SNNPy Alpha 3.0.1

Patched small memory leak

see release 3.0.0 for v3 features

SNNPy Alpha 3.0.0

The neural network modelling software currently has the following features.

• Xavier initiation of weights using box mueller transform to generate normally distributed random variables.
• Uniform random initialization of weights.
• Uniform random initialization of weights.
• Simple forward propogation algorithm.
• Simple back propogation algorithm.
• Batch training.
• Batch randomzitaion (ensuring that the training examples arent always in the same order).
• 4 activation functions (linear, sigmoid, ReLU, TanH).
• Possibility to use different activation functions in the input, hidden and output layer.
• 2 cost functions (cross entropy cost, and mean square cost).
• Configurable learning rates.
• Fully configurable feed forward network structures (only requirement being there should be at least 1 input, 1 hidden layer neuron and 1 output neuron).
• Gradient batch averaging.
• L1 and L2 Regularization

SNNPy Beta 2.0.0

Working FFN with weight and bias optimization done by backpropogation. Major overhaul to several algorithms and api.

SNNPY Beta 1.0.0

Working FFN with weight and bias optimization done by brute force numerical derivation.