V. et al. International evaluation of an AI system for breast cancer screening. Nature 577, 89‒94 (2020). 画像出典: https://news.mit.edu/2019/using-ai-predict-breast-cancer-and-personalize-care-0507 マンモグラフィ検診は,⼈間でも判定が難しいので,AI⽀援は がん予測の精度向上と⼈間の作業負荷の削減につながる 8
㻕㻓㻓㻖㻓㻔 㻕㻓㻓㻖㻓㻚 㻕㻓㻓㻗㻓㻔 㻕㻓㻓㻗㻓㻚 㻕㻓㻓㻘㻓㻔 㻕㻓㻓㻘㻓㻚 㻕㻓㻓㻙㻓㻔 㻕㻓㻓㻙㻓㻚 㻕㻓㻓㻚㻓㻔 㼗㼌㼐㼈 ncrease and decrease in the number of oncerning a fact y that a common-sense fact is found on the ease in a similar manner as time passes. The n and expired states are represented by a uni- tribution. In total, the temporal distribution ance of a statement on the Web is modeled as tribution. matical formulation is as follows. We repre- Recognition Model using a mixture distribu- eans the probability that web page about a n be created at time t. It is expressed as a lin- on of a Gaussian distribution N(t; µ, σ2) with d an exponential distribution f(t) with weight = α1N(t; µ, σ2) + α2f(t) (1) 2 i: index for distributions (i ∈ {1, 2}). αi : weight for distribution i. λ: parameter for the exponential distribution. µ: mean vector for the Gaussian. σ2: variance for the Gaussian. φi: parameter vector (αi, λ, µ, σ2). pi(xk |φi): probability of xk by distribution i. Φ: parameter vector for the mixture model. p(xk |Φ): probability of xk by the mixture model. select initial estimated parameter vector Φ until Φ converges to Φ do Φ ← Φ for each i do initialize Ψi , Mi , Si for each k do ψik ← αipi(xk|φi) p(xk|Φ) Ψi ← Ψi + ψik Mi ← Mi + ψik xk if i = 1 then Si ← Si + ψik (xk − µ)2 αi ← Ψi n if i = 1 then µ ← Mi Ψi , σ2 ← Si Ψi if i = 2 then λ ← − Ψi Mi return Φ This algorithm is based on the calculation in Appendix A. 数理的内容の学習は,初学者にはハードルが高い 12