Semi-supervised learning made simple with self-supervised clustering [CVPR 2023]

🖥 Github: https://github.com/pietroastolfi/suave-daino

⏩ Paper: https://arxiv.org/pdf/2306.07483v1.pdf

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

https://news.1rj.ru/str/DataScienceT

🌐 WizMap: Scalable Interactive Visualization for Exploring Large Machine Learning Embeddings

🖥 Github: https://github.com/poloclub/wizmap

⭐️ Colab: https://colab.research.google.com/drive/1GNdmBnc5UA7OYBZPtHu244eiAN-0IMZA?usp=sharing

📕 Paper: https://arxiv.org/abs/2306.09328v1

🔗 Web demo: https://poloclub.github.io/wizmap.

https://news.1rj.ru/str/DataScienceT

How do Transformers work?

All the Transformer models mentioned above (GPT, BERT, BART, T5, etc.) have been trained as language models. This means they have been trained on large amounts of raw text in a self-supervised fashion. Self-supervised learning is a type of training in which the objective is automatically computed from the inputs of the model. That means that humans are not needed to label the data!

This type of model develops a statistical understanding of the language it has been trained on, but it’s not very useful for specific practical tasks. Because of this, the general pretrained model then goes through a process called transfer learning. During this process, the model is fine-tuned in a supervised way — that is, using human-annotated labels — on a given task

🔗 Read More

🌸 https://news.1rj.ru/str/DataScienceT

Data Science With Python Workflow Cheat Sheet

Creator: business Science
Stars ⭐️: 75
Forked By: 38

https://github.com/business-science/cheatsheets/blob/master/Data_Science_With_Python_Workflow.pdf

https://news.1rj.ru/str/DataScienceT

80+ Jupyter Notebook tutorials on image classification, object detection and image segmentation in various domains
📌 Agriculture and Food
📌 Medical and Healthcare
📌 Satellite
📌 Security and Surveillance
📌 ADAS and Self Driving Cars
📌 Retail and E-Commerce
📌 Wildlife

Classification library
https://github.com/Tessellate-Imaging/monk_v1

Notebooks - https://github.com/Tessellate-Imaging/monk_v1/tree/master/study_roadmaps/4_image_classification_zoo

Detection and Segmentation Library
https://github.com/Tessellate-Imaging/

Monk_Object_Detection
Notebooks: https://github.com/Tessellate-Imaging/Monk_Object_Detection/tree/master/application_model_zoo

https://news.1rj.ru/str/DataScienceT

Choose JOBITT! Receive +10% of your first salary as a bonus from JOBITT!
Find your dream job with JOBITT! Get more, starting with your first paycheck! Find many job options on our Telegram channel: https://news.1rj.ru/str/ujobit

📌 LOMO: LOw-Memory Optimization

New optimizer, LOw-Memory Optimization enables the full parameter fine-tuning of a 7B model on a single RTX 3090, or a 65B model on a single machine with 8×RTX 3090, each with 24GB memory.

🖥 Github: https://github.com/OpenLMLab/LOMO/tree/main

📕 Paper: https://arxiv.org/pdf/2306.09782.pdf

🔗 Dataset: https://paperswithcode.com/dataset/superglue

https://news.1rj.ru/str/DataScienceT

Jumanji: a Diverse Suite of Scalable Reinforcement Learning Environments in JAX

Jumanji is helping pioneer a new wave of hardware-accelerated research and development in the field of RL.

🖥 Github: https://github.com/instadeepai/jumanji

📕 Paper: https://arxiv.org/abs/2306.09884v1

🔗 Dataset: https://paperswithcode.com/dataset/mujoco

https://news.1rj.ru/str/DataScienceT

Google just dropped Generative AI learning path with 9 courses:

🤖: Intro to Generative AI
🤖: Large Language Models
🤖: Responsible AI
🤖: Image Generation
🤖: Encoder-Decoder
🤖: Attention Mechanism
🤖: Transformers and BERT Models
🤖: Create Image Captioning Models
🤖: Intro to Gen AI Studio

🌐 Link: https://www.cloudskillsboost.google/paths/118

https://news.1rj.ru/str/DataScienceT

YOLOv8 is the newest state-of-the-art YOLO model that can be used for object detection, image classification, and instance segmentation tasks. YOLOv8 includes numerous architectural and developer experience changes and improvements over YOLOv5.

Code:
https://github.com/ultralytics/ultralytics

What's New in YOLOv8 ?
https://blog.roboflow.com/whats-new-in-yolov8/

Yolov8 Instance Segmentation (ONNX):
https://github.com/ibaiGorordo/ONNX-YOLOv8-Instance-Segmentation

https://news.1rj.ru/str/DataScienceT

⭐️ 15 Best Machine Learning Cheat Sheet ⭐️

1- Supervised Learning

https://github.com/afshinea/stanford-cs-229-machine-learning/blob/master/en/cheatsheet-supervised-learning.pdf

2- Unsupervised Learning

https://github.com/afshinea/stanford-cs-229-machine-learning/blob/master/en/cheatsheet-unsupervised-learning.pdf

3- Deep Learning

https://github.com/afshinea/stanford-cs-229-machine-learning/blob/master/en/cheatsheet-deep-learning.pdf

4- Machine Learning Tips and Tricks

https://github.com/afshinea/stanford-cs-229-machine-learning/blob/master/en/cheatsheet-machine-learning-tips-and-tricks.pdf

5- Probabilities and Statistics

https://github.com/afshinea/stanford-cs-229-machine-learning/blob/master/en/refresher-probabilities-statistics.pdf

6- Comprehensive Stanford Master Cheat Sheet

https://github.com/afshinea/stanford-cs-229-machine-learning/blob/master/en/super-cheatsheet-machine-learning.pdf

7- Linear Algebra and Calculus

https://github.com/afshinea/stanford-cs-229-machine-learning/blob/master/en/refresher-algebra-calculus.pdf

8- Data Science Cheat Sheet

https://s3.amazonaws.com/assets.datacamp.com/blog_assets/PythonForDataScience.pdf

9- Keras Cheat Sheet

https://s3.amazonaws.com/assets.datacamp.com/blog_assets/Keras_Cheat_Sheet_Python.pdf

10- Deep Learning with Keras Cheat Sheet

https://github.com/rstudio/cheatsheets/raw/master/keras.pdf

11- Visual Guide to Neural Network Infrastructures

http://www.asimovinstitute.org/wp-content/uploads/2016/09/neuralnetworks.png

12- Skicit-Learn Python Cheat Sheet

https://s3.amazonaws.com/assets.datacamp.com/blog_assets/Scikit_Learn_Cheat_Sheet_Python.pdf

13- Scikit-learn Cheat Sheet: Choosing the Right Estimator

https://scikit-learn.org/stable/tutorial/machine_learning_map/

14- Tensorflow Cheat Sheet

https://github.com/kailashahirwar/cheatsheets-ai/blob/master/PDFs/Tensorflow.pdf

15- Machine Learning Test Cheat Sheet

https://www.cheatography.com/lulu-0012/cheat-sheets/test-ml/pdf/

https://news.1rj.ru/str/DataScienceT

REBEL: Relation Extraction By End-to-end Language generation

REBEL is a seq2seq model that simplifies Relation Extraction.

🖥 Github: https://github.com/Babelscape/rebel

⭐️Demo: https://huggingface.co/spaces/Babelscape/rebel-demo

⭐️ Hugging face: https://huggingface.co/Babelscape/rebel-large

📕 Paper: https://arxiv.org/abs/2306.09802v1

🔗Dataset: https://huggingface.co/Babelscape/rebel-large

https://news.1rj.ru/str/DataScienceT

Semi-supervised learning made simple with self-supervised clustering [CVPR 2023]

🖥 Github: https://github.com/Ruixinhua/ExplainableNRS

⏩ Paper: https://arxiv.org/pdf/2306.07506v1.pdf

💨 Dataset: https://paperswithcode.com/dataset/mind

https://news.1rj.ru/str/DataScienceT

Get started in Data Science with Microsoft's FREE course for beginners.

- 10 weeks
- 20 lessons
- Lecture notes
- 100% FREE

https://microsoft.github.io/Data-Science-For-Beginners/

https://news.1rj.ru/str/DataScienceT

Fine-tuning MMS Adapter Models for Multi-Lingual ASR

MMS' Adapter training is both more memory efficient, more robust and yields better performance for low-resource languages.

🤗 Post: https://huggingface.co/blog/mms_adapters

🖥 Colab: https://colab.research.google.com/github/patrickvonplaten/notebooks/blob/master/Fine_Tune_MMS_on_Common_Voice.ipynb

🖥 Github: https://github.com/facebookresearch/fairseq/tree/main/examples/mms/asr

⭐️ Demo: https://huggingface.co/spaces/facebook/MMS

📕 Paper: https://huggingface.co/papers/2305.13516

https://news.1rj.ru/str/DataScienceT

Building Transformer Models with Attention Crash Course. Build a Neural Machine Translator in 12 Days

https://machinelearningmastery.com/building-transformer-models-with-attention-crash-course-build-a-neural-machine-translator-in-12-days/

https://news.1rj.ru/str/DataScienceT

⭐️ Text-Guided Adversarial Makeup 🫣

Novel facial privacy protection via adversarial latent codes. Makeup vs Face Recognition.

🌐 Review: https://t.ly/pBCP

🌐 Paper: arxiv.org/pdf/2306.10008.pdf

🔥 Code: github.com/fahadshamshad/Clip2Protect

https://news.1rj.ru/str/DataScienceT