Browsing by Author "Tuo-Hung HOU"

Now showing 1 - 3 of 3

FABRICATION METHOD FOR TWO-DIMENSIONAL MATERIALS
(2018-10-11)
Tuo-Hung HOU
;
Jyun-Hong Huang
A fabrication method for two-dimensional materials of the present invention includes the following steps: forming a thin film having at least one two-dimensional element on a substrate; forming at least one capping layer on the thin film; annealing the thin film to form a two-dimensional material film after the capping layer is formed.
IMPACT IONIZATION SEMICONDUCTOR DEVICE AND MANUFACTURING METHOD THEREOF
(2018-05-31)
Tuo-Hung HOU
;
Samuel C. PAN
;
Pang-Shiuan LIU
A semiconductor device including a field effect transistor (FET) device includes a substrate and a channel structure formed of a two-dimensional (2D) material over the substrate. Source and drain contacts are formed partially over the 2D material. A first dielectric layer is formed at least partially over the channel structure and at least partially over the source and drain contacts. The first dielectric layer is configured to trap charge carriers. A second dielectric layer is formed over the first dielectric layer, and a gate electrode is formed over the second dielectric layer.
NEURAL NETWORK PROCESSING SYSTEM
(2018-11-15)
Tuo-Hung HOU
;
Chih-Cheng CHANG
;
Jen-Chieh LIU
A neural network processing system includes at least one synapse and a neuron circuit. The synapse receives an input signal and has an external weighted value and an internal weighted value, and the internal weighted value has a variation caused by an external stimulus. When the variation of the internal weighted value accumulates to a threshold value, the external weighted value varies and the input signal is multiplied by the external weighted value of the synapse to generate a weighted signal. A neuron circuit is connected with the synapse to receive the weighted signal transmitted by the synapse, and calculates and outputs the weighted signal. The present invention can simultaneously accelerate the prediction and learning functions of the deep learning and realize a hardware neural network with high precision and real-time learning.