Neuromorphic application of oxide semiconductors
May 21-25, 2017
Artificial intelligences are promising as key technologies in future societies. However, the conventional ones are executed using complicated software on high-specked hardware, and the machine size is very bulky and power consumption is unbelievably huge. Therefore, we are investigating "braintype integrated system", namely, neural network built only by hardware, which can be compact, low power, robust, and integrated on everything in future. In order to realize that system, simplification of the processing elements, such as neurons and synapse, three-dimensional structure, and low cost fabrication are required. We have succeeded in that simplification and are trying to utilize oxide semiconductors for the neuromorphic application because they can be fabricated using low cost fabrication such as sputtering and printing, by which the three-dimensional structure can be obtained in future.
Please click Additional Files below to see the full abstract.
Mutsumi Kimura, Yasuhiko Nakashima, Tomoya Kameda, and Tokiyoshi Matsuda, "Neuromorphic application of oxide semiconductors" in "International Conference on Semiconductor Technology for Ultra-Large Scale Integrated Circuits and Thin Film Transistors VI (ULSIC vs TFT 6)", Yue Kuo (Texas A&M University, USA) Olivier Bonnaud (University of Rennes I, France) Eds, ECI Symposium Series, (2017). http://dc.engconfintl.org/ulsic_tft_6/33