Be the first to post a text review of NeuronDotNet - Neural Networks in C#. Rate and review a project by clicking thumbs up or thumbs down in the right column.

View all reviews

• Tracker artifact added

  Anonymous created the ExponentialFunction produces wrong values artifact

  posted by nobody 39 days ago

• Forum thread added

  buhochileno created the mono support forum thread

  posted by buhochileno 164 days ago

• Forum comment added

  azulin commented on the RE: Save/Load Neuronet to file? forum thread

  posted by azulin 196 days ago

• Forum comment added

  hamidude commented on the RE: save ANN to a file forum thread

  posted by hamidude 214 days ago

• Forum comment added

  hamidude commented on the RE: Save/Load Neuronet to file? forum thread

  posted by hamidude 214 days ago

• Forum thread added

  hamidude created the save ANN to a file forum thread

  posted by hamidude 214 days ago

• Forum thread added

  matt_dunn created the Newbie Question forum thread

  posted by matt_dunn 421 days ago

• Tracker artifact added

  okonovalenko created the Serialize/Deserialize KohonenSom network problem artifact

  posted by okonovalenko 424 days ago

• Forum thread added

  okonovalenko created the Save/Load Neuronet to file? forum thread

  posted by okonovalenko 428 days ago

• NeuronDotNet NeuronDotNet Core 3.0 file released: ndn30src.zip

  NeuronDotNet 3.0 Release Date: August 20th, 2008 * Support for neural networks with any acyclic structure of layers * One-One and Complete connectors are supported * Backpropagation networks and Kohonen SOMs are supported * Learning Rate changes from its initial value to a final value using a pluggable function (Linear, Logarithmic and Hyperbolic functions are built in) * Neural network initialization modules are pluggable (Random, Constant, NguyenWidrow and Normalized Random Functions are built in) * Custom activation funtions used in backpropagation networks are pluggable (Sigmoid, sine, tanh, logarithmic and linear functions are built in) * For a Kohonen Layer, Neighborhood functions are pluggable (Gaussian function and mexican hat functions are built in) * Various events are exposed which allow users to analyse how a network learns * Kohonen layers are planar in shape. However, we can have circular rows and/or columns which make them attain the shape of a cylindrical surface or a toroidal surface. * Hexagonal and Rectangular Kohonen lattice topologies are supported * Training set has been defined to support Batch Training * API to add custom network architectures and learning algorithms * Layers, connectors, networks and training sets implement ISerializable interface NeuronDotNet 2.0 Release Date: November 1st, 2007 * Backpropagation neural networks with any acyclic structure of layers * Custom activation functions are pluggable * Enhanced BackPropagation Algorithm (using Momentum term, Weight Decay and Jitter). * OneOne and Complete connections between layers NeuronDotNet 1.0 Release Date: May 3rd, 2007 First release * Support for simple feed-forward backpropagation neural networks * Activation functions - Sigmoid, Linear, Logarithminc, Sine or Tanh

  posted 504 days ago