Hello,
I wonder what is the difference between optimizing an airfoil using artificial neural network (ANN) and convolutional neural network (CNN) ? How much do the output differ using each method ?
Thanks,
An ANN is a collection of connected and tun-able units (a.k.a. nodes, neurons, and artificial neurons) which can pass a signal (i.e., usually a real-valued number) from a unit to another. The number of (layers of) units, their types, and the way they are connected to each other is called the network architecture.
The class of ANN covers several architectures including :::e.g.,
1) Convolutional Neural Networks (CNN).
2) Recurrent Neural Networks (RNN) eg LSTM and GRU, Auto-encoders.
3) Deep Belief Networks.
Accordingly, CNN is just one kind of ANN.
The CNN is a subclass of ANN. The benefits of using CNN are: reduces the complexity of the model, requires less computational power and memory, and can capture more details in the picture such as spatial and contextual information.
CNN is a subclass of neural networks which have at least one convolution layer. They are great for capturing local information (e.g. neighbor pixels in an image or surrounding words in a text) as well as reducing the complexity of the model (faster training, needs fewer samples, reduces the chance of over fitting).
- Badges
- Science topic