@cas_sn02:

★CAS_SN★🇸🇳  ✪
★CAS_SN★🇸🇳 ✪
Open In TikTok:
Region: SN
Tuesday 07 July 2026 18:39:12 GMT
107206
5128
171
152

Music

Download

Comments

user6853005300790
user6853005300790 :
Genre yii la khamoul lou nit di amei confiance thie niome balenii vocal
2026-07-07 21:41:38
177
mara_luxury
Ndeye🌹❤️ :
Lèguie stp mame ak maman naniou diobo yeup am diam stp
2026-07-07 22:54:03
98
fashionhouse860
J-ta Cissé ngary :
Donc mame mo audio
2026-07-07 19:26:13
221
maamydiagne2
Xaritou yayam :
Dolene bayii maman rek athie
2026-07-07 20:41:38
251
theywillcome1
éveil conscience :
lalaké
2026-07-07 19:37:56
162
fatou.thiam6245
Fatou Thiam :
Di gardé ay audio juste pour téseunté thieye kaliphone
2026-07-07 21:18:15
146
sass69781
Sass :
ay yow tu nous fatiguée on est fatiguée depuis deux ans
2026-07-07 21:29:15
54
user4546674537175
user4546674537175 :
Na saf na saf 😂😂😂
2026-07-07 19:33:59
51
barbier92
Fama :
Mame yallah nala yallah same 🙏
2026-07-07 19:23:35
27
_mithiou
_mithiou :
Ça ne veut absolument rien dire franchement li moy lane audio dieuwaté ak audio wah entre deux personnes pourquoi diko tek
2026-07-07 22:23:42
24
1510ndieguen
Ndiéguénebisness :
maman seul niou deme rek
2026-07-08 00:39:18
5
aicha.aboubacryl.s
aicha aboubacryl sadex :
sa ne veux rien dire
2026-07-07 21:11:27
13
la.gazelle010
La gazelle :
Essaye d changer stp
2026-07-07 21:42:59
9
princessemamita24
Gueye Ndioro🎀😘 :
Diakhaleeeeeeeeeeeeeeeeeeee😳
2026-07-07 19:07:59
18
minabizz0
Min@✌️❤️😘 :
Pour le moment ok
2026-07-07 20:45:28
6
eleganceunique1
L’élégance unique 🔥 :
Dispo
2026-07-07 22:15:02
0
To see more videos from user @cas_sn02, please go to the Tikwm homepage.

Other Videos

*Why does an AI that can detect microscopic cancer fail just because the room lighting changes?** 🤯 
 
 It’s called the
*Why does an AI that can detect microscopic cancer fail just because the room lighting changes?** 🤯 It’s called the "Shortcut Learning" paradox. Instead of learning what an object actually is, neural networks are notoriously lazy—they memorize the background, the camera lens artifacts, or the shadows. When those change, the AI's confidence collapses. For years, the standard fix was to force the AI to be completely blind to these changes. But that destroys useful data. To fix 21st-century AI, we actually need an 18th-century physics principle. 💡 **The Quick-Win (Mental Model):** Think of AI training like a train moving forward on steel tracks. A sudden change in lighting is like a strong crosswind. Because the tracks hold the train perfectly perpendicular (90°) to the wind, the wind does *zero work* on the train's forward motion. We can build these exact "mathematical tracks" inside a neural network. By forcing the nuisance data to be perfectly orthogonal to the AI's decision path, the distraction exerts *zero first-order influence*. The AI still sees the lighting change, but it becomes geometrically irrelevant. Robustness without blindness. 🧠 **Want the full mathematical proof?** If you want to see how we translate d'Alembert’s Principle of Virtual Work into a PyTorch-ready loss function, I’ve written a complete academic deep-dive. 🔗 **Link in bio to read the full Substack article.** 👇 **Question for you:** What is the most ridiculous "shortcut" you’ve ever seen an AI take? (Like classifying a husky as a wolf just because there was snow in the background?) Let me know in the comments! #DeepLearning #MachineLearning #ComputerVision #Physics #Mathematics

About