Inside Artificialis - #10
Nov 01, 2022 9:01 am
Hey, . Welcome to the monthly version of the Artificialis newsletter!
A summary of what happened during the month, the best blogs of our Medium publication, latest news of our Discord server events, and recent news in the world of Artificial Intelligence and Machine Learning!
So seat back, take a cup of coffee, let's go over what happened this month.
First of all, a list of this month most viewed blog articles:
- Model Compression: an Introduction to Teacher-Student Knowledge Distillation, Alessandro
- How is AI used to Improve Customers' Experience? by Rahul
A little bit from me:
I accepted a job offer! I'm stepping up and I'll be working as a Computer Vision Engineer for NTT Data, a world-wide consulting company!
Moreover, I recently had the boost to dive into computer vision and optimization even more, and I'll dive into more advanced topics. Let me know if you have any interest in seeing something particularly!
AI in the world
Crossmodal-3600 — Multilingual Reference Captions for Geographically Diverse Images
Today we present and make publicly available the Crossmodal 3600 (XM3600) image captioning evaluation dataset as a robust benchmark for multilingual image captioning that enables researchers to reliably compare research contributions in this emerging field. XM3600 provides 261,375 human-generated reference captions in 36 languages for a geographically diverse set of 3600 images. We show that the captions are of high quality and the style is consistent across languages. [...]
UL2 20B: An Open Source Unified Language Learner
A novel language pre-training paradigm called Unified Language Learner (UL2) that improves the performance of language models universally across datasets and setups. UL2 frames different objective functions for training language models as denoising tasks, where the model has to recover missing sub-sequences of a given input. [...]
New European Political Party Is Led by an Artificial Intelligence
Introducing: The Synthetic Party, a new political party in Denmark that hopes to soon have a parliament seat. Oh, and by the way, its head honcho, Leader Lars, is actually an AI chatbot, and all of its policies are AI-derived. Cool? [...]
CircularNet: Reducing waste with Machine Learning
Enter what we call “CircularNet”, a set of models that lowers barriers to AI/ML tech for waste identification and all the benefits this new level of transparency can offer. Our goal with CircularNet is to develop a robust and data-efficient model for waste/recyclables detection, which can support the way we identify, sort, manage, and recycle materials across the waste management ecosystem. [...]
Colab's ‘Pay As You Go’ Offers More Access to Powerful NVIDIA Compute for Machine Learning
Google Colab is launching a new paid tier, Pay As You Go, giving anyone the option to purchase additional compute time in Colab with or without a paid subscription. This grants access to Colab’s powerful NVIDIA GPUs and gives you more control over your machine learning environment. [...]
Tip of the month
This month's tip is:
You got NANs during your training? Clip that gradient!
Gradient clipping, which was first introduced in recurrent neural networks and avoids exploding gradients is a great way to make your training more stable, especially if you have noisy data or high variance in your data.
'Till next month, you can find everyone here:
Have a fantastic month, !
If you'd like to support our community, and have access to millions of amazing articles and tutorials, consider subscribing to Medium's program via our link, we'll receive a small portion of your fee.
All of the money will be used to sponsor our Discord's events prizes!
