InoteveraGaidhi rinotevera
Catastrophic Kukanganwa
Mutauro AI
Basics GUIDE
Kuramba Kudzidza uye Njodzi Kukanganwa
Continual learning updates a model over a sequence of tasks or data streams while trying to retain useful prior capabilities.
Teerera kugwaro iriAI-yakarondedzerwa · ~1 min
Pa peji ino1 min verenga
Pfupiso
Catastrophic forgetting is a common failure where learning new tasks degrades earlier performance.
Kudzika Kwakadzika
EWC uses a Fisher-information-based regularizer to discourage changes to parameters considered important for prior tasks. GEM uses episodic examples to constrain gradient updates; its guarantee concerns a local linear approximation to previous-task losses, so actual finite updates can still change performance. iCaRL stores exemplars, selects representatives with a herding procedure and classifies using per-class mean features. Replay methods revisit retained examples; these methods have different memory, privacy and compute tradeoffs. The stability-plasticity tradeoff describes balancing retention with learning new tasks.
Kuitwa muNyika yeChokwadi
Evaluate old and new tasks after each update.
Use replay samples when permitted by data policy.
Compare regularization methods such as EWC against fine-tuning.
Record task order and memory budget.
Ramangwana Rekuenderera Kudzidza uye Njodzi Kukanganwa
Continual-learning results depend on task sequence, model, data access, and evaluation protocol. Report both new-task learning and old-task retention.
Kuzvishandisa
Nei zvichikosha
- Sarudzo dzakajeka. Inokubatsira kuparadzanisa zvakajeka zvichemo zvehunyanzvi kubva mumutauro wekushambadzira.
- Mutengo uye bhajeti. Iwe unogona kubvunza zvirinani kuita mibvunzo usati washandisa mari kana nguva.
- Team uye workflow. Zvikwata zvine nzwisiso yakagovaniswa inoita zvirinani chigadzirwa, mutemo, uye sarudzo dzekudzidza.
Chenjera
- Zvikwata zvakasiyana zvinogona kushandisa izwi rimwechete zvakasiyana, saka tsanangura nzvimbo nekukurumidza.
- Benchmarks inogona kutaridzika yakasimba nepo chaiyo-yenyika kuita isina kuenzana.
- Kuregeredza mhando yedata uye zvirongwa zvekuongorora zvinowanzogadzira mhedzisiro isina kusimba.
Matanho anotevera
- Tanga netsanangudzo yemutauro wakajeka yemhedzisiro yaunoda.
- Sarudza metric imwe yekubudirira uye imwe yekutadza mamiriro usati waedzwa.
- Mhanya mutyairi mudiki ane data remumiriri, kwete demo rakakwenenzverwa.
- Gwaro uko Kuenderera Kudzidza uye Njodzi Kukanganwa kunobatsira uye uko nzira dzakareruka dziri nani.
Ramba Uchiongorora
Tsamba yemahara
Tora iyo yemazuva ese AI pfupiso
Nhatu dzakasimbiswa dzeAI nyaya mangwanani ega ega pakati pevhiki, dzakanyorwa neChirungu chakajeka. Yemahara zvachose, hapana ads.
Imwe email zuva rega rega revhiki. Bvisa kunyoresa kamwe chete. Hatimbotengese kana kugovera kero yako.
Zviedze iwe pachako
Take the Continual Learning and Catastrophic Forgetting quiz
Mhinduro yepakarepo pamhinduro yega yega, uye chitupa chinogovaniswa chine ID inobatika kana wapedza kosi.
Tsigira dzidzo yemahara yeAI. AI Understanding ndeye 501(c)(3) isingabatsiri - hapana ads, hapana paywall, zvachose. Ita chipo
Mibvunzo inowanzo bvunzwa
Chii chinonzi Continual Learning uye Catastrophic Forgetting?
Continual learning updates a model over a sequence of tasks or data streams while trying to retain useful prior capabilities. Catastrophic forgetting is a common failure where learning new tasks degrades earlier performance.
Chii chinonzi 'catastrophic forgetting'?
Kukanganwa kwakashata ndiko kurasikirwa kwakanyanya kwekuita kwekare-basa kana network yakagovaniswa uremu inodhindwa uchidzidza chimwe chinhu chitsva.
Chii chinoitwa neElastic Weight Consolidation (EWC)?
EWC inowedzera chirango (uchishandisa ruzivo rweFisher) iyo inomisa uremu hunoonekwa hwakakosha kumabasa ekare, kuderedza kukanganwa.
Nzira dzekudzokorora dzinorwisa sei kukanganwa?
Replay inosanganisa mienzaniso yakapfuura kuita mabhechi matsva kuitira kuti ma gradients aratidze mabasa ekare uye matsva, kuenzanisa data rekutanga rakabatanidzwa.
How does Gradient Episodic Memory (GEM) constrain a gradient update while learning a new task?
GEM projects updates using episodic-memory losses so the local first-order approximation does not increase loss on previous-task examples. This constraint is based on a local linearization and does not guarantee actual loss will never rise after every finite step.
Sei kusanyatsogadzirisa basa idzva kuchikonzera kukanganwa?
Unconstrained gradient inogadziridza nyora zvakare maremu akagovaniswa akananga kune itsva optimum, achisiya matunhu aive akanaka kune ekutanga mabasa.
Ramba uchidzidza
Mazano anoenderana
Mamwe madhairekitori akasarudzirwa nyaya iyi