Neural Networks (NN)
neural network tries to simulate the way a brain processes, learns and remembers
information. An NN learns from experience. It looks for similarities in information
that is fed to it and compares that with previous data. It then makes a selection
based on that. That is, it looks for patterns.
This pattern matching is
based on what is called machine learning, but you have to teach an NN what is
a match and what is not. Feed in enough examples of characteristics of an alive
human (e.g., breathing, pulse, eye movement, etc.) and a neural network will
start to establish a pattern as to whether those inputs point towards a correct
diagnosis of alive or dead.
Figure 3: Again, our simplistic example of a Neural Network
are various forms of machine learning in a neural network including:
e.g., feed in an activity that has zero total float and tell the NN that
the activity is "on the critical path". After feeding in enough of these activities,
it will establish a pattern that matches zero float activities to critical path
- Unsupervised: feed in activities but don't
tell the NN which are on the critical path or let the NN try and categorize the
activities based on its various attributes e.g., total float. In this instance,
the NN will perhaps group into zero and non-zero float without knowing this relates
to critical path it simply groups activities together.
teaching through reward, e.g., teaching a kid good behavior by offering a
treat. As to our planning software examples, perhaps the license cost of the software
should automatically go up or down depending on how good the AI engine suggestions