Explorations in parallel distributed processing: a handbook of models, programs, and exercises
Explorations in parallel distributed processing: a handbook of models, programs, and exercises
The appeal of parallel distributed processing
Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
Handwritten digit recognition with a back-propagation network
Advances in neural information processing systems 2
Software systems construction with examples in Ada
Software systems construction with examples in Ada
| Hi-index | 0.00 |
A neural network is a computer program structured as a simplified model of a brain. It contains nodes (analogous to neurons) and connections between nodes (analogous to synapses). Neural networks can solve difficult pattern-matching problems. A node sums the inputs it receives from other nodes and passes the result through a transfer function to produce its output. A modifiable weight is associated with each connection. A network is trained on a given training set of inputs. During training, the weights are successively adjusted to produce the desired output.Classical design and implementation of neural networks are based on arrays that hold the node values and connection weights. The control structure consists of nested loops through these arrays. This paper suggests instead an object-based design where the nodes are modeled as objects to be operated on. This design models the conceptual network more closely and makes the software more understandable and maintainable. A generic Ada package representing a neural network is presented in some detail.