This paper presents selected design and operation details of a custom integrated neural chip. This neural processing chip is designed in the recent 0.18 μm, single poly, six-layer Copper Interconnect Technology. The chip realizes an architecture that achieves the task of autonomous-learning execution times in micro to milli seconds. The core consists of basic building blocks of 4-quadrant multi...

We constructed an analog circuit generating fluctuations of which a probability density function has power law tails. In the circuit fluctuations with an arbitrary exponent of the power law can be obtained by tuning the resistance. A theory of a differential equation with both multiplicative and additive noises which describes the circuit is introduced. The circuit is composed of a noise genera...

A Built-In Self-Test (BIST) approach has been proposed for functionality measurements of analog circuitry in mixed-signal systems. The BIST circuitry consists of a direct digital synthesizer (DDS) based test pattern generator (TPG) and multiplier/accumulator (MAC) based output response analyzer (ORA). In this paper we investigate and discuss the effects of phase delay on analog functionality me...

This paper focuses on the design of two analog nonlinear transformations dedicated to signal processing such as energy detection: square function and Teager Energy Operator (TEO). Both requiring an multiplier, this firstly analyses equations a MOS Gilbert cell in order operate around mid supply voltage. Considering this, having differential input range ±400 mV, has been designed using AMS 0.35 ...

Consider a four-quadrant detector consisting of four circular active regions of area Aq each, placed symmetrically around the sample, as shown schematically in Fig. 1(a). The sample holder is inserted from the right, and the quadrants are 90° apart, oriented symmetrically at ±45° with respect to the primary tilt axis. The specimen tilt angles are labeled  and β, with positive angles correspond...

Neural networks are suitable to resolve problems where conventional resolution methods fail. The multipliers form a basic and important block in realising a neural network and this is commonly known as “Synapse”. Their roles are to multiply an input current with trained digital weights. Several research attempts to implement synapses. Some use numeric implementation whereas others use analogue ...