**3.1 CMOS neuron models**

In past few decades, researches on biological neurons have been fully investigated in the field of neuroscience [27–32]. In general, the dendrite, the soma, the axon and the synapse are four major elements of a biological neuron [33]. Within a nervous system, dendrites collect and transmit neural signal to the soma, while the soma plays an important role as the CPU to carry out the operation of the nonlinear transformation. Moreover, signals are processed and transmitted in form of a nerve impulse, also known as the spike [34]. During the operation, an output spike is formed when the input stimulus surpasses the threshold level, indicating as the firing process. **Figure 3** demonstrates a typical firing and resting operation in a biological neuron. Synapses along with the axon are then transmitted the spike data patterns to other neurons.

The leaky integrate-and-fire (LIF) neuron model plays an important role in the neuron design to convert raw analog signals into spikes [35]. **Figure 4** depicts the analog electronic circuit model of a LIF neuron. The input excitation, *Iex*, can be expressed as

$$I\_{ex} = C\_m \cdot \frac{d\,V\_m}{dt} + I\_{leak\nu} \tag{1}$$

**15**

**Figure 5.**

*Opening the "Black Box" of Silicon Chip Design in Neuromorphic Computing*

place. The LIF neuron is capable to process both firing and resetting operations,

From Eq. (1), it can be observed that the integration time over the membrane capacitor can be regulated by excitation and leakage currents. Such relation can be

> *dVm dt* <sup>+</sup> \_\_\_\_ *Vm Rleak*

Neural code is used to characterize raw analog signals into neural responses. In general, there are two distinct classes to represent neural codes. One class converts analog signals into a spike train where only the number of spikes matters, knowing as the rate code. Another class converts analog signals into the temporal response structure [36] where time intervals matters, knowing as the temporal code.

**Figure 5** demonstrates major differences between the rate code and the temporal code. In the rate code, analog signals are encoded into the firing rate within a sampling period, as shown in **Figure 5a**. Considering the implementation complexity, the rate encoding scheme is easier to implement through electronic circuits compared to the temporal encoding scheme; however, small variation of an analog signal in the temporal response structure are neglected, which makes the rate

*Neural codes in (a) rate code, (b) time-to-first-spike latency code, and (c) inter-spike-interval temporal code.*

determines the amount of leakage current. Thereby, the voltage

\_\_\_\_\_\_\_ *t*

, (2)

*Rleak*∙*Cm*. (3)

closely mimicking the biological behavior of neurons.

*Analog electronic circuit model of a LIF neuron.*

*Iex* = *Cm* ∙ \_\_\_\_

*Vm* = *Iex* ∙ *Rleak* − *e*

where \_\_\_ *Vm*\_ *Rleak*

**Figure 4.**

**3.2 Neural codes**

depicted by a simple resistor model, which can be rewritten as

potential across the membrane capacitor can be determined as

*DOI: http://dx.doi.org/10.5772/intechopen.83832*

where *Cm* is the membrane capacitance, \_\_\_\_ *dVm dt* represents the voltage potential across the membrane capacitor over time, and *Ileak* is the leakage current. During the operation, raw analog signals are firstly converted into an excitation current, which will be used to charge up the potential level across the membrane capacitor. When the voltage potential across the membrane capacitor surpasses the threshold level, the circuit fires a spike as its output. Once the firing process is accomplished, the membrane capacitor will be reset to its initial state until the next firing cycle takes

**Figure 3.** *Action potential of biological impulses.*

*Opening the "Black Box" of Silicon Chip Design in Neuromorphic Computing DOI: http://dx.doi.org/10.5772/intechopen.83832*

**Figure 4.** *Analog electronic circuit model of a LIF neuron.*

*Bio-Inspired Technology*

will be discussed.

expressed as

**3.1 CMOS neuron models**

**3. Spiking information processing**

In many brain-inspired neuromorphic computing systems, the interface between modules is often influenced by the signal propagation. The major design challenge in neuromorphic computing is the difficulty in adapting raw analog signals into a suitable data pattern, which can be used in the neuronal activities. Before digging deep into the architecture of our fabricated spiking neural network chip, in this section, a temporal encoding scheme through the analog IC design technique

In past few decades, researches on biological neurons have been fully investigated in the field of neuroscience [27–32]. In general, the dendrite, the soma, the axon and the synapse are four major elements of a biological neuron [33]. Within a nervous system, dendrites collect and transmit neural signal to the soma, while the soma plays an important role as the CPU to carry out the operation of the nonlinear transformation. Moreover, signals are processed and transmitted in form of a nerve impulse, also known as the spike [34]. During the operation, an output spike is formed when the input stimulus surpasses the threshold level, indicating as the firing process. **Figure 3** demonstrates a typical firing and resting operation in a biological neuron. Synapses along with

The leaky integrate-and-fire (LIF) neuron model plays an important role in the neuron design to convert raw analog signals into spikes [35]. **Figure 4** depicts the analog electronic circuit model of a LIF neuron. The input excitation, *Iex*, can be

*dVm*

across the membrane capacitor over time, and *Ileak* is the leakage current. During the operation, raw analog signals are firstly converted into an excitation current, which will be used to charge up the potential level across the membrane capacitor. When the voltage potential across the membrane capacitor surpasses the threshold level, the circuit fires a spike as its output. Once the firing process is accomplished, the membrane capacitor will be reset to its initial state until the next firing cycle takes

*dVm*

*dt* <sup>+</sup> *Ileak*, (1)

*dt* represents the voltage potential

the axon are then transmitted the spike data patterns to other neurons.

*Iex* = *Cm* ∙ \_\_\_\_

where *Cm* is the membrane capacitance, \_\_\_\_

**14**

**Figure 3.**

*Action potential of biological impulses.*

place. The LIF neuron is capable to process both firing and resetting operations, closely mimicking the biological behavior of neurons.

From Eq. (1), it can be observed that the integration time over the membrane capacitor can be regulated by excitation and leakage currents. Such relation can be depicted by a simple resistor model, which can be rewritten as

$$I\_{ex} = C\_m \cdot \frac{d\,V\_m}{dt} + \frac{V\_m}{R\_{lank}},\tag{2}$$

where \_\_\_ *Vm*\_ *Rleak* determines the amount of leakage current. Thereby, the voltage potential across the membrane capacitor can be determined as

$$\mathbf{V}\_m = I\_{\text{ex}} \cdot \mathbf{R}\_{leak} - \mathbf{e}^{\frac{\mathbf{I}}{R\_{\text{old}} \cdot \mathbf{C}\_m}}.\tag{3}$$
