این تکست تو همه چی هم خوب مد شد:
Zeroshot text to 3D

لینک:
https://bluestyle97.github.io/dream3d/

✅ Google Stock Price Prediction using LSTM

✳️ In this blog, how we can perform Google’s stock price prediction by using Keras’ LSTMs model trained on past stocks data was explained.

🔗 BlogToLearn

🔗 Github

✳️ @ai_python

350 پروژه برای یادگیری NLP همراه با کدهای برنامه نویسی آنها

#پردازش_زبان_طبیعی #کتاب #آموزش_کلاسی

✅ @AI_Python

در این مقاله شما یاد خواهید گرفت:
🔸پردازش زبان طبیعی چیست و چطور NLP را یادبگیرید؟
🔸پردازش زبان طبیعی برای چه کارهای استفاده میشود؟ و اهمیت NLP در چیست ؟
🔸استفاده پردازش زبان طبیعی برای چیست ؟
🔸تکنیکهای مورد استفاده در NLP
🔸چندتا از مدلهای پرکاربرد در NLP
🔸برنامه نویسی و فریمورکهای مورد استفاده در NLP
🔸 مناقشات پیرامون پردازش زبان طبیعی (NLP)

🔹 مقاله

#پردازش_زبان_طبیعی #کتاب #آموزش_کلاسی #پایتون

✅ @AI_Python

✅ Image Captioning using Deep Learning

✳️ In this blog, The implementation of the Image Captioning project which is a very advanced project was explained . The combination of LSTMs and CNNs for this use case was reflected.

🔗 BlogToLearn
🔗 Github

✳️ @ai_python

کورس جدید گروه Andrew NG

Machine Learning Engineering for Production

آموزش تنسرفلو

New Courses: Machine Learning Engineering for Production

#کلاس_آموزشی #یادگیری_ماشین #منابع #فیلم

✅ @AI_Python

✅ What’s new in TensorFlow 2.11?

✳️ TensorFlow 2.11 has been released! Highlights of this release include enhancements to DTensor, the completion of the Keras Optimizer migration, the introduction of an experimental StructuredTensor, a new warmstart embedding utility for Keras, a new group normalization Keras layer, native TF Serving support for TensorFlow Decision Forest models, and more. Let's take a look at these new features.

✳️ BlogToLearn

✳️ @ai_python

۵ سایت یوتیوب برای یادگیری هوش مصنوعی

#منابع #کلاس_آموزشی #فیلم #هوش_مصنوعی #یادگیری_ماشین

✅ @ai_python

خلاصه ای جامع روشهای یادگیری آمار برای رشته #آمار که قصد ورود به #هوش_مصنوعی دارند

#منابع #کتاب

✅ @ai_python

ویرایش جدید کتاب
Probabilistic Machine Learning: Advanced Topics


#کتاب #منابع


✅ @AI_Python

TextDescriptives: A Python package for calculating a large variety of statistics from text


🖥 Github: https://github.com/HLasse/TextDescriptives

⏩ Paper: https://arxiv.org/abs/2301.02057v1

➡️ Docs: https://github.com/HLasse/TextDescriptives

#مقاله

✅ @AI_Python

🟣چند تا وبسایت کاربردی و مفید

وبسایت تلفظ صحیح:
howjsay.com
وبسایت پرفریز کردن متن:
spinbot.com
quillbot.com
وبسایت تقویت لسنینگ:
listenaminute.com
وبسایت تقویت ریدینگ:
agendaweb.org/reading/reading-pdf
وبسایت تقویت اسپیکینگ:
englishtivi.com/advanced-english-phrases/

✅ @AI_Python

Text2Poster: Laying out Stylized Texts on Retrieved Images

Github: https://github.com/chuhaojin/text2poster-icassp-22

Paper: https://arxiv.org/abs/2301.02363v1

#مقاله

✅ @AI_Python

هوش مصنوعی قرار نیست جای شما رو بگیره، ولی کسی که هوش مصنوعی می‌دونه چرا!

اسلایدهای دوره LLM دانشگاه استفورد
CS324 - Large Language Models
https://stanford-cs324.github.io/winter2022/

#کلاس_آموزشی #منابع #مقاله

✅ @AI_Python

✅ Generating cifar-10 fake images using Deep Convolutional Generative Adversarial Networks (DCGAN)


✳️ This post will explain that how can we build some real-looking fake images, using Deep Convolutional Generative Adversarial Networks or DCGANs.

✳️ BlogToLearn
✳️ Github

✳️ @ai_python

همینمون مونده بود 😐

You want to get into AI and computer vision but don’t know where to begin?

Here are some of the lessons I learned that will help you get started.

Unless you’re looking to become the next Geoffrey Hinton or develop new algorithms, understanding the math behind AI is not all that important!

Instead focus on developing an intuitive understanding of neural networks. I hear you thinking, but how? Well, start by spending a lot of time training networks! Which means you should stay away from ‘Easy Button’ platforms that do all the training for you (like Google AutoML), at least until you know what you are doing. 

Try out different public datasets and perform your own experiments by changing learning rates, removing samples or try alternative optimizers.. Sit there watching epoch by epoch, seeing how networks converge. Over time you will develop a feel for the training process and most likely a profound love for ‘early stoppage’.

Learn Python (NumPy!) and OpenCV. If ever there were two technologies critical to daily life as a data scientist, it’s them. Now I don’t mean you have to learn their manuals front to back. Instead focus on the basics, enough so that you can understand open source projects and example code. The rest will come with time. 

There are a lot of different AI training frameworks, but in reality you only need one: PyTorch. It’s the most amazing machine learning framework out there and most papers are implemented in it. Stay away from TensorFlow, it’s a hot mess and will do nothing but upset you.

Don’t bother chasing the latest and greatest algorithms. Yes, it’s important to stay up to date and read. But not everything under the sun is worth implementing. Develop a list of your favorite architectures and just stick with them.

Want to know the secret to what makes a good architecture? A network that is not fancy! The best networks stick with very basic operations that have been around for years. Deploying models on your favorite device can be a real nightmare otherwise.

Finally I highly recommend that you participate in online competitions, such as Kaggle, where you can work on real-world data science and machine learning challenges. This will not only help you develop your skills, but also give you the opportunity to showcase your work and connect with others.

Are you still at the absolute beginning of your journey? You can start by following the excellent PyTorch tutorials at:  https://pytorch.org/tutorials/beginner/basics/intro.html

#منابع


✳️ @ai_python