قابلیت جدیدی که کیوی نداشت رو برای ایرانی ها بهش اضافه کردم، دیگه میتونید از زبان فارسی استفاده کنید.

چند بار ارتباط گرفتم تا درستش کنند اما اونا برای ایرانی ها کاری نکردن خودم درستش کردم تا ماهم استفاده کنیم.

لطفاً نشر حداکثری، تا از قابلیت های این کتابخونه همه ی فارسی زبانان استفاده کنند.
github.com/goldaaa/kivyir

با تشکر از @core0day
کانال تلگرامش: t.me/kivyiran

➡️ MetaFormer Baselines for Vision

🖥 Github: https://github.com/sail-sg/metaformer

🗒 Paper: https://arxiv.org/abs/2210.13452v1

➡️ Dataset: https://paperswithcode.com/dataset/imagenet

#مقاله

Full Stack Deep Learning course edition is Marvelous, in case you haven’t checked out. Great content and presentation, and the course is FREE for everyone. All the lectures are available on YouTube.

✅ Lecture 1: Course Vision and When to Use ML
✅ Lecture 2: Development Infrastructure & Tooling
✅ Lecture 3: Troubleshooting & Testing
✅ Lecture 4 : Data Management
✅ Lecture 5 : Deployment
✅ Lecture 6: Continual Learning
✅ Lecture 7: Foundation Models
✅ Lecture 8: ML Teams and Project Management
✅ Lecture 9: Ethics

Check out the full videos and detailed notes on their website - https://fullstackdeeplearning.com/course/2022/.

Youtube Channel -
https://youtube.com/FullStackDeepLearning

Highly Efficient Real-Time Streaming and Fully On-Device Speaker Diarization with Multi-Stage Clustering


🖥 Github: https://github.com/wq2012/SpectralCluster

🗒 Paper: https://arxiv.org/abs/2210.13690v1

🔩 Speaker Diarization with LSTM: https://huggingface.co/datasets/poloclub/diffusiondb

#مقاله

Deep Learning Course, University of Geneva

A great deep learning intro course that covers various neural network architectures(ConvNets, MLPs, RNNs, attention, generative models) & techniques for training them. Really good notes & slides!

DL course: https://fleuret.org/dlc

⭐️ Masked Vision-Language Transformer in Fashion

🖥 Github: https://github.com/gewelsji/mvlt

🗒 Paper: https://arxiv.org/abs/2210.15110v1

➡️ Dataset: https://paperswithcode.com/dataset/fashion-gen

#مقاله

You don't need to buy a GPU for machine learning work!

There are other alternatives. Here are some:

1. Google Colab
2. Kaggle
3. Deepnote
4. AWS SageMaker
5. GCP Notebooks
6. Azure Notebooks
7. Cocalc
8. Binder
9. Saturncloud
10. Datablore
11. IBM Notebooks

Spend your time focusing on your problem.

#منابع

✳️ @AI_Python

معرفی ربات تلگرامی

http://bot.farhadhp.ir

Text-Only Training for Image Captioning using Noise-Injected CLIP

🖥 Github: https://github.com/davidhuji/capdec

🗒 Paper: https://arxiv.org/abs/2211.00575v1

➡️ Dataset: https://paperswithcode.com/dataset/flickrstyle10k

#مقاله

✳️ @AI_Python

What makes a productive #PhD student?

A. A SUPPORTIVE supervisor
B. SUFFICIENT salary each month
C. LIMITED working hours

That’s all needed for a PhD fellow to perform productively.

Link: https://doi.org/10.1016/j.respol.2022.104561


#مقاله

✳️ @AI_Python

Looking for a good machine learning course?

Applied Machine Learning
Cornell Tech, 2020.

100% Free. 80 videos.

Full playlist: https://youtube.com/playlist?list=PL2UML_KCiC0UlY7iCQDSiGDMovaupqc83

#فیلم #منابع #یادگیری_ماشین #کلاس_آموزشی
#MachineLearning

✳️ @AI_Python

Video lectures, University of Toronto MAT1841:
Mathematics of Massive Data Analysis: Fundamentals and Applications fall 2021, by Yun William Yu
https://courses.ywyu.net/MAT1841-2021-Fall/
https://www.youtube.com/playlist?list=PLME5LqfUcYzltPyDe-nQgwXrabqDU3oRD

#فیلم #منابع


✳️ @AI_Python

GoogleAI recently announced 3 ways they are planning scale Ai technologies.

1) Ai Model Supporting 1,000 languages with AI.

2) Empowering creators & artists with Image text-to-image model.

3) Addressing climate change and health challenges with AI.

To know more: https://blog.google/technology/ai/ways-ai-is-scaling-helpful/

✳️ @AI_Python

کتاب رایگان Computer Vision

"Computer Vision: Algorithms and Applications" by Richard Szeliski.

Read it on the author's website: https://szeliski.org/Book/

#کتاب #بینایی_کامپیوتر #منابع

✳️ @AI_Python

آموزش های شبکه عصبی با Andrej Karpathy

https://www.youtube.com/playlist?list=PLAqhIrjkxbuWI23v9cThsA9GvCAUhRvKZ

#منابع #فیلم #شبکه_عصبی #آموزش_کلاسی

✳️ @AI_Python

رابط کاربری مثل جوکه، اگه مجبور هستی توضیحش بدی یعنی آنقدرها هم خوب نیست!
@ai_python

Here are 10 common AI terms explained in an easily understandable way.

1. Classification
A Machine Learning task which seeks to classify data points into different groups (called targets or class labels) that are pre-determined by the training data. For example, if we have a medical dataset consisting of biological measurements...... (heart rate, body temperature, age, height, weight, etc.) and whether or not a person has a specific disease, we could train a classification model to predict whether or not a person has the disease given just the biological measurements.

2. Regression
A supervised learning task that tries to predict a numerical result given a data point. For example, giving the description of a house (location, number of rooms, energy label) and predicting the market price of the house.

3. Underfitting
A phenomenon in which a Machine Learning algorithm is not fitted well enough to the training data, resulting in low performance on both the training data and similar but distinct data.3. Underfitting cont. A common example of underfitting occurs when a neural network is not trained long enough or when there is not enough training data. The converse phenomenon is overfitting.

4. Overfitting
A phenomenon in which a Machine Learning algorithm is too fitted to the training data, making performance on the training data very high, but performance on similar but distinct data low due to poor generalizability.A common example of overfitting occurs when a neural network is trained for too long. The converse phenomenon is underfitting.

5. Cost function
This is what Machine Learning algorithms are trying to minimize to achieve the best performance. It is simply the error the algorithm makes over a given dataset. It is also sometimes referred to as “loss function.”

6. Loss function
A (generally continuous) value that is a computation-friendly proxy for the performance metric. It measures the error between values predicted by the model and the true values we want the model to predict.During training, this value is minimized. “Loss function” is sometimes used interchangeably with “cost function,” although the two are differentiated in some contexts.

7. Validation data
A subset of data that a model is not trained on but is used during training to verify that the model performs well on distinct data. Validation data is used for hyper parameter tuning in order to avoid over fitting.

8. Neural Network
A specific type of Machine Learning algorithm which can be represented graphically as a network, inspired by the way that biological brains work.The network represents many simple mathematical operations (addition, multiplication, etc.) that are combined to produce a complex operation that may perform a complicated task (e.g. identifying cars in an image).

9. Parameter
Generally refers to the numbers in a neural network or Machine Learning algorithm that are changed to alter how the model behaves (sometimes also called weights). If a neural network is analogous to a radio, providing the base structure of a system, then parameters are analogous to the knobs on the radio, which are tuned to achieve a specific behavior (like tuning in to a specific frequency). Parameters are not set by the creator of the model, rather, the values are determined by the training process automatically.

10. Hyperparameter
A value that takes part in defining the overall structure of a model or behavior of an algorithm. Hyperparameters are not altered by the model training process and are set ahead of time before training. Many potential values for hyperparameters are generally tested to find those that optimize the training process. E.g, in a neural network, the number of layers is a hyperparameter (not altered by training), whereas the values within the layers (“weights”) themselves are parameters (altered by training).If the model is a radio, then a hyperparameter would be the number of knobs on the radio, while the values of these knobs would be parameters.

#آموزش

✳️ @AI_Python

Paint-with-Words, Implemented with Stable diffusion

https://github.com/cloneofsimo/paint-with-words-sd

اصطلاح data-drift یا dataset drift که در فارسی به جابجایی داده یا رانش داده ترجمه می‌شود زمانی اتفاق می‌افتد که مجموعه داده مورد استفاده در آموزش مدل تفاوت زیادی با داده‌هایی که در زمان استقرار یا محیط عملیاتی ( اصطلاحا deploy یا production) مشاهده خواهد شد دارد و در نتیجه مدل شما نتایج نامطلوب و عجیب ایجاد کرده و عملکرد ضعیفی دربرخواهد داشت.

در مقاله‌ای جدید، تیمی از محققان روش خاصی را برای برخورد با این مشکل در زمینه داده‌های تصویری ارائه کردند:

"Data Models for Dataset Drift Controls in Machine Learning With Images"

Paper: https://arxiv.org/abs/2211.02578
Code: https://github.com/aiaudit-org/raw2logit
Dataset: https://paperswithcode.com/dataset/raw-microscopy-and-raw-drone

#MachineLearning #DeepLearning #ArtificialIntelligence #ML #DL #AI


#یادگیری_ماشین #مقاله

✳️ @AI_Python