Stack Exchange Network

Stack Exchange network consists of 175 Q&A communities including Stack Overflow, the largest, most trusted online community for developers to learn, share their knowledge, and build their careers.

Visit Stack Exchange

Questions tagged [nef]

The Neural Engineering Framework is a framework mapping functions, dynamics and learning onto neurons, allowing for testing and creating of large-scale, biologically-plausible models.

2
votes
1answer
50 views

What tasks is Spaun 2.0 able to perform?

According to "A Large-Scale Model of the Functioning Brain" by Eliasmith et al., Spaun 1.0 was able to perform 8 distinct cognitive tasks: Copy Drawing: Given a randomly chosen handwritten digit, ...
1
vote
0answers
36 views

What's the relation between PES and LSA?

In "Learning by stimulation avoidance: A principle to control spiking neural networks dynamics" by Sinpayen et al. a learning rule called Learning by Stimulation Avoidance (LSA) is presented. ...
3
votes
1answer
112 views

Why is PES biologically plausible?

The NEF puts great emphasis on biological plausibility. However, I'm not clear on why the Prescribed Error Sensitivity (PES) learning rule, used in many NEF-based models, is considered to be ...
2
votes
1answer
42 views

What coding scheme does NEF use? Rate or phase?

There is a long-standing debate in theoretical neuroscience about what information of spikes is most important: rate or phase? What stance does the NEF take on this manner?
1
vote
0answers
66 views

How is “one-shot learning” implemented in the NEF/SPA?

In various cognitive modelling publications, "One-Shot Learning", which is just learning given very few examples, is praised as being an essential part of human cognition. For example, in "One-Shot ...
5
votes
1answer
797 views

Difference between content-addressable memory and associative memory?

Often when I'm reading theoretical neuroscience publications, such as "Towards an integration of deep learning and neuroscience", as well as "Memory and the Computational Brain", theorists often ...
1
vote
0answers
56 views

Advantages of Nengo for memory related tasks [closed]

What are some of the advantages Nengo offer as a framework for modeling memory related cognitive processes?
1
vote
0answers
33 views

Difference between GALIS and NEF/SPA?

The Gated Attractors Learning Instruction Sequences (GALIS) framework, used to solve a card-matching task, as well as the n-back task, appears to be trying to unite high-level symbolic reasoning to ...
3
votes
1answer
233 views

Limitations of Neural Engineering Framework (NEF)

All frameworks have limitations. Although I ask a lot of questions on this site in regards to the advantages of the Neural Engineering Framework (NEF), there must be significant limitations. What are ...
7
votes
1answer
287 views

Is semantic pointer architecture compatible with a predictive coding account of the brain?

Both SPA (Eliasmith et al.) and predictive coding (Friston, Clark, Rao, et al.) seem to have a lot of explanatory power. My understanding of SPA is probably rudimentary, but Eliasmith and others ...
3
votes
0answers
23 views

Relation between NEF and synchronous explanation of cognition

I'm having a hard time determining if synchrony (I'm talking about the type described in reference to the visual cortex as seen here and less about synaptic plasticity which also involves synchrony) ...
1
vote
0answers
55 views

How are Bayesian models implemented in the NEF?

One of the much documented problems of Bayesian approaches to cognitive modeling is that there isn't much of a neural grounding. The NEF can be used to compute probabilistic computations with ease (...
4
votes
1answer
34 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 ...
4
votes
1answer
101 views

Can fMRI and EEG signals be generated from NEF models?

The basic function of the NEF is to map the outside world onto neurons, using the firing rates of the neurons. It also supports various neuron models. Have these firing rates been used to create EEG ...
2
votes
1answer
84 views

Benefits of using more complicated neuron models in NEF models

The NEF allows you to use almost any neuron model as long as it has an equation for it's activity and it's spikes in some way. Usually, a simple leaky-integrate-fire (LIF) neuron model is used, but ...
3
votes
1answer
49 views

What's the function of the clean-up memory in SPA?

When I read about cognitive models that use the Semantic Pointer Architecture (SPA), such as a model for general intelligence, I often see a component called the "clean-up memory"? What's the function ...
2
votes
1answer
116 views

How is memory accounted for in the NEF?

The Neurological Engineering Framework can be used to create systems that use memory in interesting ways. One system (Spaun) is able to memorize (and forget) lists much in the same way as humans do. ...
3
votes
1answer
39 views

How well are neurotransmitters used in SPA?

How much does the SPAUN and the Semantic Pointer Architecture (SPA) that was used to build it take neurotransmitters into account? In the book How to Build a Brain, various inhibitory and excitatory ...
3
votes
1answer
28 views

How well does the NEF capture neuronal heterogeneity?

From what I understand of the Neurogical Engineering Framework (NEF), groups of neurons are used to compute functions. However, I'm not clear if these calculations take into account neurons of ...
7
votes
1answer
89 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 ...
5
votes
1answer
69 views

How does hPES compare to the learning rates of ANNs?

The primary learning mechanism of artificial neural networks (ANN) is back-propagation, which is not biologically plausible [2]. Trevor Berkolay created an alternative to this learning with the ...
9
votes
4answers
3k views

How to read a neuron tuning curve graph?

I'm working through the tutorial of section 2.4 of "How to Build a Brain" and I've encountered this graph of a neuron tuning curve. I understand the Y axis is the firing rate of the neuron, that each ...
3
votes
1answer
202 views

Relation between Nengo, SPA and NEF with respect to other Neural Models

I'm working through How to Build a Brain and I keep getting confused on the relation between Nengo, the Semantic Pointer Architecture (SPA) and the Neurological Engineering Framework (NEF). Are there ...