For questions about the function and structure of both biological and artificial neural networks (ANNs), and for the applications of ANNs to modeling in cognitive science.

learn more… | top users | synonyms

3
votes
0answers
30 views

Why do we train the threshold as a weight in neural networks?

Why do we train the threshold as a weight? I understand the process of how to do it (the bias and augmented weight vector) but do not get the importance or practical applications of doing so.
3
votes
0answers
19 views

What is the equivalent of a Hamming network in the NEF?

After doing a bit of research, I'm somewhat convinced that Hamming networks are networks that classify, but only put out a single result, as opposed to other networks which output multiple results. In ...
3
votes
0answers
24 views

A simple derivation of the generalization bounds for the classical perceptron model

I'm basically referring to the great work of Elizabeth Gardner in this matter. I find that her work is often overlooked in the field of neuroscience, arguably because it is too difficult to understand ...
3
votes
0answers
163 views

Does this neural network model exist? [closed]

I'm looking for a neural network model with specific characteristics. This model may not exist... I need a network which doesn't use "layers" as traditional artificial neural networks do. Instead, I ...
2
votes
4answers
72 views

How to begin neural network Programming [closed]

I am a Computer Science Student and recently studied neural networks, but theory only. How can this be implemented in real time programming language. What should I search for or what content should I ...
2
votes
2answers
88 views

How many action potentials from presynaptic neurons would be required to make a postsynaptic neuron fire?

I am looking for a rough estimation of the number of action potentials from other neurons required to cause a neuron to fire? I read here that a potential of ~ -55mv must be reached before an action ...
2
votes
1answer
73 views

Is the energy of an action potential divided among multiple axon terminals?

My understanding is that the bulk of an axon is myelinated, greatly adding to the efficiency of transmitting action potentials. However, the axon terminals are not myelinated. I'm wondering if the ...
2
votes
1answer
31 views

During synchronized waves oscillation (alpha beta etc…) do neurons fire only once for each wave cycle?

Or can they fire few times then pause and again, firefew times and pause periodically? If the second case happens then do we know if the neurons that fire in synchronity fire the same number of ...
2
votes
1answer
35 views

How can neuronal networks with local learning rules predict their future inputs?

Local learning rules like Contrastive Hebbian Learning, XCAL, etc. are based on the idea of strengthening edges when the neurons they connect fire simultaneously. This causes frequent patterns in the ...
2
votes
0answers
36 views

Are there any precise design principles for artificial connectomes or neural networks?

I've been reading about the openworm.org project. I've downloaded the code and run some simulations. The people at OpenWorm have made an experiment where they setup a robot with the neural network of ...
2
votes
0answers
90 views

Differences between the many versions of neuromorphic hardware [closed]

There is a ton of neuromorhpic hardware being pumped out these days. Off the top of my head, I can name IBM (BlueGene and TrueNorth), Qualcomm, Neurogrid, Brainstorm (Neurogrid 2.0), Spinnaker, ...
1
vote
2answers
53 views

How useful are neural circuits in psychology?

We can identify many kinds of patterns of how neurons connect such as lateral inhibition, negative/positive feedback, convergence, divergence, and facilitation. But have any of these circuits been ...
1
vote
2answers
77 views

Reference request in Circuit and Signals for Computational Neuroscience

In the area of computational neuroscience, there are basic theories from electric circuits and signal processing to be applied. For background study, which reference will be more suitable ? ...
1
vote
2answers
38 views

Understanding neuronal firing in the context of Spike Timing Dependent Plasticity

When discussing Spike Timing Dependent Plasticity in neurons, when we say that a neuron fires do we mean it fires only one spike? Or do we still say "the neuron has fired" when a train of n spikes was ...
1
vote
1answer
84 views

How many possible states does a brain have?

Suppose I have a box, inside of which is a light which can be either on or off: it has exactly two states. Suppose I wanted to take some "snapshot" of the state of this device, and store all the ...
1
vote
1answer
43 views

Why do I get smaller accuracy when I use 80% of training sets using HMAX model?

I am trying to compute the accuracy of the HMAX model. I am using the Face category (containing 435 images) from the Caltech101 database. I split it into $x$ ...
1
vote
1answer
147 views

Is it truly necessary to upgrade Tononi's criteria of consciousness in the Integrated Information theory?

I am referring specifically to a very recent paper by Max Tegmark. In this paper he proposes 3 more criteria (independence, dynamics, and utility principle) in addition to Tononi's original criteria ...
1
vote
0answers
22 views

When we say signals go from one cortical area to an other one do we mean they go directly without going through the thalamus for example?

Or is it implied signals always have to go back and forth between the thalamus and the cortex? Or is it possible they do both at the same time? Or maybe for areas next to each others they can go ...
1
vote
0answers
6 views

How can higher concepts get unrolled with upward and feedback connections differing?

In the neocortex, input patterns are compressed hierarchically. Sensory inputs in the lower levels are combined by higher levels to form abstract concepts. However, there are even more feedback ...
0
votes
2answers
186 views

As for future mind control/reading technology, can humans fight it?

As of recent times, rats have communicated through wireless brain implants, from across the globe. Also, recent fMRI technologies have allowed prediction of movements (or intention), and the ...
0
votes
1answer
38 views

What is an example of a learning machine that achieves zero variance?

I'm attempting to find an example of a learning machine/neural network that achieves zero variance, but I am having a hard time finding an example anywhere. Variance is defined as the generalization ...
0
votes
1answer
40 views

Does human to human interface carry the same information from the brain [closed]

I'd like to know if the human to human interface carry the same information from the brain or it is just a signal that switch on or off electrical impulses that causes the limb to contract? Is it ...