Free AI library

Nka na ụzụ nduFree forever.

177 plain-English guides, structured learning paths, and an open library — built by an independent 501(c)(3) nonprofit so anyone can understand modern AI.

177Ntuziaka efu
1Topic tracks
~2 minPer guide
~6hReading time

Bido ebe a

Ise outcome-based courses

Each course includes explicit outcomes, mapped competencies, practice activities, and an applied capstone.

Topic tracks

Browse by track

Jump into the area you care about. Every track has multiple plain-English guides.

Ihe ndị bụ isiIsi echiche: ka AI si arụ ọrụ na ọkwa dị elu.84 ndu Asụsụ AILLMs, NLP, ChatGPT, mkpali, na nghọta ederede.155 ndu Visual AIỌgbọ onyonyo, ọhụụ kọmputa, vidiyo, na imewe.133 ndu Audio AIOlu, egwu, pọdkastị na ọdịyo-mbụ AI.117 ndu Companieslọ ọrụProfaịlụ nke OpenAI, Anthropic, Google, Meta, na ndị ọzọ.121 ndu NgwaKedu ka AI si egosipụta na nzuzo, ọchụchọ, ndị nnọchite, na ndụ kwa ụbọchị.111 ndu Ụlọ ọrụAI na ahụike, ego, agụmakwụkwọ, ike na ndị ọzọ.91 ndu Nka na ụzụChips, nlegharị anya nke ọma, RAG, vectors na akụrụngwa AI.177 ndu Ọha mmadụỌgbaghara, nzuzo, nwebisiinka, nchekwa na ọdịnihu AI.30 ndu

Full library

Nduzi niile

177 nke 1019 egosiputara ntuziaka. Wepụta site na egwu ma ọ bụ chọọ n'elu.

Nka na ụzụ

Nchekwa ngwa ngwa AI

Prompt security addresses attempts to make a language-model application treat untrusted content as instructions or disclose information it should protect.

2 min gụọGụọ
Nka na ụzụ

Njikwa data AI

AI data governance assigns responsibility and rules for how data is collected, used, shared, retained, and corrected throughout an AI system.

2 min gụọGụọ
Nka na ụzụ

AI Cloud Architecture

Ihe owuwu igwe ojii AI na-ahazi mkpokọta, nchekwa, ịkparịta ụka n'Ịntanet, ụdị na ọrụ ngwa n'ime sistemụ arụmọrụ maka ibu ọrụ AI.

2 min gụọGụọ
Nka na ụzụ

BYOL na nlekọta onwe onye na-adịghị agbanwe agbanwe

BYOL (Bootstrap Your Own Latent) na-amụta ihe ngosi onyonyo bara uru na-enweghị akara ọ bụla yana, ihe ijuanya, na-enweghị atụ na-adịghị mma.

2 min gụọGụọ
Nka na ụzụ

Barlow ejima na mbelata redundancy

Barlow Twins bụ usoro a na-ahụ maka onwe ya nke na-amụta ihe nnọchianya site n'ime ka njikọ njikọ dị n'etiti echiche abụọ agbakwunyere nso na njirimara…

2 min gụọGụọ
Nka na ụzụ

Ịkpọ aha ụgha na ọzụzụ onwe

Pseudo-labeling bụ usoro a na-ahụ maka ọkara ebe ihe atụ a zụrụ n'obere akara akara na-ewepụta akara nke ya maka data enweghị akara, wee zụọ ndị ahụ…

2 min gụọGụọ
Nka na ụzụ

Idezi n'otu n'otu na mmụta na-elekọta ọkara

Idozi n'otu n'otu na-akuziri ihe nlere iji nye otu azịza ahụ mgbe ntinye enweghị akara na-akpaghasị n'ụzọ dị nta na-echekwa akara.

2 min gụọGụọ
Nka na ụzụ

Ịkekọrịta Parameter siri ike na netwọkụ ọrụ ọtụtụ

Nkesa oke ike bụ ụdị mmụta mmụta ọtụtụ ọrụ dị iche iche ebe ọtụtụ ọrụ na-ekekọrịta otu ọkwa zoro ezo wee kewaa n'ime 'isi' mmepụta dị iche iche…

2 min gụọGụọ
Nka na ụzụ

Gating na ụzọ na Mgbakọ Ọnọdụ

Ịgba ọsọ na ịkwọ ụgbọ mmiri na-eme ka netwọkụ akwara rụọ ọrụ naanị akụkụ ọ chọrọ maka ntinye ọ bụla kama ịmegharị ihe nlereanya ahụ oge ọ bụla.

2 min gụọGụọ
Nka na ụzụ

Gumbel-Softmax na Reparameterization

Gumbel-Softmax bụ aghụghọ nke na-ahapụ netwọkụ akwara ozi 'nlere anya' site na ngalaba dị iche iche ebe a ka na-azụ ya site na mgbada gradient.

2 min gụọGụọ
Nka na ụzụ

Nke kwụ ọtọ-Sitemato

The Straight-Through Estimator (STE) bụ aghụghọ dị mfe maka netwọk ọzụzụ nke nwere usoro siri ike na-enweghị isi dị ka ịgbachi ma ọ bụ ọnụ ụzọ.

2 min gụọGụọ
Nka na ụzụ

Netwọk ugboro ugboro abụọ

Netwọk na-emegharị ugboro abụọ na-agụ usoro ma na-aga n'ihu na azụ, ya mere nnochite anya ọnọdụ ọ bụla na-esetịpụ gburugburu site n'oge gara aga na ọdịnihu.

2 min gụọGụọ

Ọgụchachara? Gopụta ya.

Check what you learned with a topic quiz, then explore our structured courses or work toward a certificate. Every guide stays free to read.

Nwalee ihe ị mụtaraNweta asambodoNye OnyinyeGụọ ebumnuche anyị