چطور رزومه و کاور لتر حرفه ای بنویسید:

https://hwpi.harvard.edu/files/ocs/files/hes-resume-cover-letter-guide.pdf

#اپلای

✅ @AI_Python

کانولوشن چطوری کار میکنه؟

یک مدل دیگه باز از طرف openai معرفی شد که می‌تونه متن رو به آبجکت سه بعدی تبدیل کنه.
به این صورت که به صورت متن بهش میگید چی میخواهید اونم براتون جنریت می‌کنه.


https://github.com/openai/point-e

اسم من میثمه،
در این کانال فقط چیزهایی که به نظر خودم جالب هستند رو پست میکنم.
هوش مصنوعی یکی از موضوعاتی هست که در موردش می‌نویسم.
دوست داشتید دنبال کنید دوست نداشتید میوت نکنید لفت بدید.
مرسی.

@ai_person

Generalized Decoding for Pixel, Image, and Language


🖥 Github: https://github.com/microsoft/X-Decoder

Hugging Face Demo: https://huggingface.co/spaces/xdecoder/Demo

⭐️ Project: https://x-decoder-vl.github.io/

⏩ Paprer: https://arxiv.org/pdf/2212.11270.pdf

✔️ Dataset: https://paperswithcode.com/dataset/visual-genome

#مقاله

✅ @AI_Python

🔥 Training neural networks 𝘄𝗶𝘁𝗵𝗼𝘂𝘁 𝗯𝗮𝗰𝗸𝗽𝗿𝗼𝗽?
Geoffrey Hinton proposed a forward-forward (FF) algorithm at this year's NeurIPS.

The idea is inspired by the realization that there is very little to no evidence that mammal brains are performing back-prop-like operations when learning. Are mammal brains strictly feed-forward? Maybe. Paper Link: https://www.cs.toronto.edu/~hinton/FFA13.pdf

Want to try FF yourself? Now you can do it in PyTorch!

Checkout it's now available on #github :
https://github.com/mohammadpz/pytorch_forward_forward

#مقاله

✅ @AI_Python

3D Highlighter: Localizing Regions on 3D Shapes via Text Descriptions


🖥 Github: https://github.com/threedle/3DHighlighter

⭐️ Project: https://threedle.github.io/3DHighlighter/

⏩ Paprer: https://arxiv.org/abs/2212.11263

#مقاله

✅ @AI_Python

✅ Text Autoencoder (RNN) to generate news headlines

✅ The idea is similar to the kind of image autoencoder we built in lecture: we will have an encoder that maps a news headline to a vector embedding, and then a decoder that reconstructs the news headline. Both our encoder and decoder networks will be Recurrent Neural Networks, so that you have a chance to practice building a neural network that takes a sequence as an input a neural network that generates a sequence as an output.

✳️ Github Link

✳️ @ai_python

Brain tumor detection and segmentation from MRI images using CNN and Unet models.

The CNN model is used to detect whether a tumor is there or not. After 15 epochs of training, the calculated accuracy is about 99.6%.
The U-net model is used to segment tumors in MRI images of the brain. After 10 epochs of training, the calculated accuracy is about 98%.
These deep neural networks are implemented with Keras functional API. Use the trained models to detect and segment tumors on brain MRI images. The result is satisfactory.

You can download my U-net trained model from: "" and CNN trained model from "".

To access the codes, refer to my GitHub.

GitHub:

LinkedIn

Website

#آموزش