What are the init functions in lasagne?

Recipe Objective - What are the init functions in lasagne?

Lasagne provides the "lasagne.init" class to create initializers for parameter variables.

Explore the Real-World Applications of Recommender Systems

Initialiers:-

1. Constant([val]) - Initialize weights with constant value.

2. Normal([std, mean]) - Sample initial weights from the Gaussian distribution.

3. Uniform([range, std, mean]) - Sample initial weights from the uniform distribution.

4. Glorot(initializer[, gain, c01b]) - Glorot weight initialization.

5. GlorotNormal([gain, c01b]) - Glorot with weights sampled from the Normal distribution.

6. GlorotUniform([gain, c01b]) - Glorot with weights sampled from the Uniform distribution.

7. He(initializer[, gain, c01b]) - He weight initialization.

8. HeNormal([gain, c01b]) - He initializer with weights sampled from the Normal distribution.

9. HeUniform([gain, c01b]) - He initializer with weights sampled from the Uniform distribution.

10. Orthogonal([gain]) - Intialize weights as Orthogonal matrix.

11. Sparse([sparsity, std]) - Initialize weights as sparse matrix.

For more related projects:-

/projects/data-science-projects/keras-deep-learning-projects
/projects/data-science-projects/neural-network-projects

Example:-

from lasagne.layers import DenseLayer
from lasagne.init import Constant, GlorotUniform
ly1 = DenseLayer((100,20), num_units=50, W=GlorotUniform('relu'), b=Constant(0.0))

ly1