genome.models.dnn¶
Deep Neural Network models
-
class
genome.models.dnn.HiddenLayer(input, n_in, n_out, layer_num, W=None, bias=None, activation=None)¶ Bases:
objectHidden Layer class object
This abstract class is used for a wrapper for intermediate layers. Common activation function used are
T.nnet.sigmoid,T.nnet.softplus,T.nnet.relu,T.tanh.Parameters: - input – A symbolic
Tensorinput - n_in (int) – Number of input variables.
- n_out (int) – Number of output variables.
- layer_num (int) – The n-th layer of the neural network
- W – Weight parameters - A
TensorSharedVariable(optional) - bias – Bias parameters - A
TensorSharedVariable(optional) - activation – Activation function, example
T.nnet.softplus, defaults to linear regression if undefined
- input – A symbolic
-
class
genome.models.dnn.MLP(input, n_in, n_out, layers)¶ Bases:
genome.models.base.MultiLayerModelInitializes a Multilayer perceptron model
Parameters: - input (theano.tensor.TensorVariable) – symbolic variable that describes the input
- n_in (int) – Number of input variables
- n_out (int) – Number of output variables
- layers (list of theano.shared.TensorSharedVariable) – Defines the number of input connection, output connection and layer activation
function. Example:
[(n_in, n_hidden, activation),... (n_hidden, n_out, activation)]
Example
>>> x = T.matrix('x') >>> model = MLP(input=x, n_in=5, n_out=2, layers=[(5, 4), (4, 2)])
-
negative_log_likelihood(y)¶
-
class
genome.models.dnn.ResLogit(input, n_vars, n_choices, n_layers, beta=None, asc=None)¶ Bases:
genome.models.logit.MultinomialLogitInitializes a ResLogit model
The ResLogit model consists of a series of residual blocks that captures the heterogeneity in the data. It is an extension of the
MultinomialLogitclass.Parameters: - input (theano.tensor.TensorVariable) – symbolic variable that describes the input
- n_vars (int) – Number of input variables
- n_choices (int) – Number of choice alternatives
- n_layers (int) – Number of residual layers
- beta (theano.shared.TensorSharedVariable, optional) – \(\beta\) parameters
- asc (theano.shared.TensorSharedVariable, optional) – Alternative Specific Constants
-
class
genome.models.dnn.ResNetLayer(input, size, layer_num, W=None)¶ Bases:
objectA ResNetLayer implementing a softplus activation and square matrix
For now, we don’t use reference parameters (masking) for the residual matrix. Reason – no logical reason to do so.
Parameters: - input – A symbolic
Tensorinput - size (tuple(int, int)) – The shape of the residual correlation matrix
- layer_num (int) – The n-th layer of the neural network
- W – Weight parameters - A
TensorSharedVariable(optional)
- input – A symbolic