Here is a list of parameters you should take into consideration (to name some):
The learning algorithm (gradient descent is the most explained of them)
The number of layers (3,4 layers is usually enough - input, 1 or 2 hidden, output). The output layer depends on your output (e.g., if you want to classify yes/no then your output layer consists of two nodes)...
Here is what I gathered from skimming the paper for just the figure.
Your first figure, which is the figure 3 in the paper, already has the answer in its caption:
Figure 3: The two types of structural mutation in NEAT. Both types,
adding a connection and adding a node, are illustrated with the
connection genes of a network shown above their ...
Yes, the "one boolean per set element" is the standard way of encoding such a set. This is known as a "one-hot encoding". Yes, there will be a lot of input neurons, but that's not necessarily a serious problem; current procedures for training neural networks are able to handle millions of nodes with no problems.
If you know that $T$ will contain at most $...
I assume that a Turing machine will nor be able to reason that the liar paradox statement is a logical paradox with no decidable answer and will be stuck forever.
Why do you assume that? It's perfectly possible for a Turing machine to recognize a specific paradox and to have logic systems that include the concept of paradox.
Also, note that undecidability ...
Your premise is wrong. A single-layer neural network (perceptron) can use a (nonlinear) activation function. Nothing prevents you from doing that.
It's common that the last layer of a neural network doesn't use any activation function, and instead is input into a softmax layer. If there's only one layer, that means that no activation function is used. ...
Is there a possibility to develop an analog-based ASIC for neural
This had been already implemented a long time ago.
I guess, no one ever seriously supposes that this is impossible. There're many implementations in papers since 70th. They're still not of industry-standard quality, and with some limitations. However, they're real prototypes ...
A good start would be to understand what reinforcement learning is; and identify which problems are reinforcement learning problems and which aren't. Deep reinforcement learning is only relevant if you have a reinforcement learning problem; otherwise, it's almost certainly not relevant. Among other things, reinforcement learning deals with a stateful ...
When Building AI and ML for you Chatbot, you basically have 2 options:
You can use a 3rd party tool which will take care of the
AI/Conversational part of the Chatbot.
You can make your own using Machine Learning.Overwhelming, but quite
a few developers are choosing to go this route and many companies
are trying to democratize Machine Learning.
You can ...
You can represent the problem as a directed graph where the nodes are the states and the edges are the action that signifies the transition from one state to another if the action is performed. Once this is done you can use various graph path finding algorithms to find the sequence of actions to reach a specific state from a starting state.