اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدSome Interesting Features of Memristor CNN
56
0
0.0
(
0
)
تأليف
Makoto Itoh
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
In this paper, we introduce some interesting features of a memristor CNN (Cellular Neural Network). We first show that there is the similarity between the dynamics of memristors and neurons. That is, some kind of flux-controlled memristors can not respond to the sinusoidal voltage source quickly, namely, they can not switch `on rapidly. Furthermore, these memristors have refractory period after switch `on, which means that it can not respond to further sinusoidal inputs until the flux is decreased. We next show that the memristor-coupled two-cell CNN can exhibit chaotic behavior. In this system, the memristors switch `off and `on at irregular intervals, and the two cells are connected when either or both of the memristors switches `on. We then propose the modified CNN model, which can hold a binary output image, even if all cells are disconnected and no signal is supplied to the cell after a certain point of time. However, the modified CNN requires power to maintain the output image, that is, it is volatile. We next propose a new memristor CNN model. It can also hold a binary output state (image), even if all cells are disconnected, and no signal is supplied to the cell, by memristors switching behavior. Furthermore, even if we turn off the power of the system during the computation, it can resume from the previous average output state, since the memristor CNN has functions of both short-term (volatile) memory and long-term (non-volatile) memory. The above suspend and resume feature are useful when we want to save the current state, and continue work later from the previous state. Finally, we show that the memristor CNN can exhibit interesting two-dimensional waves, if an inductor is connected to each memristor CNN cell.
قيم البحث
اقرأ أيضاً
A simple and unambiguous test has been recently suggested [J. Phys. D: Applied Physics, 52, 01LT01 (2018)] to check experimentally if a resistor with memory is indeed a memristor, namely a resistor whose resistance depends only on the charge that flo
ws through it, or on the history of the voltage across it. However, although such a test would represent the litmus test for claims about memristors (in the ideal sense), it has yet to be applied widely to actual physical devices. In this paper, we experimentally apply it to a current-carrying wire interacting with a magnetic core, which was recently claimed to be a memristor (so-called `$Phi$ memristor) [J. Appl. Phys. 125, 054504 (2019)]. The results of our experiment demonstrate unambiguously that this `$Phi$ memristor is not a memristor: it is simply an inductor with memory. This demonstration casts further doubts that ideal memristors do actually exist in nature or may be easily created in the lab.
This is a review of some of the interesting properties of the Riemann Zeta Function.
We demonstrate that AdS_5 x T^{pq} is unstable, in the sense of Breitenlohner and Freedman, for unequal p and q. This settles, negatively, the long-standing question of whether the T^{pq} manifolds for unequal p and q might correspond to non-supersym
metric fixed points of the renormalization group. We also show that the AdS_3 x S^7 vacuum of Sugimotos USp(32) open string theory is unstable. This explains, at a heuristic level, the apparent absence of a heterotic string dual.
An analysis of the literature shows that there are two types of non-memristive models that have been widely used in the modeling of so-called memristive neural networks. Here, we demonstrate that such models have nothing in common with the concept of
memristive elements: they describe either non-linear resistors or certain bi-state systems, which all are devices without memory. Therefore, the results presented in a significant number of publications are at least questionable, if not completely irrelevant to the actual field of memristive neural networks.
We present new computational building blocks based on memristive devices. These blocks, can be used to implement either supervised or unsupervised learning modules. This is achieved using a crosspoint architecture which is an efficient array implemen
tation for nanoscale two-terminal memristive devices. Based on these blocks and an experimentally verified SPICE macromodel for the memristor, we demonstrate that firstly, the Spike-Timing-Dependent Plasticity (STDP) can be implemented by a single memristor device and secondly, a memristor-based competitive Hebbian learning through STDP using a $1times 1000$ synaptic network. This is achieved by adjusting the memristors conductance values (weights) as a function of the timing difference between presynaptic and postsynaptic spikes. These implementations have a number of shortcomings due to the memristors characteristics such as memory decay, highly nonlinear switching behaviour as a function of applied voltage/current, and functional uniformity. These shortcomings can be addressed by utilising a mixed gates that can be used in conjunction with the analogue behaviour for biomimetic computation. The digital implementations in this paper use in-situ computational capability of the memristor.
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
