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
2
votes
0answers
17 views

From the following paragraph, why would the input or the initial condition not matter in the output?

On pg.37 of “Principles of Neural Science,” they state that “...in systems with feedback circuits it is the dynamic activity of the system that determines the outcome of computation, not inputs or ...
2
votes
0answers
31 views

Biological Neural Network Modification to Unlearn Understandings

Lets assume that a person grows up thinking that religion X is true religion. So he builds up a profile in ones head and when notion of religion X appears the neurons that is related are fired, giving ...
2
votes
0answers
28 views

Single neuron dominates for all input patterns using STDP in simple LIF SNN

I have been reading latley on SNN and decided to try and implement myself some simple simulation. So I wrote a simple MATLAB simulation using simple LIF current based model and I try using STDP to ...
0
votes
0answers
22 views

What lies at the core of human brain's processing, is it a simple retrieval from memory or actual computation?

For example, let's say I am solving a tough Calculus problem, as is my friend. I have practised calculus problems for several months now. While my friend is new to it. So, I solve it easily while my ...
0
votes
0answers
11 views

Connectome Datasets Related to Consciousness

I am a mathematics student currently looking for connectome datasets specifically related to consciousness research. I have mainly looked at the following sites: https://neurodata.io/ https://db....
1
vote
1answer
82 views

Is using tensorflow for Spiking neural networks a “good” idea?

I recently started working with Spiking Neural Networks and was hoping for some input from others. I saw there were many libraries/platforms specifically made for working with SNN's (Brian, PyNN, ...
0
votes
0answers
6 views

Graph Dynamical Systems for simulating Spiking Neural Networks

Computational approaches to understanding the connectivity of biological neural networks using graph theory and dynamical systems have been recently gaining traction. I am wondering if there are any ...
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, ...
7
votes
2answers
354 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 ...
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 ...
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 ...
1
vote
0answers
26 views

Testing Multilayer Perceptron [closed]

The following script is from Trappenberg's Fundamentals of Computational Neuroscience and is used to test a perceptron's robustness against noise. However, how would one alter it to test the output ...
2
votes
1answer
92 views

Is there a biological equivalent to the bias term used in artificial neural networks?

For the longest time, I had been thinking that the bias term used in the standard artificial neural network model (the ubiquitous one used in most machine learning implementations) can be interpreted ...
0
votes
0answers
25 views

Resources for learning Advanced Neuroscience

I am very interested in learning at an high level: How neurons send signals to each other Activation sites of neurons The exact process of signal transmission Dopamine and other neurotransmitters ...
4
votes
1answer
194 views

Delay time of Transmitting the information from one neuron to another in brain

Inside the brain the electrical signals are transmitted from one neuron to another by using special chemicals, called "neuro-transmitters" from the axon terminals. Could anyone can tell me how to ...
0
votes
0answers
17 views

reservoir computing and transient states

I'm exploring reservoir computing more precisely, Echo states network. I can't find good explication for number of drop of transient states. How to tune this variable and what is the impact of this ...
1
vote
0answers
17 views

How many axons and dendrites are entering and exiting human male internal urethral sphincter?

As I know, this information is not available yet. If indeed it is not available, this question may wait for future answers. I have known out that some parts of human connectome are already mapped, so ...
1
vote
0answers
42 views

Decussation of Cranial Nerves

Which cranial nerves decussate apart from the few nerve fibers of the optic nerve that do and how to easilly remember the cranial nerves that do? Here is a paper for the Trochlear Nerve But I have ...
0
votes
1answer
66 views

Are neurons the wrong shape to model neural networks?

Looking at neural networks, each node can be described as a neuron with either several long input wires, or several long output wires. A neuron, however, has many short input wires (dendrites) and a ...
2
votes
2answers
278 views

ML/Neuroscience: TensorFlow vs PyTorch vs Keras for bulding NN models of the nervous system?

I would be very grateful to people with experience in using neural network models in neuroscience for advice! What approach would you recommend for building neural networks? I am choosing between ...
3
votes
1answer
74 views

Myelin and Myelin Sheath

https://medlineplus.gov/ency/article/002261.htm Why is Myelin used as a term to mean the Myelin Sheath as opposed to the proper term? It is apparent to me that Myelin is the substance itself ...
5
votes
1answer
86 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 ...
4
votes
0answers
65 views

What is the state of the art on the wiring optimisation problem?

One of the earliest neuroscientists, Santiago Ramón y Cajal, postulated that brains are arranged to minimise wire length [1]. In [1] Dmitri Chklovskii and Charles Stevens formulate this problem as ...
3
votes
2answers
67 views

Simulating Hudgkin Huxley neural network

I'm starting work on a computational neuroscience project where I want to create my own model of a spiking Hodgkin-Huxley neuron and connect many instances (about 400) of this model through synapses. ...
1
vote
0answers
31 views

Hypotheses about neural coding and neural correlates of concepts and reasoning - at the level of neurons and synapses

Are there some hypotheses about neural coding of language, concepts and logical reasoning in the brain, about neural correlates of thoughts? When I search the books, then I find lot of books about ...
1
vote
1answer
74 views

Is the visual cortex of a newborn baby immediately capable of object detection or is this skill learned over time, and if so, how?

Is the visual cortex of newborn babies right off the bat capable of making sense of raw visual data, for instance, converting the constant stream of raw RGB images perceived by the eyes into a ...
-1
votes
1answer
110 views

Why can't human thoughts be stored in metals?

As metals are good conductors of electricity and they can be charged by the electrical activity of thoughts, why can't human thoughts be stored in metals? Why thoughts cannot be stored in the form of ...
1
vote
0answers
32 views

Do people still use ACT-R?

A lot of computational cognitive scientists seem to be working on Neural nets (mostly vision scientists), Reinforcement learning (mostly decision making people) and Bayesian Inferences. I could hardly ...
4
votes
2answers
322 views

Hebbian Learning - Understanding Simultaneous Firing

I'm beginning to write a neural network simulator in Java and thinking of Hebbian Learning but I'm stuck at one thing: What causes two neurons to fire at the same interval while only one of them is ...
9
votes
5answers
789 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 ...
2
votes
1answer
54 views

Are there animals with only excitatory neurons?

Are there animals with only excitatory neurons? I am not sure it is possible. Also, maybe excitation/inhibition can become relative? I however will be happy to read your opinion.. For example, are ...
3
votes
1answer
242 views

What is the difference between principal neurons and pyramidal cells?

I am reading Kandel's "Principals of Neural Sciences". There the book sometimes refers to excitatory neurons as principal cells, and sometimes as pyramidal cells. Can anyone tell me the difference? ...
13
votes
2answers
350 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 ...
1
vote
0answers
16 views

Training adjustments of synaptic Weights [closed]

I'm a graduate student in the Electrical Engineering Program currently working on my thesis and I have to figure out how to train synaptic weights in an Artificial Neural Network either analogously or ...
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
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
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 ...
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 ...
3
votes
0answers
47 views

Convolutional Operations in the Visual Cortex

One of the fundamental operations in image neural networks is the operation of convolution, where a filter slides across the receptive field, activating on particular features. This is incredibly ...
3
votes
1answer
263 views

Why is Biological plausibility in Machine Learning important?

I have found that many authors of machine learning papers, that employ the Hebbian learning rule, refer to the biological plausibility of it, as one of the arguments to use it instead of the well ...
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 ...
3
votes
0answers
50 views

Task-based vs task-positive networks

Do the terms "task-positive network" and "task-based network" refer to the same thing, such as the Fronto-Parietal Control Network (FPCN), as distinct from the task-negative networks such as the ...
2
votes
2answers
73 views

Does the brain's architecture change while growing up?

If we are somehow able to record and store all the neural connection in the brain of a child and also the brain of the same individual when he is old will there be difference between the two ? Is the ...
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 ...
4
votes
1answer
159 views

Is neurogenesis driven by prediction error?

Various Deep Learning algorithms [1] and neural models [2] make use of neurogenesis to reduce prediction errors. How much evidence is there that neurogenesis is driven by prediction error or novel ...
3
votes
0answers
60 views

How to derive the generalization bounds for the classical perceptron model? [closed]

I thank all the commenters for the valuable feedback. I'm trying to improve this question (which I had long ago -- omg I'm getting old). Is there a way to simply derive the generalization bounds for ...
2
votes
0answers
31 views

Serializing and deserializing stable states of Hopfield networks

I am looking for simple artificial neural networks that may perform the following serializing task. Consider two identical Hopfield networks, one being at rest, the other being in a stable state of ...
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 ...
1
vote
0answers
52 views

How will brain-computer interfacing work? [duplicate]

I have just been reading about Elon Musks new company Neuralink. He claims that it is possible to increase the communication speed between humans and computers by using direct brain interfaces which ...
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 ...