Farasin Markov Models adanwo

Awọn idahun ati awọn alaye han bi o ṣe n mu ibeere naa.

1. Kini 'farasin' ni Awoṣe Markov Farasin tọka si?
   • Awọn ipinlẹ ko ṣe akiyesi ati pe a ṣe akiyesi lati awọn abajade
   • Awọn paramita awoṣe jẹ asiri
   • Awọn akiyesi ti wa ni ìpàrokò
   • Awọn iyipada jẹ laileto ati aimọ
2. Kini ohun-ini Markv ti gba nipasẹ HMM kan?
   • Gbogbo awọn ipinlẹ n jade aami kanna
   • Ipinle ti o tẹle nikan da lori ipo ti o wa lọwọlọwọ
   • Awọn akiyesi jẹ ominira ti awọn ipinlẹ
   • Gbogbo ipinle jẹ dogba seese
3. Eyi ti alugoridimu nwa awọn nikan julọ seese ọkọọkan ti farasin ipinle?
   • Algoridimu Siwaju
   • Baum-Welch
   • Viterbi algorithm
   • Isosile ite
4. Awọn eto iṣeeṣe mẹta wo ni pato HMM kan ni kikun?
   • Ṣaaju, o ṣeeṣe, ati ẹri
   • Itumọ, iyatọ, ati isomọ
   • Iṣagbewọle, pamọ, ati awọn òṣuwọn ti o wu jade
   • Ipo ibẹrẹ, iyipada, ati awọn iṣeeṣe itujade
5. Kini algorithm Baum-Welch ṣe?
   • Kọ ẹkọ awọn aye HMM lati inu data nipasẹ ireti-ti o pọju
   • Encrypts ọkọọkan akiyesi
   • Wa ọna kan ti o ṣeeṣe julọ
   • Ṣe iṣiro matrix iyipada gangan ni fọọmu pipade
6. Which Transformer feature can directly relate tokens at distant positions in a sequence?
   • An HMM emission table
   • Self-attention over positions in the input
   • A fixed single-state transition
   • A requirement to process only one token ever
7. What does the Forward algorithm compute for a sequence of observations?
   • Only the single most likely state path
   • The most likely parameter initialization
   • The total probability of the observations by summing over possible hidden-state paths
   • The mean of the emission probabilities
8. A hidden state emits a word or acoustic symbol. Which HMM probability describes that relation?
   • The initial-state probability
   • The transition probability
   • The discount factor
   • The emission probability