4 added 163 characters in body
source | link

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 Neurological Engineering Framework (NEF) and Nengo called hPES (Homeostatic Prescribed Error Sensitivity) [1]. But how does it's learning capabilities compare to the standard supervised and unsupervised learning of ANNs in terms of computational power required and speed of learning?

[1] See also, "How to Build a Brain" by Chris Eliasmith chapter 6.4

[2] Further details around this claim can be found in the question "Is back-prop biologically plausible?"

Note: I realised that thisThis question portrayed ANNs and the NEF as adversarial, which really isn't the case. Spaun the brain model, which is kind of the poster child of the NEF, uses ANNs (Deep BeliefConvolutional Neural Networks specifically) converted into spiking neurons in it's vision system.

The primary learning mechanism of artificial neural networks (ANN) is back-propagation, which is not biologically plausible.

Trevor Berkolay created an alternative to this learning with the Neurological Engineering Framework (NEF) and Nengo called hPES (Homeostatic Prescribed Error Sensitivity) [1]. But how does it's learning capabilities compare to the standard supervised and unsupervised learning of ANNs in terms of computational power required and speed of learning?

[1] See also, "How to Build a Brain" by Chris Eliasmith chapter 6.4

Note: I realised that this question portrayed ANNs and the NEF as adversarial, which really isn't the case. Spaun the brain model, which is kind of the poster child of the NEF, uses ANNs (Deep Belief Networks specifically) converted into spiking neurons in it's vision system.

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 Neurological Engineering Framework (NEF) and Nengo called hPES (Homeostatic Prescribed Error Sensitivity) [1]. But how does it's learning capabilities compare to the standard supervised and unsupervised learning of ANNs in terms of computational power required and speed of learning?

[1] See also, "How to Build a Brain" by Chris Eliasmith chapter 6.4

[2] Further details around this claim can be found in the question "Is back-prop biologically plausible?"

Note: This question portrayed ANNs and the NEF as adversarial, which really isn't the case. Spaun the brain model, which is kind of the poster child of the NEF, uses ANNs (Convolutional Neural Networks specifically) converted into spiking neurons in it's vision system.

3 added 282 characters in body
source | link

The primary learning mechanism of artificial neural networks (ANN) is back-propagation, which is not biologically plausible.

Trevor Berkolay created an alternative to this learning with the Neurological Engineering Framework (NEF) and Nengo called hPES (Homeostatic Prescribed Error Sensitivity) 1[1]. But how does it's learning capabilities compare to the standard supervised and unsupervised learning of ANNs in terms of computational power required and speed of learning?

1 [1] See also, "How to Build a Brain" by Chris Eliasmith chapter 6.4

Note: I realised that this question portrayed ANNs and the NEF as adversarial, which really isn't the case. Spaun the brain model, which is kind of the poster child of the NEF, uses ANNs (Deep Belief Networks specifically) converted into spiking neurons in it's vision system.

The primary learning mechanism of artificial neural networks (ANN) is back-propagation, which is not biologically plausible.

Trevor Berkolay created an alternative to this learning with the Neurological Engineering Framework (NEF) and Nengo called hPES (Homeostatic Prescribed Error Sensitivity) 1. But how does it's learning capabilities compare to the standard supervised and unsupervised learning of ANNs in terms of computational power required and speed of learning?

1 See also, "How to Build a Brain" by Chris Eliasmith chapter 6.4

The primary learning mechanism of artificial neural networks (ANN) is back-propagation, which is not biologically plausible.

Trevor Berkolay created an alternative to this learning with the Neurological Engineering Framework (NEF) and Nengo called hPES (Homeostatic Prescribed Error Sensitivity) [1]. But how does it's learning capabilities compare to the standard supervised and unsupervised learning of ANNs in terms of computational power required and speed of learning?

[1] See also, "How to Build a Brain" by Chris Eliasmith chapter 6.4

Note: I realised that this question portrayed ANNs and the NEF as adversarial, which really isn't the case. Spaun the brain model, which is kind of the poster child of the NEF, uses ANNs (Deep Belief Networks specifically) converted into spiking neurons in it's vision system.

2 edited tags
| link
    Tweeted twitter.com/#!/StackCogSci/status/487244004485234689
1
source | link