minimal_init

minimal_init([rng], [T], dims...;
    sampling_type=:bernoulli_sample!, weight=0.1, irrational=pi,
    start=1, p=0.5)

Create a layer matrix with uniform weights determined by weight (Rodan and Tino, 2011). The sign difference is randomly determined by the sampling chosen.

Arguments

• rng: Random number generator. Default is Utils.default_rng() from WeightInitializers.
• T: Type of the elements in the reservoir matrix. Default is Float32.
• dims: Dimensions of the matrix. Should follow res_size x in_size.

Keyword arguments

• weight: The weight used to fill the layer matrix. Default is 0.1.
• sampling_type: Sampling that decides the distribution of weight negative numbers. If set to :no_sample the sign is unchanged. If set to :bernoulli_sample! then each weight can be positive with a probability set by positive_prob. If set to :irrational_sample! the weight is negative if the decimal number of the irrational number chosen is odd. If set to :regular_sample!, each weight will be assigned a negative sign after the chosen strides. strides can be a single number or an array. Default is :no_sample.
• positive_prob: probability of the weight being positive when sampling_type is set to :bernoulli_sample!. Default is 0.5.
• irrational: Irrational number whose decimals decide the sign of weight. Default is pi.
• start: Which place after the decimal point the counting starts for the irrational sign counting. Default is 1.
• strides: number of strides for assigning negative value to a weight. It can be an integer or an array. Default is 2.

Examples

julia> res_input = minimal_init(8, 3)
8×3 Matrix{Float32}:
  0.1  -0.1   0.1
 -0.1   0.1   0.1
 -0.1  -0.1   0.1
 -0.1  -0.1  -0.1
  0.1   0.1   0.1
 -0.1  -0.1  -0.1
 -0.1  -0.1   0.1
  0.1  -0.1   0.1

julia> res_input = minimal_init(8, 3; sampling_type = :irrational)
8×3 Matrix{Float32}:
 -0.1   0.1  -0.1
  0.1  -0.1  -0.1
  0.1   0.1  -0.1
  0.1   0.1   0.1
 -0.1  -0.1  -0.1
  0.1   0.1   0.1
  0.1   0.1  -0.1
 -0.1   0.1  -0.1

julia> res_input = minimal_init(8, 3; p = 0.1) # lower p -> more negative signs
8×3 Matrix{Float32}:
 -0.1  -0.1  -0.1
 -0.1  -0.1  -0.1
 -0.1  -0.1  -0.1
 -0.1  -0.1  -0.1
  0.1  -0.1  -0.1
 -0.1  -0.1  -0.1
 -0.1  -0.1  -0.1
 -0.1  -0.1  -0.1

julia> res_input = minimal_init(8, 3; p = 0.8)# higher p -> more positive signs
8×3 Matrix{Float32}:
  0.1   0.1  0.1
 -0.1   0.1  0.1
 -0.1   0.1  0.1
  0.1   0.1  0.1
  0.1   0.1  0.1
  0.1  -0.1  0.1
 -0.1   0.1  0.1
  0.1   0.1  0.1