MACHINE LEARNING

Eliminating Gender Bias in Sentiment Analysis Systems

By

–

16 November 2022 16h37

De-biasing sexist sentiment classifiers pic.twitter.com/QBLJtIknN6
— IBM Data, AI & Automation (@IBMData) 16 novembre 2022

De-biasing sexist sentiment classifiers

Testing Stock Prediction Models for Security Flaws

By

–

16 November 2022 16h37

Testing stock prediction models for security flaws 📈 pic.twitter.com/XO9AQCglr1
— IBM Data, AI & Automation (@IBMData) 16 novembre 2022

Testing stock prediction models for security flaws

Using AI-Generated Images to Enhance Machine Translation Models

By

–

16 November 2022 16h36

Training models on “hallucinated images”, like @OpenAI’s Dall-E, to improve machine translation pic.twitter.com/TM9hvBvixr
— IBM Data, AI & Automation (@IBMData) 16 novembre 2022

Training models on “hallucinated images”, like @OpenAI
’s Dall-E, to improve machine translation

Probabilistic Generative Modeling Enhances Machine Design Efficiency

By

–

16 November 2022 16h36

Designing machines using probabilistic generative modeling to bring more efficiency into the design process pic.twitter.com/h8BHvqfOHB
— IBM Data, AI & Automation (@IBMData) 16 novembre 2022

Designing machines using probabilistic generative modeling to bring more efficiency into the design process

AI Models Learn Emergent Languages Through Images

By

–

16 November 2022 16h36

Using images to teach #AI models emergent languages, making it easier to learn non-Indo-European languages 🗣️ pic.twitter.com/aaunITPKsl
— IBM Data, AI & Automation (@IBMData) 16 novembre 2022

Using images to teach #AI models emergent languages, making it easier to learn non-Indo-European languages

IBM Research Uses Synthetic Data to Accelerate AI Training

By

–

16 November 2022 16h36

Synthetic data are computer-generated examples that can augment or replace real data to speed up the training of #AI. Here’s how @IBMResearch is using this “fake data”

→ View original post on X — @learnopencv

YOLOv6 Underwater Trash Detection Training Experiment

By

@learnopencv

–

16 November 2022 15h38

Hundreds of aquatic species are being negatively impacted by the increased under water trash deposits. This is a real problem. We recently ran an underwater trash detection training experiment using YOLOv6.
Head over to our https://t.co/tSVje68CSR for the full read.#yolov6 #ai pic.twitter.com/vS6Ug105WJ
— Satya Mallick (@LearnOpenCV) 16 novembre 2022

Hundreds of aquatic species are being negatively impacted by the increased under water trash deposits. This is a real problem. We recently ran an underwater trash detection training experiment using YOLOv6.
Head over to our https://
learnopencv.com/yolov6-custom-
dataset-training/
… for the full read. #yolov6 #ai

→ View original post on X — @thom_wolf

Hugging Face Releases 1.3T Parameter Mixture-of-Experts Model

By

@thom_wolf

–

16 November 2022 15h16

We’ve heard mixture-of-experts (MoE) were in the air (GPT4??) so we’ve just added the first one in the transformers library for you to play with 🙂 With for nothing less than a 1.3 trillion parameters checkpoint model on the hub! The largest model on the hub at the moment