Kedis ku xidhan hagaha · Dhexdhexaad Heerka

Kediska Is-Daawaynta Wanaagsan

Ku baadh ciyaarta-is-daynta ee Go iyo qaabka luqadda, barbar dhig AlphaGo Zero iyo AlphaZero, oo baadh calaamadaha xogta go'an iyo khataraha xogta-synthetic-ka.

Wadooyinka haga ee la xidhiidhaDaawaynta Wanaagsan ee Self Play
Su'aal 1 ee 8

Nidaamkee caanka ah ayaa gaadhay ciyaarta Go ee ka sarreeya bini'aadamka iyadoo la adeegsanayo is-ciyaar kaliya oo aan lahayn diiwaannada ciyaarta aadanaha?

Horudhac su'aal kasta8 su'aalo

Jawaabaha iyo sharraxaadaha waxay soo baxayaan markaad qaadanayso kediska.

  1. Nidaamkee caanka ah ayaa gaadhay ciyaarta Go ee ka sarreeya bini'aadamka iyadoo la adeegsanayo is-ciyaar kaliya oo aan lahayn diiwaannada ciyaarta aadanaha?
    • AlphaGo eber
    • Deep Blue
    • Watson
    • GPT-2
  2. Gudaha SPIN, muxuu ciyaara doorka 'ka soo horjeeda' ee ay tahay in tusaaluhu garaaco?
    • Qaab abaal-marineed oo bani-aadmigu tababaray oo gaar ah
    • Isbaaradii hore ee moodeelka iyo jawaabihiisii
    • Soosaaraha qoraalka random
    • Calaamadeeyaha
  3. Waa maxay faa'iidada ugu weyn ee waxtarka xogta ee is-dheellitirka hagaajinta?
    • Waxay u baahan tahay xog-ururin cusub oo biniaadmi ah wareeg kasta
    • Waxa kaliya oo ay ku shaqeysaa xog aan xadidneyn
    • Waxay ka soo saari kartaa faa'iidooyin badan oo ka mid ah dataset go'an iyada oo aan lahayn calaamado cusub oo bini'aadan ah
    • Wax model ah uma baahna
  4. Ujeedada tababarka SPIN, waa maxay qaabka loo riixay inuu sameeyo?
    • Ka door bidaa jawaabaha ay iyadu abuurto marka loo eego tixraacyada aadanaha
    • Iska daa dhammaan xogta aadanaha
    • Xafid habka imtixaanka
    • U qoondee suurtagalnimada sare ee jawaabaha tixraaca aadanaha marka loo eego wax soo saarkeedii hore
  5. Which pair of games did the AlphaZero paper demonstrate beyond its Go experiments?
    • Chess and shogi
    • Poker and bridge
    • Checkers and Othello
    • Atari and StarCraft
  6. What risk did researchers report when language models are recursively trained on generated data?
    • Model collapse, with loss of diversity and representation of the original distribution
    • Guaranteed monotonic improvement at every iteration
    • Automatic prevention of distribution shift
    • A higher count of verified human labels
  7. What search component does AlphaGo Zero use alongside self-play?
    • A nearest-neighbor lookup over human game records
    • A language-model tokenizer
    • Monte Carlo tree search guided by a policy and value network
    • A fixed list of opening moves
  8. Why can automatic checkers be useful in self-play for math or code tasks?
    • They guarantee that a model never learns incorrect strategies
    • They replace the need for a task specification
    • They make all generated examples independent of the model
    • They can verify generated solutions without requiring a new human label for each attempt