A python wrapper for SkyNet neural network that can de downloaded here : http://ccpforge.cse.rl.ac.uk/gf/project/skynet/
SkyNet is an efficient and robust neural network training code for machine learning. It is able to train large and deep feed-forward neural networks, including autoencoders, for use in a wide range of supervised and unsupervised learning applications, such as regression, classification, density estimation, clustering and dimensionality reduction. SkyNet is implemented in C/C++ and fully parallelised using MPI.
SkyNet is written by Philip Graff, Farhan Feroz, Michael P. Hobson and Anthony N. Lasenby
reference : http://xxx.lanl.gov/abs/1309.0790
Bases: SkyNet.SkyNet
A neural net classifier.
This class calls Skynet as a classifier.
Parameters: | id : string, compulsory
input_root : string, optional (default=custom)
output_root : string, optional (default=custom)
result_root : string, optional (default=custom)
config_root : string, optional (default=custom)
layers : tuple , optional (default=(10,10,10))
activation : tuple =, optional (default=(2,2,2,0))
prior : boolean, optional (default =True)
mini-batch_fraction : float, optional(default=1.0)
validation_data : bool, optional (default = True)
confidence_rate : float, optional (default=0.03)
confidence_rate_minimum : float, optional (default=0.02)
iteration_print_frequency : int, optional (default=50)
max_iter : int, optional (default=2000)
n_jobs : integer, optional (default=1)
whitenin : integer, optional (default=1)
whitenout : integer, optional (default=1)
convergence_function : integer, optional (default=4)
historic_maxent : bool, optional (default=False)
line_search : int, optional (default = 0)
noise_scaling : bool, optional (default = False)
set_whitened_noise : bool, optional (default =False)
sigma : float, optional (default = 0.3)
fix_seed : bool, optional (default =False)
fixed_seed : int, optional (default =0)
resume : bool, optional (default = False)
reset_alpha : bool, optional (default = False)
reset_sigma : bool, optional (default = False)
randomise_weights : float, optional (default = 0.01)
verbose : int, optional (default=2)
pretrain : bool,
nepoch : int, optional (default=10)
|
---|
See also
References
[R1] | SKYNET: an efficient and robust neural network training tool for machine learning in astronomy http://arxiv.org/abs/1309.0790 |
Attributes
n_features | ( int) The number of features. |
train_input_file | (string) Filename of the written training file. |
valid_input_file | (string.) Filename of the written validation file. |
SkyNet_config_file | (string) Filename of SkyNet config file. |
network_file | (string) Filename of SkyNet network file. This file contains the trained weights: |
Predict class probabilities for X.
The predicted class probabilities of an input sample is computed as by trained neural network
Parameters: | X : array-like of shape = [n_samples, n_features]
|
---|---|
Returns: | p : array of shape = [n_samples,n_classes]
|
Attributes
output_file | (String) SkyNet writes to this file: result_root + self.id + _predictions.txt. |
Bases: SkyNet.SkyNet
A neural net regeressor.
Parameters: | id : string, compulsory
input_root : string, optional (default=custom)
output_root : string, optional (default=custom)
result_root : string, optional (default=custom)
config_root : string, optional (default=custom)
layers : tuple , optional (default=(10,10,10))
activation : tuple =, optional (default=(2,2,2,0))
prior : boolean, optional (default =True)
mini-batch_fraction : float, optional(default=1.0)
validation_data : bool, optional (default = True)
confidence_rate : float, optional (default=0.03)
confidence_rate_minimum : float, optional (default=0.02)
iteration_print_frequency : int, optional (default=50)
max_iter : int, optional (default=2000)
n_jobs : integer, optional (default=1)
whitenin : integer, optional (default=1)
whitenout : integer, optional (default=1)
convergence_function : integer, optional (default=4)
historic_maxent : bool, optional (default=False)
line_search : int, optional (default = 0)
noise_scaling : bool, optional (default = False)
set_whitened_noise : bool, optional (default =False)
sigma : float, optional (default = 0.3)
fix_seed : bool, optional (default =False)
fixed_seed : int, optional (default =0)
resume : bool, optional (default = False)
reset_alpha : bool, optional (default = False)
reset_sigma : bool, optional (default = False)
randomise_weights : float, optional (default = 0.01)
verbose : int, optional (default=2)
pretrain : bool,
nepoch : int, optional (default=10)
|
---|
See also
References
[R2] | SKYNET: an efficient and robust neural network training tool for machine learning in astronomy http://arxiv.org/abs/1309.0790 |
Attributes
n_features | ( int) The number of features. |
train_input_file | (string) Filename of the written training file. |
valid_input_file | (string.) Filename of the written validation file. |
SkyNet_config_file | (string) Filename of SkyNet config file. |
network_file | (string) Filename of SkyNet network file. This file contains the trained weights: |
Predict regression target for X.
The predicted regression target of an input sample is by the trained neural network.
Parameters: | X : array-like of shape = [n_samples, n_features]
|
---|---|
Returns: | y: array of shape = [n_samples]
|
Attributes
output_file | (String) SkyNet writes to this file: |