5 = 1 k2 E 2 4 X i 0 @✏2 i + X j6=i ✏i✏j 1 A 3 5 = 1 k v + k 1 k c = ( 1 k v (c = 0) v (c = v) ϞσϧฏۉԽ • ෳͷϞσϧΛผʑʹ܇࿅ͤͨ͞ޙɺͦΕΒͷϞσϧ͢ ͔ͯΒςετࣄྫʹର͢Δग़ྗΛථ • ௨ৗϞσϧ͕ҟͳΕɺಉ͡ςετࣄྫͰ͕͋ͬͯͯ͢ ಉؒ͡ҧ͍Λ͠ͳ͍ͨΊɺ͏·͘ಇ͘ • ޡ͕ࠩฏۉ0ͷଟมྔਖ਼نʹै͏kݸͷճؼϞσϧͷྫ: ࢄ E[✏2 i ] ڞࢄ E[✏i✏j] ֤Ϟσϧͷޡࠩ Ξϯαϯϒϧ༧ଌثͷ ظೋޡࠩ
= y|v) = softmax(W >v + b)y · · · ˜ Pensemble(y = y|v) / 2n v u u t Y d2{0,1}n exp ⇣ W > y,: (d v) + by ⌘ = exp 0 @ 1 2n X d2{0,1}n W > y,: (d v) + by 1 A = exp ✓ 1 2 W > y,: v + by ◆
represent something, so this must be a local representation. • “Distributed representation” means a many-to- many relationship between two types of representation (such as concepts and neurons). • Each concept is represented by many neurons • Each neuron participates in the representation of many concepts IUUQXXXDTUPSPOUPFEVdCPOOFSDPVSTFTTDTDMFDUVSFTMFDQEG