Questions tagged [spiking-neural-networks]

For questions related to spiking neural networks (SNNs) that more accurately model biological neurons in the brain than perceptrons or RNN cells by simulating pulses within and across neurons rather than simulating signal values that remain constant for each learning iteration (by example index or batch index for mini-batch).

Filter by
Sorted by
Tagged with
1
vote
0answers
22 views

How does Lateral Inhibition Provide Competition among Neurons?

I stumbled upon a paper from P.Diehl and M.Cook with the title "Unsupervised learning of digit recognition using spike-timing-dependent plasticity" and I'm trying to understand the logic ...
4
votes
1answer
113 views

What are examples of machine learning techniques inspired by neuroscience?

What are examples of machine learning techniques (i.e. models, algorithms, etc.) inspired (to different extents) by neuroscience? Particularly, I'm interested in recent developments, say less than 10 ...
4
votes
0answers
45 views

Is it a good idea to first train a spiking neural network and then convert it to a conventional neural network?

In many papers about artificial spiking neural networks (SNNs), the performance of them is not up to par with traditional ANNs. I have read how some people have converted ANNs to SNNs using various ...
2
votes
0answers
51 views

Can traditional neural networks be combined with spiking neural networks?

Can traditional neural networks be combined with spiking neural networks? And can there be training algorithms for such hybrid network? Does such hybrid network model biological brains? As I ...
1
vote
1answer
81 views

How does one characterize a neural network with threshold-based activation functions?

In an attempt at designing a neural network more closely modeled by the human brain, I wrote code before doing the reading. The neuron I have modeled operates on the following method. Parameters: ...
21
votes
7answers
2k views

If digital values are mere estimates, why not return to analog for AI?

The impetus behind the twentieth century transition from analog to digital circuitry was driven by the desire for greater accuracy and lower noise. Now we are developing software where results are ...