and the coupling to the external magnetic field. The model is applied to a wide range of research areas, including combinatorial optimization problems.
To reduce the time required for the exploration, we focused on Fujitsu Ltd's Digital Annealer(1), the first quantum-inspired digital technology(2). In order to utilize Digital Annealer, input in the form of an Ising model(3), an analysis method of statistical mechanics, is required. We were successful in expressing an originally developed AI model, capable of predicting the characteristics of semiconductor materials from the complex compounding conditions of materials, in the Ising model. By simulating the Ising model on Digital Annealer, we have reduced the required exploration time to tens of seconds, or about 1/72,000 of the time required by conventional AI models, which search by conditions limiting the type and amount of compounding. In addition, we were able to obtain a formula that achieves 30% higher performance as a semiconductor material.
In our "Long-term Vision for Newly Integrated Company," the Showa Denko Group announced that it would commit itself to the research and development of AI and computational science, the core of its fundamental R&D activities. The results of this development are an example of the achievements of R&D activities based on the application of "Chemistry to Think" and "Chemistry to Formulate," both of which the Group has defined as basic frameworks for technological development. The Group will apply this development to various materials, accelerate its development activities, and provide customers with solutions for problems, thereby contributing to a sustainable society.
(1) Digital Annealer: Domain specific architecture (basic computer design consisting of memory and computing circuits) specialized in solving computationally intensive combinatorial optimization problems. (https://www.fujitsu.com/global/services/business-services/digital-annealer/)
(2) Quantum-inspired computing technology: High-performance computing technology inspired by quantum technology, though not directly using quantum effects.
(3) Ising model: A statistical mechanical model for describing the behavior of spins in magnetic materials. The model describes the macroscopic magnetization of a magnetic material by considering the interaction between the spins and the coupling to the external magnetic field. The model is applied to a wide range of research areas, including combinatorial optimization problems.
IonQ Achieves Industry Leading Performance on Next Generation Barium Qubits