Questions tagged [neural-network]

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.

Filter by
Sorted by
Tagged with
32
votes
2answers
2k views

Neural networks with biologically plausible accounts of neurogenesis

One of the reasons artificial neural net algorithms like cascade correlation (pdf) have been generating interest is because they start with a minimal topology (just input and output unit) and recruit ...
29
votes
2answers
747 views

How are newly created neurons recruited into existing networks?

As far as I understand, the basics of neurogenesis (abstracted down to the level that makes sense to a computer scientist) is as follows: Neural progenitor cells differentiate into new neurons that ...
28
votes
2answers
3k views

What is an effective metric of complexity for an Artificial Neural Network?

After asking the question What is the most complex neural network... I realized I don't really have a good metric of "complexity" in a general sense. The simplest measure would likely be count of ...
21
votes
7answers
12k views

Difference between parallel processing done by human brain and by computers

I am asking a question regarding parallel processing as done by billions of Neurons inside our brain and parallel processing done by our computers in a cluster for example or even on a Graphics ...
17
votes
3answers
3k views

Is back-prop biologically plausible?

One of the common criticisms of Deep Learning is it's training algorithms, back-propagation of error (back-prop), has no biologically plausible implementation, despite evidence of something like it ...
16
votes
3answers
811 views

What are the key examples of the use of computational methods in the study of biological neural networks?

In an upcoming postdoc, I'm going to be looking through biological neural network data in the hopes of finding some interesting "patterns". I'm coming at this field from a mathematics/computer ...
16
votes
1answer
2k views

Modern treatments of Alan Turing's B-type neural networks

In the cognitive sciences Alan Turing is best known for launching AI with his Computing machinery and intelligence (1950). However, this was not his first contribution to the cognitive sciences, in ...
15
votes
2answers
1k views

What can we learn from the neural networks of C.elegans to understand human brains?

Recently I am reading some works about Caenorhabditis Elegans. A C.elegans has 302 neurons and we already know the function and connection of every one of their neurons so that we can exactly ...
15
votes
2answers
400 views

References for biologically plausible models of knowledge representation?

I'm looking for references that deal with the issue of how various kinds of semantic knowledge are (or might be) represented neurally. Most of the discussion of this topic seems skewed by social ...
14
votes
1answer
465 views

How does neural spiking begin in the fetus?

I'm interested in modeling human brain spiking activity. How does the very first spiking activity begin in the fetus? I imagine all spiking activity is initiated by the senses and internal ...
14
votes
3answers
2k views

How distantly related are research in computational neuroscience and neural networks/machine learning?

If one is more interested in understanding how algorithms in the biological brain solve problems (theoretically, particularly the mathematical aspect), and possibly in building brain-inspired ...
13
votes
2answers
349 views

How is the biological accuracy of ANNs typically measured?

I am referring to the computational neuroscience side of neural network research that focuses on biological accuracy. I've read references to improving biological realism (using say spiking neurons ...
12
votes
3answers
270 views

Is there any recent work on modeling how we rapidly acquire new knowledge?

I work with neural network models of human cognition a lot, and one thing that bugs me about them is the timescale: they learn over thousands of trials whereas humans seem to learn after a couple ...
12
votes
1answer
3k views

What is the most complex artificial neural network created to date?

A few years ago I wrote a research paper for college on neural networks. At the time IBM's Blue Brain was the clear winner. Some rumor went around that they were close to emulating a brain the ...
12
votes
1answer
154 views

What is the role of traveling waves in circuit formation during cortical development?

Propagating waves of activity have been characterized in various regions of the brain such as the visual cortex (Nauhaus et al., 2012). Recently they have been reported for the first time to occur ...
11
votes
3answers
50k views

What is the difference between biological and artificial neural networks?

I read that neural networks are of two types: a) Biological neural networks b) Artificial neural networks (or ANN) I read, "Neural Networks are models of biological neural structures," and the ...
11
votes
1answer
365 views

Hebbian Learning Rule, Local or Global?

I just learned about the Hebbian Learning Rule. It essentially says "Neurons that fire together, wire together". I'm wondering if the learning rule is affected by the spatial distance of the two ...
11
votes
1answer
162 views

Is a network of neurons the only factor in memory?

Background I'm actually writing a science fiction novel set a couple decades in the future. Brains are not my field. I've done as much research as I could. In the story, the protagonist finds out he ...
11
votes
1answer
2k views

Spurious attractors in Hopfield networks

A classic "Hopfield network" is a type of artificial neural network in which the units are bi-stable and fully interconnected by symmetrically weighted connections. In 1982, Hopfield showed that such ...
11
votes
3answers
215 views

What kinds of information can (and cannot) be extracted from connectome?

Several scientific projects are trying to map the connectome, such as The Human Connectome Project. The connectomes of other organisms, such as C. elegans, have been mapped already. Having an ...
10
votes
1answer
87 views

Why do long range axons in mammals travel in white matter tracts?

I am curious to know as to why long range, myelinated axons prefer to convene and form white matter tracts, rather than simply reach its target in an arbitrary fashion. Is there some kind of ...
10
votes
1answer
148 views

Does an action potential abolish an excitatory postsynaptic potential?

From some sources, I've read that excitatory postsynaptic potentials (EPSPs) decay over time, which would imply that they aren't abolished by action potentials. However, other sources seem to indicate ...
10
votes
1answer
721 views

Is a Hopfield network with a continuous activation variable and a discrete time variable possible?

I've found plenty of resources on Hopfield networks that use either discrete variables for both activation level and time or continuous variables for both activation level and time. Is it possible to ...
10
votes
1answer
267 views

Are there any connectionist models that integrate reinforcement and fully supervised learning?

I've been working on modeling some phenomena involving real-time control in an environment with inherent rewards (specifically, playing a 'pong'-like game), and it's increasingly looking like ...
10
votes
1answer
126 views

Does a recent general review of recurrent neural networks exist?

Does anyone know of a comparatively recent paper reviewing the literature on psychological applications of recurrent neural networks? I'm looking for a paper which provides a general overview of the ...
9
votes
5answers
788 views

Why can't we use 100% of the brain in a certain moment?

I know it's a myth that we only use 10% of our brain, but the point is that we use less than 10% in any given moment; only by using different parts of our brain for various tasks over time do we ...
9
votes
1answer
201 views

How can STDP fit with reciprocal connectivity?

I have rather technical question regarding STDP dynamics. I am working on a neural network implementing an STDP learning algorithm, and have noticed that it is extremely anti-reciprocal. When two ...
8
votes
3answers
495 views

Is there a neural network model of Pavlovian Learning?

I am trying to find a computer simulation of Pavlovian learning. i.e. an action such as salivation in response to a stimulus such as a bell ringing. Most neural network models I've seen seem to be ...
8
votes
3answers
5k views

What do the weights of an artificial neural network represent in biological neurons?

In artificial neural networks the connections between neurons are a assigned numbers called "weights" or "parameters". As new data is fed into the neural net, these weights change. This is how the ...
8
votes
1answer
92 views

What exactly is an astroglial calcium wave?

There are quite a few conflicting reports as to what stimulates them, how they propagate, whether they communicate intercellularly, and what they look like. The only consistent information I can ...
8
votes
1answer
304 views

Spiking Neural Network Simulation: Measuring and Classifying Bump Attractor States

I am currently working with Spiking Neural Networks and multi-(meta)-stable attractor states. What I observe in my simulations are 'bump' attractors that appear, disappear, and may wander around. ...
7
votes
1answer
1k views

How does the brain break down visual information for processing? What “channels” is visual input broken into?

Some time ago I remember reading about how the human brain breaks down visual information into a number of individual "channels". For example, one channel might focus on edges and lines, another ...
7
votes
1answer
95 views

What's the functional difference between the NEF and normal ANNs?

Aside from obvious biological plausibility, from a computational standpoint, what's the motivation of using the Neural Engineering Framework (NEF) instead of Artificial Neural Networks (ANNs) for ...
7
votes
2answers
353 views

The computer model of the brain

I am a computer programmer or computer engineer, and am interested in comparing the brain to a classical computer in some way. How well does this comparison hold up? This is a general introduction ...
7
votes
2answers
218 views

How is the biological error signal in predictive coding computed?

I am quite inspired by the results obtained by PredNet, which implements a predictive coding model using artificial neural networks. They compute the prediction error as a simple subtraction, and then ...
7
votes
1answer
182 views

What functional purpose does a cortical column serve?

The Blue Brain project led by Henry Markram focused on simulating cortical columns under the idea they form basic processing units of the brain/cognitive function. What functional purpose does a ...
7
votes
1answer
122 views

Can processing effort for sub-tasks in neural networks be measured?

I often heard statements like: 80% of your brain processing is computing the effect of gravity or, similarily: You only use 20% of your brain power My question isn't about the truth of these ...
7
votes
1answer
125 views

Question concerning Jeff Hawkins' On Intelligence

In 2004 Jeff Hawkins' book On Intelligence was widely praised. But Hawkins made some claims about artificial neural networks that seem (to me) untenable today, only 13 years later. He gives the ...
6
votes
3answers
1k views

Are there neural loops within a column or an area of the cortex?

Neuronal networks can make loops because a neuron has a direction (from dendrite to axon). What's the smallest area in the cortex where we can find a loop and what are these loops? I understand ...
6
votes
1answer
2k views

Information storage capacity of a neural network?

I seem to remember reading about some equation that states the amount of information that can be held by a neural network with n neurons in it arranged in l layers, or something vaguely like that (n ...
6
votes
2answers
206 views

Utility or software to visualize Neural Network?

I am using Octave to generate a Neural Network with a single hidden layer, and saving it as two CSV files. Is there a utility or software that will load the files and create an image, PDF or HTML ...
6
votes
1answer
119 views

What is the purpose of dead end neurons in this diagram?

I was reading over some sources about ANNs, and here I found this diagram of a Recurrent Neural Network (RNN, the source calls it a feedback neural network). I noticed that a few neurons in this ...
6
votes
1answer
1k views

Computational differences between spiking neural networks and previous ANNs

This is an AI question regarding "3rd generation neural networks" - spiking neural networks (SNN). I hve been studying this concept online from various papers, mainly Maass (1997). I and am ...
6
votes
1answer
408 views

How does a human classify or cluster data?

Here, what I mean by DATA are text documents. I am going to do a research on text clustering algorithms by the help of artificial neural networks (ANNs). But first of all I need to know how our brain ...
6
votes
0answers
50 views

What kind of feed-back scheme is there for a back-propagation feed-forward ANN for self-learning of touching a coordinate with robot arm?

I'm a beginner in this topic and are learning how to build an artificial neural network and different types of training associated with them. Right now, I'm trying to figure out self learning. For ...
6
votes
1answer
147 views

Interpretation & Actual Result of “10% of your brain” Myth [duplicate]

It is well known that the common myth that an individual only ever uses 10% of their brain is.. well, a myth. I had a question about a possible interpretation of this idea, and a follow-up question ...
5
votes
2answers
780 views

Why is it so difficult to use a “true mirror” as a mirror

This Youtube video shows what a "true mirror" is: https://www.youtube.com/watch?v=ZSxCZCy5Wsk In short, when you look into a true mirror you look at yourself (among other things) as you really are, ...
5
votes
4answers
1k views

What role do circular network structures play in neural networks?

I'm developing small virtual neural networks and for the most part, the networks have remained feed-forward. When I create circular structures, it becomes a challenge to find a balance with the neural ...
5
votes
1answer
61 views

Why is the occipital lobe behind instead of in front?

These are regions of our brain: Our eyes are in front below our forehead, however, the visual area Occipital Lobe is behind. Are there any biological reasons for this? why shouldn't Occipital Lobe be ...
5
votes
1answer
99 views

How far can a signal travel in the neocortex without passing through the white matter?

Correct me if I am wrong please, from what I understand horizontal communication spans very short distance in all layers of the neocortex but layers I and II. In these two layers dendrites and axons ...