Analog VLSI and Neural Systems
ثبت نشده
چکیده
We have done integration and differentiation with simple, single–timeconstant circuits that had τs + 1 in the denominator of their transfer functions. These systems gave an exponentially damped response to step or impulse inputs. In Chapter 8, we showed how a second-order system can give rise to a sinusoidal response. In this chapter, we will discuss a simple circuit that can generate a sinusoidal response. We call this circuit the second-order section; we can use it to generate any response that can be represented by two poles in the complex plane, where the two poles have both real and imaginary parts. With this circuit, we can adjust the positions of the complex-conjugate poles anywhere in the plane. The second-order circuit is shown in Figure 11.1; it contains two cascaded follower–integrator circuits and an extra amplifier. The capacitance C is the same for both stages (C1 = C2 = C), and the transconductance of the two feed-forward amplifiers, A1 and A2, are the same: G1 = G2 = G (approximately—if G is defined as the average of G1 and G2, small differences will have no first-order effect on the parameters of the response). We obtain an oscillatory response by adding the feedback amplifier A3. This amplifier has transconductance G3, and its output current is proportional to the difference between V2 and V3, but the sign of the feedback is positive; for small signals, I3 is equal to G3(V2 − V3). If we reduce the feedback to zero by shutting off the bias current in A3, each follower–integrator circuit will have the transfer function given
منابع مشابه
On Fault Probabilities and Yield Models for Analog VLSI Neural Networks
We investigate the estimation of fault probabilities and yield for analog VLSI implementations of neural computation. Our analysis is limited to structures that can be mapped directly onto silicon as truly distributed parallel processing systems. Our work improves on the framework suggested recently by Feltham and Maly [3] and is also applicable to analog or mixed analog/digital VLSI systems.
متن کاملCurrent Mode Subthreshold Analog MOS Components for Neuromorphic Processing TECHNICAL REPORT
Analog VLSI neuromorphic computation has become an active eld of research [Mead, 1990] [Andreou et al., 1991] [Cohen and Andreou, 1992] in the last few years. Indeed, arti cial neural systems inspired by biological neural networks are becoming an increasingly popular topic among analog VLSI designers. Biological neural systems for sensory perception and motor control are both compact and energy...
متن کاملSynaptic Dynamics in Analog VLSI
Synapses are crucial elements for computation and information transfer in both real and artificial neural systems. Recent experimental findings and theoretical models of pulse-based neural networks suggest that synaptic dynamics can play a crucial role for learning neural codes and encoding spatiotemporal spike patterns. Within the context of hardware implementations of pulse-based neural netwo...
متن کاملImplementing Neural Architectures Using Analog VLSI Circuits
Biological systems routinely perform computations, such as speech recognition and the calculation of visual motion, that baffle our most powerful computers. Analog very large-scale integrated (VLSI) technology allows us not only to study and simulate biological systems, but also to emulate them in designing artificial sensory systems. A methodology for building these systems in CMOS VLSI techno...
متن کاملA VLSI convolutional neural network for image recognition using merged/mixed analog-digital architecture
Hierarchical convolutional neural networks are a well-known robust image-recognition model. In order to apply this model to robot vision or various intelligent vision systems, its VLSI implementation with high performance and low power consumption is required. This paper proposes a VLSI convolutional network architecture using a hybrid approach composed of pulse-width modulation (PWM) and digit...
متن کاملComputation in Neuromorphic Analog VLSI Systems
In this paper we present an overview of basic neuromorphic analog circuits that are typically used as building blocks for more complex neuromorphic systems. We present the main principles used by the neuromorphic engineering community and describe, as case example, a neuromorphic VLSI system for modeling selective visual attention. 1 Neuromorphic Engineering The term “neuromorphic” was coined b...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2013