Figure 7 - uploaded by Oleh Kolesnytskyj
Content may be subject to copyright.
Bipolar transistors with insulated gate (IGBT): a) inside structure of IGBT-device, b) IGBT-devise symbol. IGBT-devices are a new compromise technical solution that allowed to combine the positive qualities as bipolar (small voltage drop in the open state, high voltage switching) and MOSFET-transistors (low power management, high speed switching). At the same time losses are increasing proportionally to current, rather than to square of the current, as in field-effect transistors. Maximum voltage in IGBT-transistors is limited by technological breakdown and today produced devices with operating voltage up to 4000 V. This residual voltage on transistor in switched state does not exceed 2 ... 3 V. Neural circuit within bispin-device using IGBT-transistor VT1 shown in Fig. 8. As shown in Fig. 8, IGBT-transistor VT1 loaded on the array of N LEDs (or semiconductor lasers) VD3 ... VD (N +2). Properties of IGBT-transistor allow to do this, because switching current in modern IGBT-transistors close to 600 A, and switching frequency-up to 150 kHz.
Source publication
Proposed by the authors compact optoelectronic implementation of a
spiking neural network uses a matrix of semiconductor lasers. Also
proposed the implementation of neural element on bispin-device, which is
able to manage bya range of lasers in the array. Described the
principles of the network in the training and operation mode. To modify
the conn...
Similar publications
![Fig. 1: Spiking neural network architecture; from [10].](profile/Hananel-Hazan/publication/328400536/figure/fig1/AS:692522569457664@1542121655043/Spiking-neural-network-architecture-from-10_Q320.jpg)
Agriculture is a major source of income of a nation’s economy and it plays an important role in feeding mankind. Agriculturists and scientists are working hard to maximize productivity while minimizing the impact on the environment. One important aspect of smart agriculture is disease management in crops. Crops are affected by several diseases caus...
Brain-inspired deep spiking neural network (DSNN) which emulates the function of the biological brain provides an effective approach for event-stream spatiotemporal perception (STP), especially for dynamic vision sensor (DVS) signals. However, there is a lack of generalized learning frameworks that can handle various spatiotemporal modalities beyon...
A spiking neural network model inspired by synaptic pruning is developed and trained to extract features of hand-written digits. The network is composed of three spiking neural layers and one output neuron whose firing rate is used for classification. The model detects and collects the geometric features of the images from the Modified National Ins...
Citations
... In [12], an implementation of optoelectronic spiking neural network is proposed. It is made in a hybrid form, i.e. it combines optical two-dimensional spatially-light modulators (SLM) and electronic (VLSI) components. ...
... In [12] it is shown that 1 neuron in a such "sandwich structure" can be placed on an area of 10×10 microns. If aperture of 3 cm is considered to be a technologically normal size for optoelectronic devices, then it can accommodate 3000 pixels. ...
In this paper, we present a compact solution for optical interconnects in optoelectronic integrated neural networks using high-contrast all-dielectric nano-post arrays. The nano-post arrays are made of amorphous silicon, which has a high refractive index and high transmittance in the near infrared. The radius of each post is changed to generate different phase delays. Deflection and convergence of the light are realized by proper design of the phase profile of the nano-post array. Connection efficiencies are calculated by numerical simulations and compared with those of zone plate interconnects. Simulation results show that the proposed nano-post arrays can have superior performance over zone plates in applications that require short focal length and high efficiency.
