406
P. A. Dananjaya et al.
allows us to achieve better accuracy with high energy efficiency. If we say, SNN
corresponds to low energy networks and DNN corresponds to network with better
accuracy then, spiking deep neural network (SDNN) will be Better Accuracy Low
Energy (BALE) neural network. While it is difficult to achieve in a mapped SDNN
the same level of accuracy as the DNN, research is ongoing to develop better mapping
techniques.
SDNN background
DNN to SNN conversion techniques were developed in the ongoing research to map
a trained neural network in conventional frame-based vision system representation
to an event-based one [89]. Neurons in the frame-based CNN were converted to
event-based neurons with leak, membrane potential reset and refractory periods.
One of the first research paper on CNN to SNN conversion is [66]. The conventional CNN is first converted into a tailored CNN which fulfils the requirements of
the SNN. This tailored CNN is then trained. Finally, this tailored CNN is converted
into a spiking CNN, while retaining the trained weights. The requirements imposed
by the SNN on the tailored CNN are as follows:
1. Using RELU [29] as activation functions
2. Removing biases from convolution and fully connected layers
3. Using spatial linear subsampling in place of maxpooling.
The work in [66] was extended in [88] by adding weight normalization techniques
to improve the conversion accuracy. The approximation errors in SNNs due to either
excessive or too little spikes are avoided by rescaling of weights. Model and databased weight normalization techniques were proposed; data-based normalization
gives no loss in conversion accuracy for classification of MNIST dataset.
The integrate and fire (IF) neuron model was extensively used in SDNN until
[30] demonstrated that a CNN can also be mapped onto a SDNN made up of leaky
integrate and fire (LIF) neurons which are more biological plausible. This is achieved
by using a modified LIF neuron known as the softened LIF neuron and by training
the network with noise so as to improve network robustness against the variability
inherent in spikes.
The hardware constrained neuromorphic algorithm is implemented in [76] on
the IBM Truenorth neuromorphic chip. The hardware constraints are namely, low
precision weights and restricted connectivity among spiking neurons.
Adapting SNN is introduced in [90], which is based on adaptive spiking neurons.
Asynchronous pulsed sigma-delta coding scheme is used by these spiking neurons
to efficiently encode information in spike trains, while homeostatically optimizing
the firing rate. This method uses an order of magnitude less spikes compared to
other SDNN approaches; the RELU neurons in an ANN could be directly mapped
to adaptive spiking neurons during conversion.
General steps for conversion
The conversion of a pre-trained DNN to the event-based domain is for inference
purposes. The principle of the conversion technique as mentioned in [66] is that the
P. A. Dananjaya et al.
allows us to achieve better accuracy with high energy efficiency. If we say, SNN
corresponds to low energy networks and DNN corresponds to network with better
accuracy then, spiking deep neural network (SDNN) will be Better Accuracy Low
Energy (BALE) neural network. While it is difficult to achieve in a mapped SDNN
the same level of accuracy as the DNN, research is ongoing to develop better mapping
techniques.
SDNN background
DNN to SNN conversion techniques were developed in the ongoing research to map
a trained neural network in conventional frame-based vision system representation
to an event-based one [89]. Neurons in the frame-based CNN were converted to
event-based neurons with leak, membrane potential reset and refractory periods.
One of the first research paper on CNN to SNN conversion is [66]. The conventional CNN is first converted into a tailored CNN which fulfils the requirements of
the SNN. This tailored CNN is then trained. Finally, this tailored CNN is converted
into a spiking CNN, while retaining the trained weights. The requirements imposed
by the SNN on the tailored CNN are as follows:
1. Using RELU [29] as activation functions
2. Removing biases from convolution and fully connected layers
3. Using spatial linear subsampling in place of maxpooling.
The work in [66] was extended in [88] by adding weight normalization techniques
to improve the conversion accuracy. The approximation errors in SNNs due to either
excessive or too little spikes are avoided by rescaling of weights. Model and databased weight normalization techniques were proposed; data-based normalization
gives no loss in conversion accuracy for classification of MNIST dataset.
The integrate and fire (IF) neuron model was extensively used in SDNN until
[30] demonstrated that a CNN can also be mapped onto a SDNN made up of leaky
integrate and fire (LIF) neurons which are more biological plausible. This is achieved
by using a modified LIF neuron known as the softened LIF neuron and by training
the network with noise so as to improve network robustness against the variability
inherent in spikes.
The hardware constrained neuromorphic algorithm is implemented in [76] on
the IBM Truenorth neuromorphic chip. The hardware constraints are namely, low
precision weights and restricted connectivity among spiking neurons.
Adapting SNN is introduced in [90], which is based on adaptive spiking neurons.
Asynchronous pulsed sigma-delta coding scheme is used by these spiking neurons
to efficiently encode information in spike trains, while homeostatically optimizing
the firing rate. This method uses an order of magnitude less spikes compared to
other SDNN approaches; the RELU neurons in an ANN could be directly mapped
to adaptive spiking neurons during conversion.
General steps for conversion
The conversion of a pre-trained DNN to the event-based domain is for inference
purposes. The principle of the conversion technique as mentioned in [66] is that the