Up tókànItọsọna atẹle
Ẹkọ Ilọsiwaju ati Igbagbe Ajalu
Awọn ipilẹ
Èdè AI Itọsọna
Igbagbe Ajalu
Catastrophic forgetting occurs when training on new tasks degrades performance on previously learned tasks.
Gbọ si itọsọna yiiAI-ṣe afihan · ~2 min
Lori iwe yi2 min ka
Akopọ
Continual-learning methods attempt to balance adaptation and retention.
Jin Dive
Catastrophic forgetting occurs when learning new tasks degrades earlier capabilities. EWC penalizes changes to parameters important to earlier tasks; GEM constrains gradients using episodic examples under a local first-order approximation; iCaRL stores exemplars and uses class-mean features. LoRA freezes base weights and learns low-rank task updates, which may reduce direct interference but does not guarantee retention. The original RAG paper distinguishes sequence-level and token-level document marginalization. These mechanisms address different issues and require evaluation on old and new tasks.
Real-World imuse
Elastic Weight Consolidation penalizes changes to parameters estimated to be important for earlier tasks.
Experience replay mixes stored earlier examples with new-task examples during training.
LoRA keeps task-specific low-rank updates separate from frozen base weights in some adaptation settings.
Retrieval-augmented generation can consult an external index rather than storing every fact only in model parameters.
Ojo iwaju ti Igbagbe Ajalu
Evaluate old and new task performance after each update and make the retention criterion explicit. Choose methods based on data availability, storage and privacy constraints. Research benchmarks do not establish that any single technique prevents forgetting in all deployment settings.
Fifi o sinu iwa
Kini idi ti o ṣe pataki
- Iyara ati iwọn. Ṣiṣan iṣẹ ede le gbe ni iyara laisi irubọ aitasera.
- Wiwọle ati arọwọto. O faagun iraye si kọja awọn ede ati awọn aza ibaraẹnisọrọ.
- Awọn ipinnu diẹ sii. Awọn ẹgbẹ le lo akoko diẹ sii lori idajọ lakoko ti adaṣe n kapa atunwi.
Ṣọra fun
- Awọn otitọ ti a sọ di mimọ le tẹ awọn ijabọ sii ni idakẹjẹ, awọn ṣiṣan atilẹyin, tabi awọn abajade iwadii.
- Ifamọ kiakia le ṣẹda awọn abajade aisedede kọja awọn ibeere ti o jọra.
- Awọn data ọrọ ifarabalẹ le farahan ti awọn idari wiwọle ko lagbara.
Next awọn igbesẹ
- Ṣetumo ọna kika iṣẹjade, ohun orin, ati awọn iṣedede didara ṣaaju ṣiṣejade.
- Awọn idahun ilẹ pẹlu awọn orisun ti o gbẹkẹle nigbakugba ti deede ba ṣe pataki.
- Jeki aaye ayẹwo atunyẹwo eniyan fun awọn abajade ti o ga julọ.
- Tọpinpin awọn ilana ikuna ati tunṣe awọn itọsi tabi ṣiṣan iṣẹ nigbagbogbo.
Tesiwaju Ṣiṣawari
Ìwé ìròyìn ọfẹ
Gba ìkànìyàn AI ojoojúmọ́
Ìtàn AI mẹta tó jẹ́rìí ní gbogbo owurọ́ ọjọ́ iṣẹ́, kọ́wé ní Gẹ̀ẹ́sì tó rọrùn. Ọfẹ́ fún gbogbo àkókò, kò sí ìpolówó.
Ìmeèlì kan ní gbogbo ọjọ́ iṣẹ́. Yọkúrò ní ìkànìyàn ní ìkànìyàn kan. A kò ta tàbí pín àdírẹ́sì rẹ.
Ṣe idanwo fun ara rẹ
Take the Catastrophic Forgetting quiz
Ìdáhùn lẹ́sẹ̀kẹsẹ̀ lórí gbogbo ìdáhùn, àti iwe-ẹ̀rí tó lè pin pẹ̀lú ID tó lè jẹ́rìí lẹ́yìn tí o bá kọ́ ẹ̀kọ́.
Ṣe àtìlẹ́yìn ẹ̀kọ́ AI ọfẹ́. AI Understanding jẹ́ àjọ àìní èrè 501(c)(3) — kò sí ìpolówó, kò sí àkúnya owó, ní gbogbo àkókò. Ṣe ẹbun kan
Awọn ibeere ti a beere nigbagbogbo
What is Catastrophic Forgetting?
Catastrophic forgetting occurs when training on new tasks degrades performance on previously learned tasks. Continual-learning methods attempt to balance adaptation and retention.
Ipo wo ni o ṣapejuwe igbagbe ajalu ni nẹtiwọọki nkankikan?
Igbagbe ajalu jẹ ipadanu airotẹlẹ ti awọn agbara atijọ nigbati nẹtiwọọki kan ti ni ikẹkọ lori iṣẹ-ṣiṣe tuntun, nitori awọn iwuwo pinpin ni a kọkọ kọ.
Kini idi ti igbagbe ajalu n ṣẹlẹ ni awọn nẹtiwọọki nkankikan?
Imọye n gbe ni awọn aye pinpin, nitorinaa ikẹkọ lori data tuntun yipada awọn iwọn kanna ati paarẹ ẹkọ iṣaaju.
Kini Isọdọtun Iwọn Elastic (EWC) ṣe lati dinku igbagbe?
EWC ṣe afikun ijiya isọdọtun ti o fa fifalẹ awọn imudojuiwọn si awọn paramita ti a ro pe o ṣe pataki fun awọn iṣẹ ṣiṣe atijọ, ifoju nipasẹ alaye Fisher.
Bawo ni iriri tun ṣe (atunṣe) ija gbagbe?
Atunṣe atunṣe ni awọn apẹẹrẹ ti o ti kọja (ti o fipamọ tabi ti ipilẹṣẹ) lakoko ti o nkọ awọn iṣẹ-ṣiṣe tuntun ki iṣẹ ṣiṣe atijọ ti ni fikun.
What does LoRA do to base-model weights when adding a task-specific adapter?
LoRA freezes base weights and trains low-rank updates for a task. This can reduce direct parameter interference but does not guarantee retention across every continual-learning sequence.
Tesiwaju kikọ
Jẹmọ awọn itọsọna
Awọn itọsọna diẹ sii ti a yan fun koko yii