RESUMO
One of the biggest struggles while working with artificial neural networks is being able to come up with models which closely match biological observations. Biological neural networks seem to capable of creating and pruning dendritic spines, leading to synapses being changed, which results in higher learning capability. The latter forms the basis of the present study in which a new ionic model for reservoir-like networks, consisting of spiking neurons, is introduced. High plasticity of this model makes learning possible with a fewer number of neurons. In order to study the effect of the applied stimulus in an ionic liquid space through time, a diffusion operator is used which somehow compensates for the separation between spatial and temporal coding in spiking neural networks and therefore, makes the mentioned model suitable for spatiotemporal patterns. Inspired by partial structural changes in the human brain over the years, the proposed model evolves during the learning process. The effect of topological evolution on the proposed model's performance for some classification problems is studied in this paper. Several datasets have been used to evaluate the performance of the proposed model compared to the original LSM. Classification results via separation and accuracy values have shown that the proposed ionic liquid outperforms the original LSM.
RESUMO
Memristor devices have attracted tremendous interest due to different applications ranging from nonvolatile data storage to neuromorphic computing units. Exploring the role of surface roughness of the bottom electrode (BE)/active layer interface provides useful guidelines for the optimization of the memristor switching performance. This study focuses on the effect of surface roughness of the BE electrode on the switching characteristics of Au/TiO2/Au three-layer memristor devices. An optimized wet-etching treatment condition was found to modify the surface roughness of the Au BE where the measurement results indicate that the roughness of the Au BE is affected by both duration time and solution concentrations of the wet-etching process. Then we fabricated arrays of TiO2-based nanostructured memristors sandwiched between two sets of cross-bar Au electrode lines (junction area 900 µm2). The results revealed a reduction in the working voltages in current-voltage characteristic of the device performance when increasing the surface roughness at the Au(BE)/TiO2 active layer interface. The set voltage of the device (Vset) significantly decreased from 2.26-1.93 V when we increased the interface roughness from 4.2-13.1 nm. The present work provides information for better understanding the switching mechanism of titanium-dioxide-based devices, and it can be inferred that enhancing the roughness of the Au BE/TiO2 active layer interface leads to a localized non-uniform electric field distribution that plays a vital role in reducing the energy consumption of the device.
RESUMO
In this paper, a novel neuro-fuzzy computing system is proposed where its learning is based on the creation of fuzzy relations by using a new implication method without utilizing any exact mathematical techniques. Then, a simple memristor crossbar-based analog circuit is designed to implement this neuro-fuzzy system which offers very interesting properties. In addition to high connectivity between neurons and being fault tolerant, all synaptic weights in our proposed method are always non-negative, and there is no need to adjust them precisely. Finally, this structure is hierarchically expandable, and it can do fuzzy operations in real time since it is implemented through analog circuits. Simulation results confirm the efficiency and applicability of our neuro-fuzzy computing system. They also indicate that this system can be a good candidate to be used for creating artificial brain.
