Ikibazo gihuza ibibazo · Biragoye Urwego
Kumenyekanisha Ikibazo
Witoze guhindura ibintu bidasubirwaho, guhinduka-guhinduka-ubucucike, hamwe no gukosora Yakobo, harimo imipaka yo kumenya ibintu bidasanzwe.
Ikibazo 1 Bya 8
Ni ubuhe buryo bw'imibare bugomba guhinduka muburyo busanzwe bugira?
Reba buri kibazo8 ibibazo
Ibisubizo nibisobanuro bigaragara mugihe ufata ikibazo.
- Ni ubuhe buryo bw'imibare bugomba guhinduka muburyo busanzwe bugira?
- Igomba kuba ikarita idasanzwe, idashobora guhinduka
- Igomba kuba idahinduka (bijective) kandi itandukanye
- Igomba kugabanya ibipimo kuri buri ntambwe
- Igomba kuba imbonerahamwe yo gushakisha
- Nihe formula ireka ibisanzwe bitemba bibara bishoboka?
- Imikorere ya softmax
- Ikigereranyo cya Bellman
- Amategeko ya Bayes akoreshwa mubitabo
- Guhindura-guhinduka-formula ukoresheje Jacobian determinant
- Ni ukubera iki imyubakire yububiko nka RealNVP na Glow ikoresha guhuza ibice?
- Gukora inyabutatu ya Yakobo kugirango igenamigambi rihendutse kubara
- Gukora icyitegererezo kidahinduka
- Gukuraho ibikenewe kugabanwa shingiro
- Guhindura icyitegererezo muri GAN
- What does a tractable normalizing flow provide that an ordinary GAN generator generally does not?
- A guarantee of perfect anomaly detection
- A guarantee of faster sampling than every GAN
- An explicitly evaluable model density through change of variables
- A non-invertible mapping with no base distribution
- How should a team use normalizing-flow likelihoods for anomaly detection?
- Assume every high-likelihood input is familiar
- Treat density as the probability mass of a single point
- Skip checking real anomaly labels
- Validate them as a signal against relevant in-distribution and anomalous examples
- Nubuhe buryo bugezweho, bukoreshwa muri sisitemu nka Stable Diffusion 3, bwakuze mubitekerezo bikomeza?
- Gusubira inyuma mugihe
- Guhuza gutemba (kwiga umuvuduko umuvuduko utwara urusaku kumakuru)
- Tokenisation
- Gushakisha ibiti
- A one-dimensional flow inverse is z = x / 2. What log-Jacobian term appears in log p(x)?
- log(2)
- The parameter count of the network
- log(1/2)
- No term because the inverse is linear
- Why must a normalizing flow account for stretching or shrinking volume?
- A transformed region’s density must reflect the changed volume
- The transformation must lose half its dimensions
- Every output point must have probability mass one
- The base distribution must be discarded after training