# theanets.feedforward.Regressor¶

class theanets.feedforward.Regressor(layers=(), loss='mse', weighted=False, rng=13)

A regressor attempts to produce a target output given some inputs.

Notes

Regressor models default to a MSE loss. To use a different loss, provide a non-default argument for the loss keyword argument when constructing your model.

Examples

To create a regression model, just create a new class instance. Often you’ll provide the layer configuration at this time:

>>> model = theanets.Regressor([10, 20, 3])


Data

Training data for a regression model takes the form of two two-dimensional arrays. The shapes of both of these arrays are (num-examples, num-variables) – the first axis enumerates data points in a batch, and the second enumerates the relevant variables (input variables for the input array, and output variables for the output array).

For instance, to create a training dataset containing 1000 examples:

>>> inputs = np.random.randn(1000, 10).astype('f')
>>> outputs = np.random.randn(1000, 3).astype('f')


Training

Training the model can be as simple as calling the train() method, with the inputs and target outputs as data:

>>> model.train([inputs, outputs])


Use

A regression model can be used to predict() the output of some input data points:

>>> test = np.random.randn(3, 10).astype('f')
>>> print(model.predict(test))


__init__(layers=(), loss='mse', weighted=False, rng=13)
 __init__([layers, loss, weighted, rng]) add_layer([layer, is_output]) Add a layer to our network graph. add_loss([loss]) Add a loss function to the model. build_graph([regularizers]) Connect the layers in this network to form a computation graph. feed_forward(x, **kwargs) Compute a forward pass of all layers from the given input. find(which, param) Get a parameter from a layer in the network. itertrain(train[, valid, algo, subalgo, ...]) Train our network, one batch at a time. load(filename) Load a saved network from disk. loss(**kwargs) Return a variable representing the regularized loss for this network. monitors(**kwargs) Return expressions that should be computed to monitor training. predict(x, **kwargs) Compute a forward pass of the inputs, returning the network output. save(filename) Save the state of this network to a pickle file on disk. score(x, y[, w]) Compute R^2 coefficient of determination for a given labeled input. set_loss(*args, **kwargs) Clear the current loss functions from the network and add a new one. train(*args, **kwargs) Train the network until the trainer converges. updates(**kwargs) Return expressions to run as updates during network training.
 DEFAULT_OUTPUT_ACTIVATION INPUT_NDIM OUTPUT_NDIM inputs A list of Theano variables for feedforward computations. num_params Number of parameters in the entire network model. params A list of the learnable Theano parameters for this network. variables A list of Theano variables for loss computations.