Inside Artificialis - #8
Aug 30, 2022 9:21 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:
- DropBlock: A better Dropout for CNN's, Alessandro Lamberti
- Writing Snake in 12 Lines of Pytorch, Elias F. Fyksen
- ViT - VisionTransformer, a Pytorch implementation, Alessandro Lamberti
A little bit from me:
As you might know, I'm building Hydra AI, a multi-endpoint Machine Learning infrastructure for image analysis, facial attributes analysis, multi-label object detection and NLP tasks.
Check it out on RapidAPI.
AI in the world
BlenderBot 3 is capable of searching the internet to chat about virtually any topic, and it’s designed to learn how to improve its skills and safety through natural conversations and feedback from people “in the wild.” Most previous publicly available datasets are typically collected through research studies with annotators that can’t reflect the diversity of the real world.
Stable Diffusion - Public release
Stable Diffusion is a text-to-image model that will empower billions of people to create stunning art within seconds. It is a breakthrough in speed and quality meaning that it can run on consumer GPUs. You can see some of the amazing output that has been created by this model without pre or post-processing on this page.
This Robot Dog Has an AI Brain and Taught Itself to Walk in Just an Hour
Pure reinforcement learning algorithms need too much trial and error to learn skills for them to train in the real world. By filtering out less successful actions in advance, the world model allows the robot to more efficiently figure out what works. “Learning world models from past experience...
At SIGGRAPH, NVIDIA CEO Jensen Huang Illuminates Three Forces Sparking Graphics Revolution
In addition, NVIDIA announced a set of simulation-ready USD assets, designed for use in industrial digital twins and AI training workflows. Huang called Omniverse “a USD platform, a toolkit for building metaverse applications, and a compute engine to run virtual worlds.” The latest version packs...
Advancing conservation with AI-based facial recognition of turtles
Protecting the ecosystems around us is critical to safeguarding the future of our planet and all its living citizens. Fortunately, new artificial intelligence (AI) systems are making progress in conservation efforts worldwide, helping tackle complex problems at scale – from studying the behaviour of animal communities in the Serengeti to help conserve the diminishing ecosystem, to spotting poachers and their wounded prey to prevent species going extinct.
Tip of the month
This is a new format I'd like to bring into the newsletter, let me know if you find it useful.
This month's tip is:
PYTORCH ASYNC DATA LOADING
The PyTorch data loader has the num_workers keyword.
If you set that over zero, it means that it can now use the CPU to process data while you are training your network on the GPU.
It's asynchronous and often it's faster.
'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!
