Bisection Neural Network Toward Reconfigurable Hardware Implementation.

A hardware-friendly bisection neural network (BNN) topology is proposed in this work for approximately implementing massive pieces of complex functions in arbitrary on-chip configurations. Instead of the conventional reconfigurable fully connected neural network (FC-NN) circuit topology, the proposed hardware-friendly topology performs NN behaviors in a bisection structure, in which each neuron includes two constant synapse connections for both inputs and outputs. Compared with the FC-NN one, the reconfiguration of the BNN circuit topology eliminates the remarkable amount of dummy synapse connections in hardware.

Neuromorphic chip integrated with a large-scale integration circuit and amorphous-metal-oxide semiconductor thin-film synapse devices.

Artificial intelligences are promising in future societies, and neural networks are typical technologies with the advantages such as self-organization, self-learning, parallel distributed computing, and fault tolerance, but their size and power consumption are large. Neuromorphic systems are biomimetic systems from the hardware level, with the same advantages as living brains, especially compact size, low power, and robust operation, but some well-known ones are non-optimized systems, so the above benefits are only partially gained, for example, machine learning is processed elsewhere to download fixed parameters. To solve these problems, we are researching neuromorphic systems from various viewpoints.

Neuromorphic System Using Memcapacitors and Autonomous Local Learning.

Artificial intelligence is used for various applications and is promising as an indispensable infrastructure in future societies. Neural networks are representative technologies that imitate human brains and exhibit various advantages. However, the size is bulky, the power is huge, and some advantages are not demonstrated because they are executed on Neumann-type computers.

Amorphous metal oxide semiconductor thin film, analog memristor, and autonomous local learning for neuromorphic systems.

Artificial intelligence is a promising concept in modern and future societies. Presently, software programs are used but with a bulky computer size and large power consumption. Conversely, hardware systems named neuromorphic systems are suggested, with a compact computer size and low power consumption.

Memristive characteristic of an amorphous Ga-Sn-O thin-film device.

We have found a memristive characteristic of an α-GTO thin-film device. The α-GTO thin-film layer is deposited using radio-frequency (RF) magnetron sputtering at room temperature and sandwiched between the Al top and bottom electrodes. It is found that the hysteresis loop of the flowing current (I) and applied voltage (V) characteristic becomes larger and stable after the one hundredth cycle.

Studies on the mechanism of printing film-coated tablets containing titanium dioxide in the film by using UV laser irradiation.

Aim: The purpose of this article is to study a detailed mechanism of printing when film-coated tablets were irradiated by UV laser at a wavelength of 355 nm.

Methods: Hydroxypropylmethylcellulose (HPMC) film containing titanium dioxide (TiO(2)) and the film not containing TiO(2) and TiO(2) powder were lirradiated by the UV laser and estimated by the morphological observation by zoom stereo microscope, thermogravimetric analysis (TGA), total color difference (dE), X-ray powder diffraction (XRD), and dispersive Raman microscopy.

Results: In the case of the film containing TiO(2), the film showed a visible change in its color from white to gray by the UV laser irradiation.