Just to orient my exposition, which one do you prefer: the long or the short explanation?
The longer one:
“Artificial Neural Networks (ANN) are models of computation that simulate the way the neural tissue in animals computes.
Neural tissue is made up by a large number of interconnected neurons: each neuron is a cell which has numerous locations, called synapses, that receive the electrochemical signals of hundred or thousands of other neurons. When the combined potential of all those rises above a certain threshold, a chemical transmissions is initiated, propagating a signal through a long thin projection of the body of the cell, called axon, which in turn is connected to the body of other neurons. In this way, neurons make up complex biological circuitry, where chemical potentials travel back and forth: the paths that gets used the most strengthen, those that are less useful weakens over time.
Artificial neurons are abstractions that treats signals in a similar way: they are nonlinear functions that receives many weighted inputs, and when those adds to a value above the threshold, they output a value. Usually the hyperbolic tangent is taken to be the activation function.
[pic]
Artificial neurons are connected in layers, each neurons receiving the inputs of every neurons in the layer before, outputting its value to every neurons in the layer after.
This architecture is called fully connected, was the first to be considered and to be implemented.”
The short one:
“Artificial Neural Networks aim at imitating the way neural tissue computes.
Neural tissue is made up by cells called neurons. They have a body littered with receptors where other neurons can connect (synapses), and have a long prolongation called axion, that can connect to other neurons. When combined the electrochemical potential in the synapses rises above a certain threshold, the axion transmit an impulse to the neurons it’s connected.
Neurons are connected in complex ways, creating a biological circuit where signals can be strengthened or weakened based on their use.
Artificial neurons imitate this behaviour using a threshold function, usually a sigmoid function such as the hyperbolic tangent. Each neuron weights each of its input, add them together and pass the value to the threshold function, which will propagate the signal if the combined input is sufficient.
Artificial Neural Network usually are made up of neurons lined in layers, each neuron in a layer receiving the input of every neuron in the layer before and passing its output to each neuron in the layer after. This model is called fully connected and, while powerful, quickly becomes unmanageable for ANNs that have thousands of neurons per layer or have many layers to process the input (deep neural networks).”
Second—“The paths that gets used the most strengthen, those that are less useful weakens over time” seems good to include, but you don’t make any mention of how that translates into ANNs. Maybe that comes later? Apart from that, I prefer the short version.
Third—Both discussions of threshold functions are kind of awkward. Long version—the first part makes it sound like the activation function is Heaviside: either 0 or 1. You attempt to correct that impression, but you don’t say what an activation function is, so it doesn’t work. Short version—depending on your audience, “sigmoid” and “hyperbolic tangent” need to be defined; and the second part again seems to suggest Heaviside contraray to the first part.
I think I’d recommend you just leave the Heaviside impression in place (maybe correct it in a footnote). “Artificial neurons imitate this behaviour using a threshold function. Each neuron weights each of its inputs, adds them together, and propagates the signal if the combined input is above some level.”
I am pro-[pic], depending on the pic.
Fourth—you can’t leave the “short” version there; you’re opening a plot thread and then not closing it. If you’re going somewhere with it (discussing/mentioning different ANN models, or how this model can be made manageable, or something), then great, but you might want to not start it until the point where you take it somewhere. If not, you should probably just cut it.
“The first to be considered and implemented” has similar problems, but less strongly.
Thanks for the lenghty analysis, yes I’m aware that these are the first drafts of a first draft, and I don’t even know if they will retain this form, but your comments made me realize that a shorter, faster pace is the way to go. Thank you very much!
Just to orient my exposition, which one do you prefer: the long or the short explanation?
The longer one:
“Artificial Neural Networks (ANN) are models of computation that simulate the way the neural tissue in animals computes.
Neural tissue is made up by a large number of interconnected neurons: each neuron is a cell which has numerous locations, called synapses, that receive the electrochemical signals of hundred or thousands of other neurons. When the combined potential of all those rises above a certain threshold, a chemical transmissions is initiated, propagating a signal through a long thin projection of the body of the cell, called axon, which in turn is connected to the body of other neurons. In this way, neurons make up complex biological circuitry, where chemical potentials travel back and forth: the paths that gets used the most strengthen, those that are less useful weakens over time.
Artificial neurons are abstractions that treats signals in a similar way: they are nonlinear functions that receives many weighted inputs, and when those adds to a value above the threshold, they output a value. Usually the hyperbolic tangent is taken to be the activation function.
[pic]
Artificial neurons are connected in layers, each neurons receiving the inputs of every neurons in the layer before, outputting its value to every neurons in the layer after. This architecture is called fully connected, was the first to be considered and to be implemented.”
The short one:
“Artificial Neural Networks aim at imitating the way neural tissue computes.
Neural tissue is made up by cells called neurons. They have a body littered with receptors where other neurons can connect (synapses), and have a long prolongation called axion, that can connect to other neurons. When combined the electrochemical potential in the synapses rises above a certain threshold, the axion transmit an impulse to the neurons it’s connected. Neurons are connected in complex ways, creating a biological circuit where signals can be strengthened or weakened based on their use.
Artificial neurons imitate this behaviour using a threshold function, usually a sigmoid function such as the hyperbolic tangent. Each neuron weights each of its input, add them together and pass the value to the threshold function, which will propagate the signal if the combined input is sufficient.
Artificial Neural Network usually are made up of neurons lined in layers, each neuron in a layer receiving the input of every neuron in the layer before and passing its output to each neuron in the layer after. This model is called fully connected and, while powerful, quickly becomes unmanageable for ANNs that have thousands of neurons per layer or have many layers to process the input (deep neural networks).”
Both versions need proofreading. That aside:
First paragraph—short version.
Second—“The paths that gets used the most strengthen, those that are less useful weakens over time” seems good to include, but you don’t make any mention of how that translates into ANNs. Maybe that comes later? Apart from that, I prefer the short version.
Third—Both discussions of threshold functions are kind of awkward. Long version—the first part makes it sound like the activation function is Heaviside: either 0 or 1. You attempt to correct that impression, but you don’t say what an activation function is, so it doesn’t work. Short version—depending on your audience, “sigmoid” and “hyperbolic tangent” need to be defined; and the second part again seems to suggest Heaviside contraray to the first part.
I think I’d recommend you just leave the Heaviside impression in place (maybe correct it in a footnote). “Artificial neurons imitate this behaviour using a threshold function. Each neuron weights each of its inputs, adds them together, and propagates the signal if the combined input is above some level.”
I am pro-[pic], depending on the pic.
Fourth—you can’t leave the “short” version there; you’re opening a plot thread and then not closing it. If you’re going somewhere with it (discussing/mentioning different ANN models, or how this model can be made manageable, or something), then great, but you might want to not start it until the point where you take it somewhere. If not, you should probably just cut it.
“The first to be considered and implemented” has similar problems, but less strongly.
Thanks for the lenghty analysis, yes I’m aware that these are the first drafts of a first draft, and I don’t even know if they will retain this form, but your comments made me realize that a shorter, faster pace is the way to go.
Thank you very much!