Njodzi Kukanganwa Quiz

Mhinduro uye tsananguro zvinoonekwa paunenge uchitora bvunzo.

1. Ndeapi mamiriro anotsanangura njodzi yekukanganwa muneural network?
   • Kana kudzidza basa idzva kunoita kuti modhi irasikirwe nemano akadzidza kare
   • Kana modhi inopera mundangariro panguva yekufungidzira
   • Kana data rekudzidzisa radzimwa netsaona
   • Kana muenzaniso uchiramba kupindura mubvunzo
2. Sei kukanganwa kwenjodzi kuchiitika mumaneural network?
   • Nekuti basa rega rega rinowana rakasiyana network otomatiki
   • Nekuti mitsva gradient inogadziridza inonyora uremu hwakagovaniswa iyo yakakodha hunyanzvi hwekare
   • Nekuti modhi haigone kuchengeta inopfuura chokwadi chimwe
   • Nekuti yekutarisisa maseketi anodzima data nechinangwa
3. Chii chinoitwa neElastic Weight Consolidation (EWC) kuderedza kukanganwa?
   • Inodzima data rebasa idzva
   • Inowedzera kaviri mwero wekudzidza
   • Inoranga shanduko kune huremu hwakakosha pamabasa akadzidzwa kare
   • Inobvisa kutarisa kubva kumuenzaniso
4. Chiitiko chinodzokorora (rehearsal) kurwisa kukanganwa sei?
   • Nokuomesa modhi yose zvachose
   • Nekudzidziswa chete pane nyowani data
   • Nokuderedza nhamba yezvikamu
   • Nekupindirana yakachengetwa mienzaniso yekare panguva yekudzidziswa kutsva
5. What does LoRA do to base-model weights when adding a task-specific adapter?
   • It freezes base weights and trains a low-rank adapter, which may reduce direct interference but does not guarantee retention
   • It rewrites every base weight for each new task
   • It stores no task-specific parameters
   • It guarantees zero forgetting on every task sequence
6. Nzira yekudzorera-yakawedzerwa inodzivisa sei kukanganwa kunotyisa?
   • Nekudzima ruzivo rwekare kuita nzvimbo
   • Nekuchengeta ruzivo rutsva mudura rekunze panzvimbo yezviyereso
   • Nokudzidzira nguva dzose pane ruzha rusina kurongeka
   • Nekudzima ndangariro yemodhi zvachose
7. How does Gradient Episodic Memory (GEM) constrain learning on a new task?
   • It removes old task examples from memory
   • It changes the model to a nearest-class-mean classifier
   • It adjusts the gradient so the first-order approximation does not increase loss on stored prior-task examples
   • It adds a KL penalty to every parameter regardless of task
8. How do RAG-Token and RAG-Sequence differ in the original RAG paper?
   • RAG-Token removes retrieval while RAG-Sequence removes generation
   • RAG-Sequence uses images while RAG-Token uses audio
   • RAG-Token trains without model parameters
   • RAG-Token marginalizes retrieved documents per output token, while RAG-Sequence uses one document for a whole sequence