gptkb:Natural_Questions:_A_Benchmark_for_Question_Answering_Research
|
https://arxiv.org/abs/1906.00300
|
gptkb:Student's_t-distribution
|
f(x) = Γ((ν+1)/2) / (√(νπ) Γ(ν/2)) (1 + x²/ν)^(-(ν+1)/2)
|
gptkb:exponential_distribution
|
lambda * exp(-lambda * x)
|
gptkb:Squeeze-and-Excitation_Networks
|
https://arxiv.org/abs/1709.01507
|
gptkb:Pearson_Type_IV_distribution
|
complex form involving gamma function
|
gptkb:BERT_on_SQuAD
|
gptkb:BERT:_Pre-training_of_Deep_Bidirectional_Transformers_for_Language_Understanding
|
gptkb:Onyx_Boox_Max_2
|
yes
|
gptkb:inverse_gamma_distribution
|
f(x; α, β) = (β^α / Γ(α)) x^(-α-1) exp(-β/x)
|
gptkb:Pearson_Type_VI
|
f(x) = (a^m * x^{m-1}) / (B(m, n) * (a + x)^{m+n}) for x > 0
|
gptkb:standard_multivariate_normal_distribution
|
(2π)^(-n/2) exp(-1/2 x^T x)
|
gptkb:Generative_Pre-trained_Transformer_3
|
gptkb:Language_Models_are_Few-Shot_Learners
|
gptkb:chi_distribution
|
(1/2^{k/2-1} Gamma(k/2)) x^{k-1} e^{-x^2/2}
|
gptkb:Onyx_Boox_Note_Air
|
yes
|
gptkb:normal_distribution
|
(1/(σ√(2π))) * exp(-0.5*((x-μ)/σ)^2)
|
gptkb:Fisher–Snedecor_distribution
|
f(x; d1, d2) = [d1^{d1/2} d2^{d2/2} x^{(d1/2)-1}] / [B(d1/2, d2/2) (d1 x + d2)^{(d1+d2)/2}]
|
gptkb:2004.05150
|
https://arxiv.org/pdf/1706.03762.pdf
|
gptkb:uniform_distribution
|
1/(b-a) for a ≤ x ≤ b
|
gptkb:Log-gamma_distribution
|
f(x; μ, θ, k) = (1/Γ(k)θ^k) exp(k(x-μ)/θ - exp((x-μ)/θ))
|
gptkb:Pearson_Type_I
|
f(x) = (x-a)^{alpha-1} (b-x)^{beta-1} / B(alpha, beta) (b-a)^{alpha+beta-1}
|
gptkb:beta_distribution
|
x^(alpha-1) * (1-x)^(beta-1) / B(alpha, beta)
|