• ## Sorting and analysis of loss function in face recognition

Time：2020-9-30

catalog Write it at the front Cross-Entropy Loss (softmax loss) Contrastive Loss – CVPR2006 Triplet Loss – CVPR2015 Center Loss – ECCV2016 L-Softmax Loss – ICML2016 A-Softmax Loss – CVPR2017 AM-Softmax Loss-CVPR2018 ArcFace Loss – CVPR2019 Euclidean distance or angular distance and normalization reference resources Blog: blog Garden CSDN blog Write it at the front […]

• ## Square Euclidean distance and error square sum of spark kmeans and source code analysis

Time：2020-7-3

1. Euclidean distanced(x,y) = √( (x-y)^2 + (x-y)^2 + … + (x[n]-y[n])^2 )2. Square Euclidean distanceThe distance formula of spark kmeans uses the square Euclidean distance. The square Euclidean distance is the square of the Euclidean distance (excluding the open root sign)d(x,y) = (x-y)^2 + (x-y)^2 + … + (x[n]-y[n])^2 3. Sum of squared error […]

• ## Square Euclidean distance and error sum of spark kmeans and source code analysis

Time：2020-5-21

1. Euclidean distanced(x,y) = √( (x-y)^2 + (x-y)^2 + … + (x[n]-y[n])^2 )2. Squared Euclidean distanceThe distance formula of spark kmeans uses the square Euclidean distance. The square Euclidean distance is the square of the Euclidean distance (without the root sign)d(x,y) = (x-y)^2 + (x-y)^2 + … + (x[n]-y[n])^2 3. Sum of squared error (SSE)The […]

• ## Cs156 machine learning – 1 the learning problem notes

Time：2020-2-8

outline example of machine learning Predicting how a viewer will rate a movie Movie rating – a solution spectrumRangeThe essece of machine learning: A pattern exists We cannot pin it down mathematially. We have data on it. The learning approah Components of learning Metaphor(analogy): Credit approvalApplicant information: kind info age 23 years gender male annual […]