Ishdan tashqari yaqin 3-4 haftadan beri bir pokistonlik professor bilan Deep Learning (Computer Vision) bo'yicha Research internship ham qilyapman. Research area asosan object detection bo'yicha.
Retina imagelardan Blood Vessellarni ajratib olish bo'yicha eksperiment qildim. Buni UNET bilan qildim. Quyida UNET haqida o'qib ko'rishingiz mumkin:
https://medium.com/@CereLabs/understanding-u-net-architecture-for-image-segmentation-74bef8caefee

Medium

Understanding U-Net Architecture For Image Segmentation

What is Image Segmentation?

(c)

Erkak kishi aytdimi bajaradi. Bajarmadimi, demak, hazillashgan.

B-bahona

Lex Fridman
Research Scientist @ MIT

Najot ta'lim'da ishni boshladik.
Hayrli qilsin.

Andrej Karpathy Research Scientist bo'libgina qolmay, youtube uchun yaxshi va sifatli kontent ham tayyorlaydi.
GPT yasash va backpropagation haqidagi videolarini ko'rib chiqqandim. O'zining micrograd deb nomlangan autograd engine'nini qurib ko'rsatgandi backpropagation haqidagi videosida.
Bundan tashqari stable diffusion, tokenization, wavenet haqida ham videolari bor.
Bu safar GPT-2ni yasashni tutorial qilibdi.
Noyob videolar.

Video

YouTube

Let's reproduce GPT-2 (124M)

We reproduce the GPT-2 (124M) from scratch. This video covers the whole process: First we build the GPT-2 network, then we optimize its training to be really fast, then we set up the training run following the GPT-2 and GPT-3 paper and their hyperparameters…

Assalomu aleykum barchaga.
Bir yangilik bilan bo'lishmoqchiman.

Najot ta'lim markazidan asosiy AI mentorlik uchun offer oldim.
Hayrli qilsin.
?

Ishdan tashqari ish ;)