Neural Networks: Spiking Neural Networks

8 important questions on Neural Networks: Spiking Neural Networks

What are the 3 generations of neural networks that Maass (1997) identifies?


  1. Networks based on McCulloch-Pitts neurons.
  2. Networks based on neurons with continuous activation function.
  3. Networks based on spiking neurons.

What is the biological inspiration for spiking neural networks?

  • neurons have a firing rate.
  • Activation level of second generation represents firing rate.
  • It can however not explain fast cortical computations.
  • More evidence has been found that the timing of action potentials is used to encode information.

How does the spiking neural network work?

Each pre-synaptic spike generates an EPSP or IPSP in case of negative weight. All small spikes are added and if this reaches the threshold the post-synaptic neuron emits a spike in its turn.
  • Higher grades + faster learning
  • Never study anything twice
  • 100% sure, 100% understanding
Discover Study Smart

What are the basics of a general spiking neural network?

Assume a neuron v.
v fires once its potential P is above threshold Theta.
P is the sum of excitatory and inhibitory postsynaptic potentials (EPSP/ISPS) from connected neurons u.
How much u which fired at time s contributes at time t depends on:
  • w ≥ 0, the weight between u and v.
  • epsilon(t-s), the response function.

Why two response functions and not just negative weights?

There is a positive function (EPSP), where epsilon is above zero and a negative function (IPSP), where epsilon is under zero.
This is caused by the biological plausibility. neurons do not change from inhibitory to excitatory and vice versa.

Does the Threshold Θ stay constant?

No, because:
  • Neurons do not fire for a few msec after they have fired at t' (absolute refractory period).
  • After this period, neurons are more reluctant to fire (i.e. require a higher P).
  • Select an appropriate threshold function.

What is the full formalisation of the spiking neural?

  • Let V be a finite set of spiking neurons
  • Let E ⊆ V x V be the set of synapses, where each synapse <u,v> ∈ E has a

                   Weight w ≥ 0
                   Response function ε: R+ → R
  • For every v ∈ V
                   Threshold function Θ: R+ → R+
  • Let F ⊆ R+ be the set of firing times of neuron u

What are some properties of spiking neural networks?

  • Spiking NNs can simulate arbitrary feed forward sigmoidal neural networks.
  • Hence, can approximate any continuous function.
  • Spiking neurons are computationally more powerful than neurons with sigmoidal activation functions.
  • Biologically more plausible.
  • Can act as reservoir in the reservoir computing approaches.

The question on the page originate from the summary of the following study material:

  • A unique study and practice tool
  • Never study anything twice again
  • Get the grades you hope for
  • 100% sure, 100% understanding
Remember faster, study better. Scientifically proven.
Trustpilot Logo