Final Cheatsheet

You might also like

Download as pdf or txt
Download as pdf or txt
You are on page 1of 1

CNNs Probability

• X, Y uncorrelated if Cov(X, Y ) = 0, independent if


RFSize = PrevRFSize + PrevRFStride × KernelSize − 1
P (X, Y ) = P (X)P (Y )
RFStride = PrevRFStride × Stride
• P (A, B) = P (A|B)P (B) = P (B|A)P (A)
W − K + 2P
O= +1 • posterior ∝ likelihood × prior
S
parameters = (K × K × D1 ) × D2 + D2
Spectral Graph Clustering
sf = (sx − sy )+
K-Means, KD-Trees
pooling layers increase receptive field and reduce spatial resolution
Kernels
Key win is computing Φ(x)> Φ(z) = O(d) < O(dp )

You might also like